Coding (general)
Rank coding models and agents on general software tasks: code generation, repository-level SWE, and terminal work
Ranking groups use separate scales. Compare configurations only inside the same group; EvalRank never flattens unlike systems into one leaderboard.
Cross-benchmark consensus
One merged ranking of models by where they place across this topic's benchmark boards. Derived from the boards below, not a calibrated top set; it updates as sources are re-scraped.
| Rank | Model | Score | Benchmarks |
|---|---|---|---|
| 1 | gpt-6-astra | 3.382 | 4 |
| 2 | claude-opus-5 | 3.154 | 4 |
| 3 | claude-fable-5 | 3.114 | 4 |
| 4 | claude-opus-5.5 | 2.880 | 3 |
| 5 | gpt-5.6-sol | 2.639 | 4 |
| 6 | claude-sonnet-5.5 | 2.621 | 3 |
| 7 | claude-fable-5.1 | 2.486 | 3 |
| 8 | glm-5.3 | 2.344 | 4 |
| 9 | gemini-3.8-flash | 2.218 | 4 |
| 10 | kimi-k3 | 2.110 | 4 |
| 11 | gpt-6.1-sol | 2.095 | 3 |
| 12 | gpt-6-sol | 2.078 | 3 |
| 13 | grok-4.6 | 2.063 | 4 |
| 14 | gemini-3.7-flash | 1.946 | 4 |
| 15 | gpt-5.6-terra | 1.896 | 4 |
| 16 | gpt-5.5 | 1.703 | 3 |
| 17 | claude-opus-4.8 | 1.663 | 4 |
| 18 | gpt-5.6-luna | 1.407 | 4 |
| 19 | step-5-preview | 1.293 | 2 |
| 20 | qwen3.8 | 1.239 | 3 |
| 21 | claude-sonnet-5 | 1.236 | 3 |
| 22 | grok-4.5 | 1.225 | 3 |
| 23 | grok-4.7 | 1.179 | 2 |
| 24 | gpt-6-luna | 1.091 | 3 |
| 25 | muse-spark-1.1 | 1.082 | 2 |
| 26 | glm-5.3-flash | 1.074 | 3 |
| 27 | muse-spark-1.2 | 1.033 | 2 |
| 28 | deepseek-v4.1-flash-max livebench-agentic-coding:deepseek-v4.1-flash | 0.970 | 1 |
| 29 | gpt-5.4 | 0.965 | 2 |
| 30 | claude-opus-5.5-max-effort livebench-agentic-coding:claude-opus-5.5-max-effort | 0.941 | 1 |
| 31 | muse-spark-1.3 | 0.921 | 1 |
| 32 | claude-fable-5.1-max-effort livebench-agentic-coding:claude-fable-5.1-max-effort | 0.913 | 1 |
| 33 | gemini-3.1-pro-preview | 0.908 | 2 |
| 34 | fable 5 [high] swe-rebench:fable 5 [high]__tools | 0.889 | 1 |
| 35 | claude-opus-5.5-xhigh-effort livebench-agentic-coding:claude-opus-5.5-xhigh-effort | 0.886 | 1 |
| 36 | claude-opus-4.7 | 0.880 | 2 |
| 37 | gemini-3.6-flash | 0.864 | 3 |
| 38 | claude-opus-5-max-effort livebench-agentic-coding:claude-opus-5-max-effort | 0.859 | 1 |
| 39 | deepseek-v4-pro | 0.855 | 4 |
| 40 | deepseek-v4-flash-vision-exp livebench-agentic-coding:deepseek-v4-flash-vision-exp | 0.833 | 1 |
| 41 | qwen3.8-max livebench-agentic-coding:qwen3.8 | 0.808 | 1 |
| 42 | grok 4.5 [high] swe-rebench:grok 4.5 [high]__tools | 0.789 | 1 |
| 43 | smaug-agentic livebench-agentic-coding:smaug-agentic | 0.784 | 1 |
| 44 | muse-spark-1.3-xhigh livebench-agentic-coding:muse-spark-1.3 | 0.760 | 1 |
| 45 | kimi-k3 livebench-agentic-coding:kimi-k3 | 0.737 | 1 |
| 46 | gemini-4-argon | 0.722 | 1 |
| 47 | claude-fable-5-max-effort livebench-agentic-coding:claude-fable-5-max-effort | 0.714 | 1 |
| 48 | deepseek-v4-pro-0813 | 0.705 | 3 |
| 49 | opus 5 [high] swe-rebench:opus 5 [high]__tools | 0.700 | 1 |
| 50 | qwen3.8-flash-next livebench-agentic-coding:qwen3.8-flash-next | 0.692 | 1 |
| 51 | swe-2 | 0.673 | 1 |
| 52 | qwen3.8.27b livebench-agentic-coding:qwen3.8.27b | 0.671 | 1 |
| 53 | deepseek-v4.1-flash | 0.664 | 2 |
| 54 | smaug-flash livebench-agentic-coding:smaug-flash | 0.650 | 1 |
| 55 | glm-5.2 | 0.642 | 3 |
| 56 | glm-5.3 livebench-agentic-coding:glm-5.3 | 0.630 | 1 |
| 57 | glm-5.2 [high] swe-rebench:glm-5.2 [high]__tools | 0.619 | 1 |
| 58 | deepseek-v4-flash-0731 | 0.610 | 3 |
| 59 | smaug-mini livebench-agentic-coding:smaug-mini | 0.610 | 1 |
| 60 | claude-sonnet-5-xhigh-effort livebench-agentic-coding:claude-sonnet-5-xhigh-effort | 0.590 | 1 |
| 61 | kimi-k2.7-code | 0.572 | 3 |
| 62 | muse-spark-1.1-xhigh livebench-agentic-coding:muse-spark-1.1 | 0.571 | 1 |
| 63 | gemini-3.5-flash | 0.569 | 2 |
| 64 | gemini-3.7-flash-high livebench-agentic-coding:gemini-3.7-flash | 0.553 | 1 |
| 65 | gpt-5.6 sol [medium] swe-rebench:gpt-5.6 sol [medium]__tools | 0.545 | 1 |
| 66 | kimi-k2.6 | 0.535 | 1 |
| 67 | gpt-5.4-mini | 0.535 | 2 |
| 68 | muse-spark-1.2-xhigh livebench-agentic-coding:muse-spark-1.2 | 0.535 | 1 |
| 69 | gpt-6-astra-max livebench-agentic-coding:gpt-6-astra | 0.517 | 1 |
| 70 | grok-4.6 livebench-agentic-coding:grok-4.6 | 0.500 | 1 |
| 71 | gpt-6.1-sol-xhigh livebench-agentic-coding:gpt-6.1-sol | 0.483 | 1 |
| 72 | junie swe-rebench:junie__tools | 0.478 | 1 |
| 73 | qwen3.8-max-0902 | 0.477 | 1 |
| 74 | glm-5.3-flash livebench-agentic-coding:glm-5.3-flash | 0.467 | 1 |
| 75 | grok-4.5 livebench-agentic-coding:grok-4.5 | 0.451 | 1 |
| 76 | muse-spark | 0.439 | 1 |
| 77 | deepseek-v4-flash | 0.439 | 2 |
| 78 | claude-sonnet-5.5-max-effort livebench-agentic-coding:claude-sonnet-5.5-max-effort | 0.435 | 1 |
| 79 | gpt-5.6-sol-max livebench-agentic-coding:gpt-5.6-sol | 0.419 | 1 |
| 80 | claude code swe-rebench:claude code__tools | 0.417 | 1 |
| 81 | claude-sonnet-4.6 | 0.416 | 3 |
| 82 | gpt-5.6-terra-max livebench-agentic-coding:gpt-5.6-terra | 0.404 | 1 |
| 83 | grok-build-0.1 | 0.398 | 1 |
| 84 | mimo-v2.5-pro release-date | 0.393 | 1 |
| 85 | deepseek-v4-pro-0813 livebench-agentic-coding:deepseek-v4-pro-0813 | 0.389 | 1 |
| 86 | mimo-v2.6-pro | 0.378 | 1 |
| 87 | gpt-6.1-sol-max livebench-agentic-coding:gpt-6.1-sol | 0.375 | 1 |
| 88 | swe-1.7 | 0.367 | 1 |
| 89 | gemini-3.8-flash-high livebench-agentic-coding:gemini-3.8-flash | 0.361 | 1 |
| 90 | codex swe-rebench:codex__tools | 0.360 | 1 |
| 91 | minimax-m3 | 0.356 | 2 |
| 92 | grok-4.7-xhigh livebench-agentic-coding:grok-4.7 | 0.347 | 1 |
| 93 | kimi-k2.5 | 0.345 | 1 |
| 94 | qwen3.7 | 0.340 | 1 |
| 95 | inkling-small | 0.336 | 1 |
| 96 | inkling | 0.334 | 2 |
| 97 | gpt-5.5-xhigh livebench-agentic-coding:gpt-5.5 | 0.333 | 1 |
| 98 | gpt-5.5-instant | 0.327 | 1 |
| 99 | gpt-5.4-xhigh livebench-agentic-coding:gpt-5.4 | 0.320 | 1 |
| 100 | muse_spark_1_3 | 0.319 | 1 |
| 101 | sonnet 5 [high] swe-rebench:sonnet 5 [high]__tools | 0.308 | 1 |
| 102 | gpt-6-sol-max livebench-agentic-coding:gpt-6-sol | 0.307 | 1 |
| 103 | grok-4.3 | 0.300 | 1 |
| 104 | ox-alpha-max livebench-agentic-coding:ox-alpha | 0.294 | 1 |
| 105 | mimo-v2.6-flash | 0.292 | 1 |
| 106 | minimax-m2.7 | 0.287 | 1 |
| 107 | glm-5.2 livebench-agentic-coding:glm-5.2 | 0.282 | 1 |
| 108 | gpt-5.4-nano | 0.279 | 1 |
| 109 | qwen3.7-plus | 0.275 | 2 |
| 110 | gpt-6-luna-max livebench-agentic-coding:gpt-6-luna | 0.269 | 1 |
| 111 | qwen3.8.27b | 0.266 | 1 |
| 112 | cursor swe-rebench:cursor__tools | 0.259 | 1 |
| 113 | claude-opus-4.7-xhigh-effort livebench-agentic-coding:claude-opus-4.7-xhigh-effort | 0.257 | 1 |
| 114 | glm-4.7 | 0.246 | 1 |
| 115 | claude-opus-4.8-max-effort livebench-agentic-coding:claude-opus-4.8-max-effort | 0.245 | 1 |
| 116 | claude-sonnet-4.5.20250929 | 0.238 | 1 |
| 117 | gpt-5.2- -high livebench-agentic-coding:gpt-5.2 | 0.234 | 1 |
| 118 | glm-5.1 | 0.230 | 1 |
| 119 | gemma-4.31b-it | 0.226 | 1 |
| 120 | gpt-5.1 | 0.223 | 1 |
| 121 | inkling-xhigh livebench-agentic-coding:inkling | 0.222 | 1 |
| 122 | claude-haiku-4.5.20251001 | 0.219 | 1 |
| 123 | ember-1 | 0.216 | 1 |
| 124 | minimax m3 swe-rebench:minimax m3__tools | 0.214 | 1 |
| 125 | mimo-v2.5 release-date | 0.211 | 1 |
| 126 | gpt-5.2-codex livebench-agentic-coding:gpt-5.2-codex | 0.211 | 1 |
| 127 | gpt-5 | 0.207 | 1 |
| 128 | gemini-2.5-pro | 0.204 | 1 |
| 129 | nemotron-3-ultra | 0.202 | 2 |
| 130 | gemini-3.5-flash-high livebench-agentic-coding:gemini-3.5-flash | 0.200 | 1 |
| 131 | nova-2.0-pro-preview | 0.200 | 1 |
| 132 | ring-2.6.1t | 0.196 | 1 |
| 133 | qwen3.235b-a22b-thinking-2507 | 0.193 | 1 |
| 134 | claude-opus-4.6-thinking-auto-high-effort livebench-agentic-coding:claude-opus-4.6-thinking-auto-high-effort | 0.189 | 1 |
| 135 | gemini-3.1-flash-lite | 0.185 | 1 |
| 136 | gemini-3.5-flash-lite | 0.182 | 1 |
| 137 | gpt-5.6-luna-max livebench-agentic-coding:gpt-5.6-luna | 0.179 | 1 |
| 138 | cogito-671b-v2.1 | 0.178 | 1 |
| 139 | qwen3.6-plus | 0.175 | 1 |
| 140 | mimo v2.5 pro swe-rebench:mimo v2.5 pro__tools | 0.172 | 1 |
| 141 | deepseek-v3.1-terminus | 0.171 | 1 |
| 142 | kimi-k2.6-thinking livebench-agentic-coding:kimi-k2.6-thinking | 0.168 | 1 |
| 143 | gpt-4.1-mini | 0.168 | 1 |
| 144 | mistral-medium-2604 | 0.161 | 2 |
| 145 | deepseek-v4-flash-0731 livebench-agentic-coding:deepseek-v4-flash-0731 | 0.158 | 1 |
| 146 | gemma-4.26b-a4b | 0.157 | 1 |
| 147 | claude-opus-4.6 | 0.155 | 1 |
| 148 | step-3.7-flash | 0.154 | 1 |
| 149 | claude-sonnet-4.20250514 | 0.150 | 1 |
| 150 | gpt-5.4-nano-xhigh livebench-agentic-coding:gpt-5.4-nano | 0.148 | 1 |
| 151 | o3-mini | 0.140 | 1 |
| 152 | composer 2.5 | 0.139 | 1 |
| 153 | grok-build-0.1 livebench-agentic-coding:grok-build-0.1 | 0.138 | 1 |
| 154 | magistral-medium-2509 | 0.137 | 1 |
| 155 | gpt-5-mini | 0.134 | 1 |
| 156 | gpt-5.6 luna [medium] swe-rebench:gpt-5.6 luna [medium]__tools | 0.133 | 1 |
| 157 | deepseek-v3.2-exp_thinking | 0.130 | 1 |
| 158 | kimi-k2.7-code livebench-agentic-coding:kimi-k2.7-code | 0.128 | 1 |
| 159 | mercury-2 release-date | 0.127 | 1 |
| 160 | glm-4.6 | 0.121 | 1 |
| 161 | gemini-3.5-flash-lite-high livebench-agentic-coding:gemini-3.5-flash-lite | 0.119 | 1 |
| 162 | command-a-plus-05.2026 | 0.114 | 1 |
| 163 | qwen3.6.27b | 0.111 | 1 |
| 164 | gemini-3.1-pro-preview-high livebench-agentic-coding:gemini-3.1-pro-preview | 0.109 | 1 |
| 165 | mistral-large-2512 | 0.108 | 1 |
| 166 | trinity-large-thinking | 0.102 | 1 |
| 167 | qwen3.7-max livebench-agentic-coding:qwen3.7 | 0.100 | 1 |
| 168 | nemotron-3-super | 0.099 | 1 |
| 169 | deepseek-v4 pro [high] swe-rebench:deepseek-v4 pro [high]__tools | 0.097 | 1 |
| 170 | gpt-oss-120b | 0.096 | 1 |
| 171 | qwen3.6.35b-a3b | 0.092 | 1 |
| 172 | gemini-3.6-flash-high livebench-agentic-coding:gemini-3.6-flash | 0.091 | 1 |
| 173 | deepseek-v3.0324 | 0.089 | 1 |
| 174 | deepseek-r1 | 0.086 | 1 |
| 175 | qwen3.5.122b-a10b | 0.083 | 1 |
| 176 | claude-sonnet-4.6-thinking-auto-medium-effort livebench-agentic-coding:claude-sonnet-4.6-thinking-auto-medium-effort | 0.082 | 1 |
| 177 | qwen3.32b | 0.077 | 1 |
| 178 | deepseek-v3 | 0.074 | 1 |
| 179 | deepseek-v4-pro livebench-agentic-coding:deepseek-v4-pro | 0.073 | 1 |
| 180 | magistral-small-2509 | 0.071 | 1 |
| 181 | gpt-oss-20b | 0.068 | 1 |
| 182 | gpt-5.4-mini-xhigh livebench-agentic-coding:gpt-5.4-mini | 0.065 | 1 |
| 183 | mistral-medium-2508 | 0.063 | 1 |
| 184 | qwen3.6.27b swe-rebench:qwen3.6.27b__tools | 0.063 | 1 |
| 185 | qwen3.30b-a3b-thinking-2507 | 0.060 | 1 |
| 186 | llama-4-maverick-17b-128e-instruct | 0.057 | 1 |
| 187 | qwen3.6-plus livebench-agentic-coding:qwen3.6-plus | 0.056 | 1 |
| 188 | qwen3-coder-next | 0.054 | 1 |
| 189 | qwen3.14b | 0.051 | 1 |
| 190 | qwen3.5.35b-a3b | 0.048 | 1 |
| 191 | minimax-m3 livebench-agentic-coding:minimax-m3 | 0.048 | 1 |
| 192 | devstral-small-2512 | 0.046 | 1 |
| 193 | qwen3.5.9b | 0.040 | 1 |
| 194 | claude-opus-4.5.20251101-thinking-64k-high-effort livebench-agentic-coding:claude-opus-4.5.20251101-thinking-64k-high-effort | 0.039 | 1 |
| 195 | claude-3.5-haiku-20241022 | 0.037 | 1 |
| 196 | mistral-small-2503 | 0.034 | 1 |
| 197 | mistral-small-2506 | 0.032 | 1 |
| 198 | claude-sonnet-5.5-xhigh-effort livebench-agentic-coding:claude-sonnet-5.5-xhigh-effort | 0.031 | 1 |
| 199 | qwen3.6.35b-a3b swe-rebench:qwen3.6.35b-a3b__tools | 0.030 | 1 |
| 200 | llama-3.3.70b-instruct | 0.029 | 1 |
| 201 | gpt-4.1-nano | 0.026 | 1 |
| 202 | mimo-v2-flash release-date | 0.024 | 1 |
| 203 | qwen3.6.27b livebench-agentic-coding:qwen3.6.27b | 0.023 | 1 |
| 204 | granite-4.1.30b | 0.021 | 1 |
| 205 | solar-pro-3 | 0.018 | 1 |
| 206 | qwen3.8b | 0.016 | 1 |
| 207 | nemotron-3-ultra-550b-a55b livebench-agentic-coding:nemotron-3-ultra-550b-a55b | 0.015 | 1 |
| 208 | gemma-3.27b-it | 0.013 | 1 |
| 209 | swe-1.6 | 0.012 | 1 |
| 210 | gemma-3.12b-it | 0.010 | 1 |
| 211 | llama-4-scout-17b-16e-instruct | 0.008 | 1 |
| 212 | deepseek-v4-flash livebench-agentic-coding:deepseek-v4-flash | 0.008 | 1 |
| 213 | llama-3.1.8b-instruct | 0.005 | 1 |
| 214 | phi-4-mini-instruct | 0.003 | 1 |
| 215 | grok-4.3 livebench-agentic-coding:grok-4.3 | 0.000 | 1 |
| 216 | qwen3.5.35b-a3b swe-rebench:qwen3.5.35b-a3b__tools | 0.000 | 1 |
Agent system · Agentic
Exploratory - not a ranked winner yetrg-coding-general-agent-system-agentic-agent-system-v1Explorer evidence
DeepSWE
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | gpt-6-astra mini_swe_agent_gpt_6_astra_xhighconfig_bbf07a11592b85abcf998b2bab14c636111bf22c2a0f135a859fc4637b64e740 | 74% | Unknown | 1 |
| 2 | gemini-3-8-flash mini_swe_agent_gemini_3_8_flash_highconfig_99f1f5a4baf710ee887184f3528382eb054e0afecf3559ac86b34d460c873004 | 74% | Unknown | 1 |
| 3 | claude-opus-5 mini_swe_agent_claude_opus_5_maxconfig_c647489700452c2c208a35693bed018b306c90d50da186a9291b35eb188e22bd | 74% | Unknown | 1 |
| 4 | gpt-6-astra mini_swe_agent_gpt_6_astra_maxconfig_40b1c572d64c805933bcf2129f08dc144572e516dae4925b339fef491870b072 | 73% | Unknown | 1 |
| 5 | gpt-6-astra mini_swe_agent_gpt_6_astra_highconfig_faa515a61e9b4ae933ed9ffafbc09b61632eef8431566e5075943695de9224b1 | 73% | Unknown | 1 |
| 6 | claude-opus-5 mini_swe_agent_claude_opus_5_xhighconfig_907c7158813ee95155a6b16492e69cab72740d132a672b18e7917e6f54d3c52b | 73% | Unknown | 1 |
| 7 | claude-opus-5 mini_swe_agent_claude_opus_5_highconfig_334f3a9751b1488836c3ca0b198a3ea0fd3e40bb457a88a406f18607209fa2b2 | 73% | Unknown | 1 |
| 8 | gpt-6-astra mini_swe_agent_gpt_6_astra_mediumconfig_d07b34ffb2af2531251a46451b40bd8518b18b6de158362a3781709c5f819647 | 73% | Unknown | 1 |
| 9 | gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_maxconfig_d275cb2c69e7afc4d9080fc5284f0decdd56f860104fd44fe1829806ddf651de | 73% | Unknown | 1 |
| 10 | gemini-3-8-flash mini_swe_agent_gemini_3_8_flash_mediumconfig_945e3c0a75cfab73b288951d2693331a0d4c93d3c38bce63058186ce60a58a7a | 71% | Unknown | 1 |
| 11 | gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_xhighconfig_5f5d92ae1a6bf9da591422530bfcd4acfeaa5aec7bdfb8a90395f8fddd4f9ccb | 71% | Unknown | 1 |
| 12 | claude-fable-5 mini_swe_agent_claude_fable_5_xhighconfig_bf246640f0460734fd45a96c676710109e2690cd919b520e6b18ec9c85079fe8 | 70% | Unknown | 1 |
| 13 | claude-fable-5 mini_swe_agent_claude_fable_5_maxconfig_6cd82db3623f359522ba12352bb5ff95b9cc92eb9e09a24ce83a2acda8dfeba2 | 70% | Unknown | 1 |
| 14 | gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_maxconfig_d7a3c6ced6dc428983ae9afd107ebd99d1e29da0322e8767df8159c22229b4b5 | 70% | Unknown | 1 |
| 15 | gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_highconfig_a9772d655df076b0c7d85604222b8ccb822d70a46403bc9f8cf8b3b160b0e223 | 69% | Unknown | 1 |
| 16 | glm-5-3 mini_swe_agent_glm_5_3_maxconfig_cd2676556edf9dfcda2adb6d7a9cd4a1a7330a4af6059b87d5727b7eb1ca7af6 | 69% | Unknown | 1 |
| 17 | claude-opus-5 mini_swe_agent_claude_opus_5_mediumconfig_820e8e67840338ad87da9a6120ed79d7238e33b22778298914022e04a4cf1617 | 69% | Unknown | 1 |
| 18 | claude-fable-5 mini_swe_agent_claude_fable_5_highconfig_04bb50f778bf6bf2c8169e378e0f045a45ffcdf91a637eeabe35a44fde13539b | 69% | Unknown | 1 |
| 19 | kimi-k3 mini_swe_agent_kimi_k3_maxconfig_7f7bf933eb0fa4a7ec5d62cfdeb29a8484d66dd1dc39d28e27ee6b3de50ff0e0 | 69% | Unknown | 1 |
| 20 | grok-4-6 mini_swe_agent_grok_4_6_mediumconfig_2b66a38fe21328d0521612421ff12f5d1eba6a8a6a80563ed1d40a0dbd05ef36 | 67% | Unknown | 1 |
| 21 | gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_maxconfig_499ebda077ee18c6bf8c3721552206ee3cf90dba0cef0d561bb06daca56dfc10 | 67% | Unknown | 1 |
| 22 | gpt-6-astra mini_swe_agent_gpt_6_astra_lowconfig_aba7c3968834f0ad1b0b5c15825bedfbc6814f23f4f0be4d06ae4a62141cb39b | 67% | Unknown | 1 |
| 23 | gpt-5-5 mini_swe_agent_gpt_5_5_xhighconfig_c13865a4ec6a39ff87177d09fb544d8eb4712f9966e2a74b8e4d4e9b735a21c6 | 67% | Unknown | 1 |
| 24 | grok-4-6 mini_swe_agent_grok_4_6_xhighconfig_43454ebde0853f40bb6c1b12f8900ea3545996192365102ab5e67608f1b80951 | 67% | Unknown | 1 |
| 25 | gemini-3-7-flash mini_swe_agent_gemini_3_7_flash_mediumconfig_b94b69cafe5ee03f283577664e74caa7e342e6133d663688f179d7a5a50b7a57 | 65% | Unknown | 1 |
| 26 | claude-fable-5 mini_swe_agent_claude_fable_5_mediumconfig_61b63ec56d8b6ea22a200a5fb3de9729acfff57a3a3beab1aac7a34ae0346940 | 65% | Unknown | 1 |
| 27 | gemini-3-7-flash mini_swe_agent_gemini_3_7_flash_highconfig_6a8634d1604a9f757490bb8f8fdbdbffe54e6b04fa34b93a825ce1c0de92511c | 65% | Unknown | 1 |
| 28 | grok-4-6 mini_swe_agent_grok_4_6_highconfig_162a581cb5c40d58417136a2856b1bbc5515aab288e49dd66579bd04a315e52e | 65% | Unknown | 1 |
| 29 | gpt-5-5 mini_swe_agent_gpt_5_5_highconfig_59053425417061eb762aefd1b03f50dbf187f5e10da5a8b7ed19b790b86d2850 | 64% | Unknown | 1 |
| 30 | glm-5-3-flash mini_swe_agent_glm_5_3_flash_maxconfig_599d6845c9eb4e3e89bbe917ac21d48dba8d197a374968fd4928f74bfa5479d5 | 63% | Unknown | 1 |
| 31 | deepseek-v4-pro mini_swe_agent_deepseek_v4_pro_maxconfig_f64966d7e89784334403b1fe7878048a57ec00876ce000c6e2bef57e5f49e129 | 63% | Unknown | 1 |
| 32 | gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_mediumconfig_402a0fe4d6931565bf6724561c4061f0e88fbda3bf95b56c133f6d26addc3e26 | 61% | Unknown | 1 |
| 33 | gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_xhighconfig_dc7c67793df85a38e322ab4feed92a231902a67745d1e268a87b6d74844d0cf4 | 60% | Unknown | 1 |
| 34 | claude-fable-5 mini_swe_agent_claude_fable_5_lowconfig_c690e0be3e8d248bcf56f308c253ff9ce8c149333a1e0b9412b7f8b69a31bf26 | 60% | Unknown | 1 |
| 35 | claude-opus-4-8 mini_swe_agent_claude_opus_4_8_maxconfig_b8895eb0c759293b55e37def7cfbd162f10b78486bc0ef5c0f3f3ae9f43a2cd9 | 59% | Unknown | 1 |
| 36 | claude-opus-5 mini_swe_agent_claude_opus_5_lowconfig_24f98c7e7848fa148f57009a6900cbf5074c5e1300c950add2e15db88b435f88 | 58% | Unknown | 1 |
| 37 | qwen3-8-max mini_swe_agent_qwen3_8_max_xhighconfig_c1fa762bbc21726067c3e67bb1d9481c18268022c7090f2f890f8d514d0fb6bf | 57% | Unknown | 1 |
| 38 | gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_xhighconfig_48bad74b1f6da89e03e6d0c75f872d8113fda707e64044512e74e758057407a3 | 57% | Unknown | 1 |
| 39 | muse-spark-1-2 mini_swe_agent_muse_spark_1_2_xhighconfig_7a7ee985e6fe340f164c16d1afb470467960e81f08fbf6f4e65f09676eeba5ae | 55% | Unknown | 1 |
| 40 | claude-opus-4-8 mini_swe_agent_claude_opus_4_8_xhighconfig_f08e8f48d01893af79c2caf089122161b3b14c03f77e05d67371c272cb310f0a | 54% | Unknown | 1 |
| 41 | gpt-5-5 mini_swe_agent_gpt_5_5_mediumconfig_1ecbed94580896d44ec01b4b99dc0303b3195e94f9691c141b2e9be484d15bb6 | 54% | Unknown | 1 |
| 42 | claude-sonnet-5 mini_swe_agent_claude_sonnet_5_maxconfig_64c1c487db75b6f50cb78e47cbcddc475d7835163bb54bca197d6929807213d8 | 54% | Unknown | 1 |
| 43 | grok-4-5 mini_swe_agent_grok_4_5_highconfig_49cbd80643e492e0cf6b291292344090b910a525752717066aa166b49500ac86 | 54% | Unknown | 1 |
| 44 | gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_highconfig_c70b094bd6bc90f6d73ca68f68464bf0e93f7fd41ac12ef19f50588add276301 | 54% | Unknown | 1 |
| 45 | gemini-3-7-flash mini_swe_agent_gemini_3_7_flash_lowconfig_fdac9250de689f25b6718a003882c23c28bf84dd32fa6062f085cdf90e670352 | 54% | Unknown | 1 |
| 46 | muse-spark-1-1 mini_swe_agent_muse_spark_1_1_xhighconfig_4f26f586de8723346aea4ac6f12834d5725a7817c0cb25377abf7b5b8174defb | 53% | Unknown | 1 |
| 47 | deepseek-v4-flash mini_swe_agent_deepseek_v4_flash_maxconfig_ce541a8d1b086c6ec893f0b97904e6a6f35cc3d5f6cef04816ef487c188a8ca1 | 53% | Unknown | 1 |
| 48 | claude-opus-4-8 mini_swe_agent_claude_opus_4_8_highconfig_58680d3eedd4aba4a66e8640af75742e54aafc7acb432a3cadbbf57a588317dc | 52% | Unknown | 1 |
| 49 | gpt-5-4 mini_swe_agent_gpt_5_4_xhighconfig_c3464a0472feb8d3fe258f92ca0c657b38233a78d3fc984651940d33f20e86e6 | 52% | Unknown | 1 |
| 50 | claude-sonnet-5 mini_swe_agent_claude_sonnet_5_xhighconfig_147bff69a94abfbdafc928e0bcd0a5e0b29af262312f804505a6afa320b38f0f | 50% | Unknown | 1 |
| 51 | claude-opus-4-8 mini_swe_agent_claude_opus_4_8_mediumconfig_3ef8a78571b4db55102a1dcd4c752a5383675e978fe3b4a95498f5bd487d1cbc | 49% | Unknown | 1 |
| 52 | claude-sonnet-5 mini_swe_agent_claude_sonnet_5_highconfig_4efd185eb4ad5275b557bc6111ae1947e9488c0690c30b536246c759b66e552c | 48% | Unknown | 1 |
| 53 | gemini-3-6-flash mini_swe_agent_gemini_3_6_flash_highconfig_66464aef80070e91183f432938fb0720c862586f4cec7a311ddb916898fe6248 | 47% | Unknown | 1 |
| 54 | gpt-5-6-sol mini_swe_agent_gpt_5_6_sol_lowconfig_b35e7084f490107ff26755c5b1273537c783262b505c1aa482e22478c164c846 | 45% | Unknown | 1 |
| 55 | gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_highconfig_7ca720abbeb6b966e08ff13e43dd66c4ce24f20cd0c21e347365f9737c3310d0 | 44% | Unknown | 1 |
| 56 | glm-5-2 mini_swe_agent_glm_5_2_maxconfig_08c75ff5b5fae701d4ee71ec5fc3cb6e2a39054e1b28350e64566658218b85e4 | 44% | Unknown | 1 |
| 57 | grok-4-6 mini_swe_agent_grok_4_6_lowconfig_b3887dfd53e7b98841d8c2f592a9e9ed2dd78f42de43dcde2110cb3b91e97624 | 42% | Unknown | 1 |
| 58 | claude-opus-4-8 mini_swe_agent_claude_opus_4_8_lowconfig_9a1325eb982ef5a1595ffad514abac5e163d6885bbbc075eba16dec0b46f4a4d | 41% | Unknown | 1 |
| 59 | claude-sonnet-5 mini_swe_agent_claude_sonnet_5_mediumconfig_f0e2c73135d5b86f49948a23ee64ac435abb667458e1fae9d1c11c8e1186ffa8 | 40% | Unknown | 1 |
| 60 | glm-5-2 mini_swe_agent_glm_5_2_highconfig_f17ac834afbf2b11b522ae81b1ca7f2447e312733af1a89d601b356c3f4af9b1 | 36% | Unknown | 1 |
| 61 | gemini-3-5-flash mini_swe_agent_gemini_3_5_flash_highconfig_0eefe519e147a16e978da082c66fa969726579aeb56973768ca73cb1bc3e21e5 | 36% | Unknown | 1 |
| 62 | gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_mediumconfig_038eeba65e62059f4ecbf181a3fc6b650197e5565b870690ab4acdf993591595 | 35% | Unknown | 1 |
| 63 | kimi-k2-7-code mini_swe_agent_kimi_k2_7_code_defaultconfig_124cbcc3be53e10cd1eacf75752b42bdb1de1e3f300505cd9a91c8d7cfb62da1 | 31% | Unknown | 1 |
| 64 | claude-sonnet-5 mini_swe_agent_claude_sonnet_5_lowconfig_2ff43d430d17fc22211a61f924364e79392742a599234cff2b758071d0f776d4 | 31% | Unknown | 1 |
| 65 | claude-sonnet-4-6 mini_swe_agent_claude_sonnet_4_6_highconfig_7a7d2700f41f08a7c77f117fa2528b852375d1ff9cd7edc244a6758602df8aca | 30% | Unknown | 1 |
| 66 | gpt-5-5 mini_swe_agent_gpt_5_5_lowconfig_eddf24c4f45fdddd638382b42b744f61680535d051dea5acdeb9da97262471d0 | 27% | Unknown | 1 |
| 67 | gpt-5-6-terra mini_swe_agent_gpt_5_6_terra_lowconfig_bd9280382f7291b715a8d59bd21f92caca736754aea139b7257112f4d58b1a58 | 24% | Unknown | 1 |
| 68 | gemini-3-1-pro-preview mini_swe_agent_gemini_3_1_pro_preview_highconfig_5ab1cfce9a0ab268f572bfcda041482ea856d2d71f2155ab18a1fed803987d6d | 12% | Unknown | 1 |
| 69 | gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_mediumconfig_6f12c6f06fbb79da94ca98267c419407731951297057e438fbfed83e8fac354d | 11% | Unknown | 1 |
| 70 | gpt-5-6-luna mini_swe_agent_gpt_5_6_luna_lowconfig_4c1aa5736b934cbb1c18d21f67ab505d0157d5aa73c579ba0c4737f1dab87dfa | 2% | Unknown | 1 |
Explorer evidence
FrontierCode
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | claude-opus-5-5_medium 2026-09-22config_90499d2a1f50ddc00ff8c1c68be58d73783300e7340eeedac5fe2d8cd4fd40ba | 55% | Unknown | 1 |
| 2 | claude-fable-5_unknown 2026-06-09config_2687d157270f72d022ef9d602e76ea269ae5bbe66b7062f45d9519682576e6bc | 53% | Unknown | 1 |
| 3 | claude-opus-5_max 2026-07-24config_01ae91077ba9150d840277a7e0fae15a73827719e0ba224bbba0bcd68fcff8fd | 53% | Unknown | 1 |
| 4 | gpt-6-astra_max 2026-09-03config_3908ce8b0cfc8880b5377d99a32b9613c8f09ed7a7a7183bf560bcdd786ee0bb | 53% | Unknown | 1 |
| 5 | claude-sonnet-5-5_xhigh 2026-09-28config_c8ee8e119935ab0d9704857eb2a639aeba26b58e63ddce2417cbdb43d8b826a5 | 52% | Unknown | 1 |
| 6 | claude-fable-5-1_medium 2026-09-01config_766d77cd2cc468aa22a3b82b7ca4c80c53738534b6e94dc98a1bedc71520717b | 51% | Unknown | 1 |
| 7 | gpt-6.1-sol_medium 2026-09-29config_813cd1d07d0def8f942f9d3a553db84f1e6cadceb3148bd682945d0778582d34 | 50% | Unknown | 1 |
| 8 | swe-2_max 2026-09-10config_fcf75fae7bddd18c493e261670a9e42da4ea61eb266e213af94cb0cc4eddf988 | 50% | Unknown | 1 |
| 9 | gpt-6-sol_max 2026-09-22config_6675e750a5409e535610dc739112c7e78133adcad0a05e81c34f3b8f68b8ed2a | 49% | Unknown | 1 |
| 10 | grok-4.6_unknown 2026-08-12config_6f19456a4f118a4b3c66a978bb3ba438e8c520a2aab0e4b97f910bbeb57e5c3a | 48% | Unknown | 1 |
| 11 | gpt-5.6-sol_unknown 2026-07-09config_17bd8197f3fd1a6dedb58a378cdf0895baf1b2a851d5854654a0c98850bba753 | 47% | Unknown | 1 |
| 12 | claude-opus-4-8_unknown 2026-05-28config_e749e354200461935a7ea9ae57b004b4e1f125109bb0bd8de48c32a13eebb614 | 47% | Unknown | 1 |
| 13 | kimi-k3_unknown 2026-07-16config_5f807dbaeaa3f031f58ad044b8844ec9ef389ab36b3912602fc7d561ae9d853f | 44% | Unknown | 1 |
| 14 | gemini-3.7-flash_unknown 2026-08-13config_d8d783f36dd7349f55dddbb4cfdc4b66f38c03141202370a1ce516fc40f3c915 | 44% | Unknown | 1 |
| 15 | gpt-5.5_unknown 2026-04-23config_1e208f4033ab491d49ba0d4b503ba2fe32291e9d6098f5d4d8f8e49626881b93 | 43% | Unknown | 1 |
| 16 | claude-sonnet-5_unknown 2026-06-30config_418d28c0e375135ed44780ae367a2993f23a63fc87007d4b8db6dc5266872519 | 43% | Unknown | 1 |
| 17 | grok-4.5_unknown 2026-07-08config_26c6959381309382a26d1cf08cc8cb0fe4f24b8d758ebb5d2c4ac13a6c1a98a4 | 42% | Unknown | 1 |
| 18 | gpt-6-luna_max 2026-09-22config_5fc8d0b52c3b5a7b8683b5f976a6abbf7564672c93865747cd5919dfee8df554 | 42% | Unknown | 1 |
| 19 | swe-1.7 2026-07-08config_5cc71ab4416f5cce5175956726318a657bb3c08aa0b571039491006d95ac92bf | 42% | Unknown | 1 |
| 20 | gpt-5.6-terra_unknown 2026-07-09config_46ae875a3954f9177367781981a840741d7fecb6bd533f37236eadb15d6e1e0a | 41% | Unknown | 1 |
| 21 | gemini-3.8-flash_medium 2026-09-02config_d8f82dd743f29d5b94155ea0e624c58bf1629ff8235a63ad332e4c7b9178e903 | 41% | Unknown | 1 |
| 22 | glm-5.3_max 2026-08-14config_a728cb2bfb6656d91c143e7128920e0bac85af3613aec05e118a522b699013af | 40% | Unknown | 1 |
| 23 | gpt-5.6-luna_unknown 2026-07-09config_e9c34ce3587902bc4450dbe8a5810efe724222888ca3811c588b2672f99350f7 | 40% | Unknown | 1 |
| 24 | claude-opus-4-7_unknown 2026-04-16config_21128ad78dc713b9bd8c2c4e5785f2df83bd2f60bb7b528d3f0e729d08305bae | 39% | Unknown | 1 |
| 25 | gemini-3.6-flash_unknown 2026-07-21config_705c95fab33af628ec07b00753678e6a2cf28a6d11f553b075ea9941f1a08c1d | 34% | Unknown | 1 |
| 26 | glm-5.3-flash_max 2026-08-20config_d0d4a1a86431f823518b1b892e991d4d772cd2dc8f51b1dd9dce30d92cf55d0f | 32% | Unknown | 1 |
| 27 | kimi-k2.7-code 2026-06-12config_31ed039d75fd33b1057b150e5c418bd51423d38b8c7df9f78ce69ac1eb40d1dd | 30% | Unknown | 1 |
| 28 | deepseek-v4-pro-0813_high 2026-08-13config_5cf2b4c8ef29bb8da9cb1e717aab6d60655026c2dfc63e3e9c70112ed6b38799 | 29% | Unknown | 1 |
| 29 | gpt-5.4-mini-2026-03-17_unknownconfig_a1a7e4c8bd25d82dbdff30aac9a30694bcf9ddf729a11c7acbe2de38ab6b594b | 27% | Unknown | 1 |
| 30 | claude-opus-4-6_unknown 2026-02-05config_e7abe35fbe8b8380a7ed4bd066f441d3c556b93518c20c7dee0040dc10f6c057 | 27% | Unknown | 1 |
| 31 | Composer 2.5 2026-05-18config_b97fd425f2526368e32ded2bdd621c90584703dd47438cbae1a93b378413ba24 | 26% | Unknown | 1 |
| 32 | glm-5.2_none 2026-06-16config_1cf4f3a461cabc583aa1fd99528a9a49cb7ad51c8bf54b17b41aa166067db96e | 25% | Unknown | 1 |
| 33 | claude-sonnet-4-6_unknown 2026-02-17config_d16ff9a95d6839c1a8010ea4b24eaba8ce434289cba69a318f262bbddda8e0bb | 24% | Unknown | 1 |
| 34 | deepseek-v4-flash-0731_unknown 2026-07-31config_59438578e54a97fdf3e8632b047ec667129e7d90aea43f3cdbe7c7d86b02848f | 19% | Unknown | 1 |
| 35 | deepseek-v4-pro_none 2026-04-24config_0ec4386dd9cf763f25ad6463b4a4d9b24d51c2e322a61f5edc47e696326a88f1 | 18% | Unknown | 1 |
| 36 | MiniMax-M3 2026-06-01config_fda1b5b794f636b1d632482936703d0882563edabfbdf6da15e1963b0c25d0fa | 15% | Unknown | 1 |
| 37 | Inkling 2026-07-15config_2935bdf11dec76c7f9a65156ca62b11fc810ba21a9180eed041f73b855bc0ff7 | 14% | Unknown | 1 |
| 38 | nemotron-3-ultra 2026-06-04config_d3ba33dca3736b40edca8909745ce2e8ea136041a2bc508dcc710f5311102ffa | 14% | Unknown | 1 |
| 39 | qwen3.7-plus 2026-06-02config_cfeeedc2c510d32d19e1045147c700762bec5ac62becc634ee0c0cbba69886c5 | 10% | Unknown | 1 |
| 40 | swe-1.6 2026-04-07config_5b9e900100b4b6b8192ff5ebb0524db73ac6993260e47bb66f20403a3c799cb4 | 9% | Unknown | 1 |
| 41 | mistral-medium-2604 2026-04-28config_88cd6bd1510474d80c7ea29dbf01a224c36b5ad2a239e017b0d4032a5839cb09 | 8% | Unknown | 1 |
Explorer evidence
LiveBench agentic coding
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | deepseek-v4.1-flash-max livebench-agentic-coding:deepseek-v4.1-flash-maxconfig_a3f3f48128015b7048dc83697f2bfe8f012daa73f5ffa11178ec46caac6e0045 | 100% | Unknown | 1 |
| 2 | claude-opus-5-5-max-effort livebench-agentic-coding:claude-opus-5-5-max-effortconfig_623424b00ad7bf3ec909007676ec6f8473696f7c7356df518cb7c6a367bab583 | 91% | Unknown | 1 |
| 3 | claude-fable-5-1-max-effort livebench-agentic-coding:claude-fable-5-1-max-effortconfig_e61c4784e49f2ae6ebee18a6898684480b342962e8c12b229bbcdcb3ee90aa74 | 81% | Unknown | 1 |
| 4 | claude-opus-5-5-xhigh-effort livebench-agentic-coding:claude-opus-5-5-xhigh-effortconfig_44e877a45e05f65cfc614cff579a28937df62aeb0cce06842ef15f643a03f651 | 80% | Unknown | 1 |
| 5 | claude-opus-5-max-effort livebench-agentic-coding:claude-opus-5-max-effortconfig_fa03387b80782426a0083d86224b364186421f9f6475c7f7af53980146d2f4c4 | 79% | Unknown | 1 |
| 6 | deepseek-v4-flash-vision-exp livebench-agentic-coding:deepseek-v4-flash-vision-expconfig_2f5283742b3da15d7054dd4c988df126247e4dd355031c2f5ce11bb9ef2217c3 | 79% | Unknown | 1 |
| 7 | qwen3.8-max livebench-agentic-coding:qwen3.8-maxconfig_26d1a7c978290d54d7ef0eabebeaf9c0d1ce39c50082e92678df53715048bfbc | 79% | Unknown | 1 |
| 8 | smaug-agentic livebench-agentic-coding:smaug-agenticconfig_67ad1d94b2e3e15e9350f6cbaeb2b779ea72938ddd0cfd5bbe55b326a9af3973 | 79% | Unknown | 1 |
| 9 | muse-spark-1.3-xhigh livebench-agentic-coding:muse-spark-1.3-xhighconfig_27796316611daaff0f2c0d9c95585ae1251e0dc908250b7fa937ae1b56fd5b2a | 78% | Unknown | 1 |
| 10 | kimi-k3 livebench-agentic-coding:kimi-k3config_3c44623be11a035903d5f110f1ef71d07c0e9527362cc1140d7af0b1aad175d0 | 74% | Unknown | 1 |
| 11 | claude-fable-5-max-effort livebench-agentic-coding:claude-fable-5-max-effortconfig_dcebf770950f840525905cfd4cf209b75af292cc15028f199a71012506b8670b | 74% | Unknown | 1 |
| 12 | qwen3.8-flash-next livebench-agentic-coding:qwen3.8-flash-nextconfig_4a92826c1f8edba2a821b99891d25bdc1177117a1e0ff6a16ac7b02505331156 | 73% | Unknown | 1 |
| 13 | qwen3.8-27b livebench-agentic-coding:qwen3.8-27bconfig_92f7a920aed94c8ff82916197320f4206f4e12206d8847aab897861be0e1e7aa | 73% | Unknown | 1 |
| 14 | smaug-flash livebench-agentic-coding:smaug-flashconfig_7c7be6bb607f705ae5e1c71de96a36378ff23218a49b2a1bb8300ccc8e4a1b95 | 72% | Unknown | 1 |
| 15 | glm-5.3 livebench-agentic-coding:glm-5.3config_5012de9feced966a8ccc1480e05037cbe594c1bfa695e86c08bd7d3ecf4be8cb | 72% | Unknown | 1 |
| 16 | smaug-mini livebench-agentic-coding:smaug-miniconfig_0ba097f94061fab8ecdb9f4f985ed096d19d6b4c3cad10094d01c3cf09bd81ca | 72% | Unknown | 1 |
| 17 | claude-sonnet-5-xhigh-effort livebench-agentic-coding:claude-sonnet-5-xhigh-effortconfig_43a9cabf932f32a8fd6429e849f209b92fee99c00b1af2f130861fabf8759be4 | 70% | Unknown | 1 |
| 18 | muse-spark-1.1-xhigh livebench-agentic-coding:muse-spark-1.1-xhighconfig_5bfd425c9188db5ba59751d48dc93c77f1f0e88472b5457fa33c17290bd9d6f6 | 68% | Unknown | 1 |
| 19 | gemini-3.7-flash-high livebench-agentic-coding:gemini-3.7-flash-highconfig_fb0cc6574ed6ac7ffdf69a8b7c28eebaa2789283a43c989d28c70ed4f5d8ba38 | 68% | Unknown | 1 |
| 20 | muse-spark-1.2-xhigh livebench-agentic-coding:muse-spark-1.2-xhighconfig_9160731edb105c8a8b3bcd5cda3e79956fe3317b3523ed3d7757352ab9183cf4 | 66% | Unknown | 1 |
| 21 | gpt-6-astra-max livebench-agentic-coding:gpt-6-astra-maxconfig_42a8b34ee9a4f138e063b1183909272846b4a1e63e5df2ce174ae8eea006b8c6 | 66% | Unknown | 1 |
| 22 | grok-4.6 livebench-agentic-coding:grok-4.6config_66e38e59192d3478e63c4c1b1a7f73ee6766beefaf61ff0a360b1f8e615d4aac | 66% | Unknown | 1 |
| 23 | gpt-6.1-sol-xhigh livebench-agentic-coding:gpt-6.1-sol-xhighconfig_5f57290c240f2bc5bee9802b989fd3c1977026ea5cf1c2b3b90ce00de7c169b9 | 65% | Unknown | 1 |
| 24 | glm-5.3-flash livebench-agentic-coding:glm-5.3-flashconfig_f2d90fa000d69788d8ba7c27f25f4a7c709b0392d758776a53c7b6fcafca4aa1 | 65% | Unknown | 1 |
| 25 | grok-4.5 livebench-agentic-coding:grok-4.5config_e9fee7d161eab1a6a13dbba4437ec82529c71beffa6065c021e96213a7ce1402 | 65% | Unknown | 1 |
| 26 | claude-sonnet-5-5-max-effort livebench-agentic-coding:claude-sonnet-5-5-max-effortconfig_c8a3216833070fac26546922f11e7510e41f719fb1159ebd788aabfb4de7d67f | 64% | Unknown | 1 |
| 27 | gpt-5.6-sol-max livebench-agentic-coding:gpt-5.6-sol-maxconfig_f2b299001d72eaf68e7ae779b7f29eb19c55590f8023553b74abcc8f2bfff556 | 64% | Unknown | 1 |
| 28 | gpt-5.6-terra-max livebench-agentic-coding:gpt-5.6-terra-maxconfig_58e8d9d93f31d32dc713de617c9fabcce4f1c51501460215d332544ec8523c9d | 62% | Unknown | 1 |
| 29 | deepseek-v4-pro-0813 livebench-agentic-coding:deepseek-v4-pro-0813config_b1ef602b63ec31a0274aea5b9c159ba86374059f9304b8eb427021c54b71febc | 62% | Unknown | 1 |
| 30 | gpt-6.1-sol-max livebench-agentic-coding:gpt-6.1-sol-maxconfig_82e08e3f15c94e36919fd9156e552d54f5e51b402e0279d32ea3a46f06a063be | 61% | Unknown | 1 |
| 31 | gemini-3.8-flash-high livebench-agentic-coding:gemini-3.8-flash-highconfig_5e651bc83d7908ab3a82f9c4e3abbfcb80c833bd97d5a51f6b15d46d7a3284d8 | 61% | Unknown | 1 |
| 32 | grok-4.7-xhigh livebench-agentic-coding:grok-4.7-xhighconfig_dd6eb5fafb9fe66d1b28f8ca1764d18b2015f4c45cc5382013f88c19f54b7772 | 60% | Unknown | 1 |
| 33 | gpt-5.5-xhigh livebench-agentic-coding:gpt-5.5-xhighconfig_f33b6bda00ff309df0ae96b94b139e89627e355cab0fda45ba69be2dea74444c | 60% | Unknown | 1 |
| 34 | gpt-5.4-xhigh livebench-agentic-coding:gpt-5.4-xhighconfig_1cd35baf86058bbcb067d9230953ec4ea959b7fce959ffe1cb4caeefcb7259e2 | 60% | Unknown | 1 |
| 35 | gpt-6-sol-max livebench-agentic-coding:gpt-6-sol-maxconfig_cff5173a77e25ec1878a770fdc5028856f9c8b5b2c1e73112740fb3c23a4b9e9 | 58% | Unknown | 1 |
| 36 | ox-alpha-max livebench-agentic-coding:ox-alpha-maxconfig_32d6a5b3871bde90f48e9324210bdd27b7faa9cee90cf595e9e37c5ecc755eea | 58% | Unknown | 1 |
| 37 | glm-5.2 livebench-agentic-coding:glm-5.2config_4263018f36603403a9ce293938692fe616138032641eac7fd56b42a11e988ed0 | 57% | Unknown | 1 |
| 38 | gpt-6-luna-max livebench-agentic-coding:gpt-6-luna-maxconfig_b62038a08bf31d47cda50b8f9fa85bcef25deb9bc5e754a1a56da8c7f0ad8d0e | 56% | Unknown | 1 |
| 39 | claude-opus-4-7-xhigh-effort livebench-agentic-coding:claude-opus-4-7-xhigh-effortconfig_c4ae48ff9433a87a1a6358ecb69351665798f780ba7ffdb21d03307cd0c99084 | 55% | Unknown | 1 |
| 40 | claude-opus-4-8-max-effort livebench-agentic-coding:claude-opus-4-8-max-effortconfig_ed201395926551ba01bdcbb0ab6747cb22040dc95c8d9c9a42e6695543f895c6 | 54% | Unknown | 1 |
| 41 | gpt-5.2-2025-12-11-high livebench-agentic-coding:gpt-5.2-2025-12-11-highconfig_5da2e1e74c881e85fa6e95e1e86ff95f66d2b4db3bcb782d47569d8c2f86f188 | 54% | Unknown | 1 |
| 42 | inkling-xhigh livebench-agentic-coding:inkling-xhighconfig_210d4d63755602d853e3b391fcb8f9a03ae30508cd764711bf00d4f4d91478ba | 53% | Unknown | 1 |
| 43 | gpt-5.2-codex livebench-agentic-coding:gpt-5.2-codexconfig_9361dcf948767508f060bd9b9435f00af0488858ffd4a34a05f051154714f14d | 53% | Unknown | 1 |
| 44 | gemini-3.5-flash-high livebench-agentic-coding:gemini-3.5-flash-highconfig_519f10ce6dfa986f913e0a8b676529d9f942ca65529e5fc665ea999caf5d643d | 52% | Unknown | 1 |
| 45 | claude-opus-4-6-thinking-auto-high-effort livebench-agentic-coding:claude-opus-4-6-thinking-auto-high-effortconfig_ded52f2edda6edd0f39efbf69e8c01653594e4a09fe06169692cc3171fbbfc7e | 52% | Unknown | 1 |
| 46 | gpt-5.6-luna-max livebench-agentic-coding:gpt-5.6-luna-maxconfig_e3f67054973eae8d12055b2087d7828e8517edd8169c113ed014233ec9ab4cdc | 51% | Unknown | 1 |
| 47 | kimi-k2.6-thinking livebench-agentic-coding:kimi-k2.6-thinkingconfig_f677d1d6c5a69e5214ea5163c28aef1da8b5a2adb2b6cc8b4add29a27be23c44 | 48% | Unknown | 1 |
| 48 | deepseek-v4-flash-0731 livebench-agentic-coding:deepseek-v4-flash-0731config_2056e61855394ea265f638b65933e2ddceee64a6bdae1084b01b7d1c98e90440 | 48% | Unknown | 1 |
| 49 | gpt-5.4-nano-xhigh livebench-agentic-coding:gpt-5.4-nano-xhighconfig_3e97d54bcf0ae865763a710c3fa4a4dc79fb5ebad56e761fcb2667d5f6d315b9 | 48% | Unknown | 1 |
| 50 | grok-build-0.1 livebench-agentic-coding:grok-build-0.1config_17213fd3b89188a50a3c410f0cd97fe95586bdf87f092d2b406d2942d5c45627 | 46% | Unknown | 1 |
| 51 | kimi-k2.7-code livebench-agentic-coding:kimi-k2.7-codeconfig_0c53be86b5d3dd18a9cc284369998d3b5352e86cf821e466f2b774fa8dd53eb1 | 46% | Unknown | 1 |
| 52 | gemini-3.5-flash-lite-high livebench-agentic-coding:gemini-3.5-flash-lite-highconfig_c13b9e922644048fd62e73f75e8cb23e5d51960a9e3e7e88e26f9ee985c95e00 | 45% | Unknown | 1 |
| 53 | gemini-3.1-pro-preview-high livebench-agentic-coding:gemini-3.1-pro-preview-highconfig_31ea798c91e15a1273c3aa128a89c3d99da42d7f87c53d5b092dd590d5d0e272 | 44% | Unknown | 1 |
| 54 | qwen3.7-max livebench-agentic-coding:qwen3.7-maxconfig_526c723601680bbd21f0d26b39723e28b38ed8ed5236854c5cdd8a7937214a07 | 43% | Unknown | 1 |
| 55 | gemini-3.6-flash-high livebench-agentic-coding:gemini-3.6-flash-highconfig_414ce51dc9cbb1149cfb361e38ceff9fff80dfeef3dd30a9bc476bf1daac4beb | 42% | Unknown | 1 |
| 56 | claude-sonnet-4-6-thinking-auto-medium-effort livebench-agentic-coding:claude-sonnet-4-6-thinking-auto-medium-effortconfig_45f4a5f474ac65b466de3a1bb6e0574f3296076c1dec393c3e9968340b9274ed | 41% | Unknown | 1 |
| 57 | deepseek-v4-pro livebench-agentic-coding:deepseek-v4-proconfig_69a8e6cf4d12564ee0b66d77c6bd5690116f378b1286c0e07b1956d455122b92 | 41% | Unknown | 1 |
| 58 | gpt-5.4-mini-xhigh livebench-agentic-coding:gpt-5.4-mini-xhighconfig_17d661fd889b3b6b7de1d2cf8f160a857b8f126cf7cb8b3cbd4ba6836a61b241 | 39% | Unknown | 1 |
| 59 | qwen3.6-plus livebench-agentic-coding:qwen3.6-plusconfig_a19b51c76a73ae2388dd7d025d3f04ece42cfbe48a8687b2b10e5ba04090d6b3 | 39% | Unknown | 1 |
| 60 | minimax-m3 livebench-agentic-coding:minimax-m3config_70308968d63164d37ff3ab52d90f9b7371ff2e67a139e2831c42316b13a8f7ec | 38% | Unknown | 1 |
| 61 | claude-opus-4-5-20251101-thinking-64k-high-effort livebench-agentic-coding:claude-opus-4-5-20251101-thinking-64k-high-effortconfig_90acaf2f301fca6bb200adc25a7bbc02f60b38f9fd69aeb3108a3efc4549a896 | 36% | Unknown | 1 |
| 62 | claude-sonnet-5-5-xhigh-effort livebench-agentic-coding:claude-sonnet-5-5-xhigh-effortconfig_e921269ddad45a601aeab57c06fe011fda91305085dfaecd382482a7e1abf63b | 35% | Unknown | 1 |
| 63 | qwen3.6-27b livebench-agentic-coding:qwen3.6-27bconfig_a4613216c98e96a740df9aa99206df2177d766124e35a4ff8fc983fe8b33cef1 | 35% | Unknown | 1 |
| 64 | nemotron-3-ultra-550b-a55b livebench-agentic-coding:nemotron-3-ultra-550b-a55bconfig_c4e39dd53ca9e460399d4e08d0be1f20632d8481fb1f0b1ce70267f9dcc29f2b | 34% | Unknown | 1 |
| 65 | deepseek-v4-flash livebench-agentic-coding:deepseek-v4-flashconfig_cb8b3b1bc3c4d2cd9fd891b40959f91faca99d85fb611bf5efbff613f644da54 | 33% | Unknown | 1 |
| 66 | grok-4.3 livebench-agentic-coding:grok-4.3config_de3dfd64073bdada42dd848c34a68abad02091bfe4d48421a0ee5121140931ff | 0% | Unknown | 1 |
Explorer evidence
SWE-rebench
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | Fable 5 [high] swe-rebench:Fable 5 [high]__toolsconfig_4e7f75da05439b3642933e9e555d35f601be606b56be74f249c84b75c72c7285 | 65% | Unknown | 1 |
| 2 | Grok 4.5 [high] swe-rebench:Grok 4.5 [high]__toolsconfig_4a0a36facd4c84472b72c62315364c005e7905eb5e714da1268a9e10704329fa | 64% | Unknown | 1 |
| 3 | Opus 5 [high] swe-rebench:Opus 5 [high]__toolsconfig_e87585e983bf07a6c02dd9e122ee8c2ae6f5871b7d00cf81ae3e56adc6c74466 | 63% | Unknown | 1 |
| 4 | GLM-5.2 [high] swe-rebench:GLM-5.2 [high]__toolsconfig_31790c4ce133091479f0e475b3c27f17707bca63b16038b982c4a5d619781022 | 63% | Unknown | 1 |
| 5 | GPT-5.6 Sol [medium] swe-rebench:GPT-5.6 Sol [medium]__toolsconfig_fd0af5a9ef00c56831263638b341da9cf910d665474da73ea958d614ed9b2973 | 62% | Unknown | 1 |
| 6 | Junie swe-rebench:Junie__toolsconfig_19dd924a998d790e3430cbf19f065f410d0becb402d0a54ff47187d54449d6a8 | 62% | Unknown | 1 |
| 7 | Claude Code swe-rebench:Claude Code__toolsconfig_7097e56f2e9fd36c0bb8cfd5de2bdd1955c6c94706e13288dcf955eef65c38ff | 60% | Unknown | 1 |
| 8 | Codex swe-rebench:Codex__toolsconfig_2503d09994edcf16bdf3fe21d749c4472d6a66f7df09489754741fad26b321f8 | 58% | Unknown | 1 |
| 9 | Sonnet 5 [high] swe-rebench:Sonnet 5 [high]__toolsconfig_9f982bb8a565d848359fa715eb45b07fabf7e4f8ef2af465ef1db26476524069 | 57% | Unknown | 1 |
| 10 | Cursor swe-rebench:Cursor__toolsconfig_26a283926b59a657126e00e3aa5950ed50b55d8f192325c2a0bf6ac79ece30de | 52% | Unknown | 1 |
| 11 | MiniMax M3 swe-rebench:MiniMax M3__toolsconfig_880d9ea0f0cb2554866d99d48bbc0369bee8d93f574e75e1e6d8c2980362d2a7 | 47% | Unknown | 1 |
| 12 | MiMo V2.5 Pro swe-rebench:MiMo V2.5 Pro__toolsconfig_94baade9cb08003b0121bfcef2b4c713b9f593a25855407b4cf4cb6d84b30a21 | 46% | Unknown | 1 |
| 13 | GPT-5.6 Luna [medium] swe-rebench:GPT-5.6 Luna [medium]__toolsconfig_60a6476cf22eb1bb99856c673a62c0707918e28ff9c5fa48b7dd91c60084e487 | 44% | Unknown | 1 |
| 14 | DeepSeek-V4 Pro [high] swe-rebench:DeepSeek-V4 Pro [high]__toolsconfig_cd306ea55772d6cddc152bf079e0a2caf9ad5196e75005290fb2ccf874735648 | 40% | Unknown | 1 |
| 15 | Qwen3.6-27B swe-rebench:Qwen3.6-27B__toolsconfig_69ba7e04be3a3d97010f1c48f1491d2bee2976fa3ab917418a543bb819d4a19e | 31% | Unknown | 1 |
| 16 | Qwen3.6-35B-A3B swe-rebench:Qwen3.6-35B-A3B__toolsconfig_030863e97e67f3c828545b380b319c8dc864d169055be74829235acb7d61e71b | 25% | Unknown | 1 |
| 17 | Qwen3.5-35B-A3B swe-rebench:Qwen3.5-35B-A3B__toolsconfig_7e7a00e9aad734a48f0ad69fe3418df9a606e2eec0fe99859cf7a9fcc2c8c7ca | 17% | Unknown | 1 |
Explorer evidence
Terminal-Bench 4.0
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | anthropic/claude-opus-5-5 terminal-bench-4-0-vals:anthropic/claude-opus-5-5 | compute=maxconfig_21cf99a2c3ced84736ed06a6d1d4141c7ecdceb145157838b1b02d257ad4c096 | 65% | Unknown | 1 |
| 2 | anthropic/claude-sonnet-5-5 terminal-bench-4-0-vals:anthropic/claude-sonnet-5-5 | compute=maxconfig_5edf763b42af2658a86c9bdde6b10941a5a1ba0fc887678683839fb15884bc83 | 64% | Unknown | 1 |
| 3 | openai/gpt-6-astra terminal-bench-4-0-vals:openai/gpt-6-astra | reasoning=maxconfig_9f93b5ba6873d839f692aaebcf9603fc73e94c0bd2318b01848ccd3f0514a807 | 60% | Unknown | 1 |
| 4 | anthropic/claude-fable-5-1 terminal-bench-4-0-vals:anthropic/claude-fable-5-1 | compute=maxconfig_86e1a9ad6b39ccee546e7454f2783cb054a7a81f712294b2f1bd4939810acf6f | 58% | Unknown | 1 |
| 5 | google/gemini-4-argon terminal-bench-4-0-vals:google/gemini-4-argon | reasoning=highconfig_f65f5b89a326148e7b8f13365027a56710c071b27f5d38539e9c5c78360b4bcb | 58% | Unknown | 1 |
| 6 | openai/gpt-6.1-sol terminal-bench-4-0-vals:openai/gpt-6.1-sol | reasoning=maxconfig_1810284fe720949b8642cb537a5548bc7c4f607eef0c25fae3c3e9a0ee2685b8 | 55% | Unknown | 1 |
| 7 | anthropic/claude-opus-5 terminal-bench-4-0-vals:anthropic/claude-opus-5 | compute=maxconfig_86fb6bdd6eccaa4b073c7ec1aaf7767be0c880c675950c2a8acaabf69b5be55a | 54% | Unknown | 1 |
| 8 | openai/gpt-6-sol terminal-bench-4-0-vals:openai/gpt-6-sol | reasoning=maxconfig_91d61243b74f06b9c39bf883cc3ed9c44532677c7f1e42d3566f17fd37a06fc0 | 44% | Unknown | 1 |
| 9 | anthropic/claude-fable-5 terminal-bench-4-0-vals:anthropic/claude-fable-5 | compute=maxconfig_a9ec0a9e5b3126cf713ee65339f0fd6bda7bfa1d30ec14a3af83dd9505dd1745 | 41% | Unknown | 1 |
| 10 | zai/glm-5.3 terminal-bench-4-0-vals:zai/glm-5.3 | reasoning=maxconfig_c71870b5a271aa69494d8ba1c41b312752dc1c2d4fb3938043ef88c91e24e1cd | 39% | Unknown | 1 |
| 11 | openai/gpt-5.6-sol terminal-bench-4-0-vals:openai/gpt-5.6-sol | reasoning=maxconfig_cf1b6f23a7efc284c33f48f5d93c4988122f6cf1683ed74ab6b26b9eb7560a3a | 38% | Unknown | 1 |
| 12 | alibaba/qwen3.8-max terminal-bench-4-0-vals:alibaba/qwen3.8-max | defaultconfig_4608142387cb9252efc1a5a1d277d12c6990099fc45431d448e233f381280e87 | 34% | Unknown | 1 |
| 13 | stepfun/step-5-preview terminal-bench-4-0-vals:stepfun/step-5-preview | defaultconfig_e7e9185a68f4a94415f6883e7ea6d4798be6090f38e0b75c5a5a8532bab7da7b | 32% | Unknown | 1 |
| 14 | xiaomi/mimo-v2.6-pro terminal-bench-4-0-vals:xiaomi/mimo-v2.6-pro | defaultconfig_4917a311faccaaf66158425adf71b5d2fb2fa6fb5185a792d475d06dacbfb59b | 31% | Unknown | 1 |
| 15 | grok/grok-4.7 terminal-bench-4-0-vals:grok/grok-4.7 | reasoning=xhighconfig_45d976c171085ab8ab8de614348e78352ddd2749ef016d8ec00efc133927a645 | 29% | Unknown | 1 |
| 16 | meta/muse_spark_1_3_max terminal-bench-4-0-vals:meta/muse_spark_1_3_max | reasoning=maxconfig_e69e2ce9eb8390866169e9f3ab9a62325badd70f34b2d2c71f9a9bb7e4f38b4f | 25% | Unknown | 1 |
| 17 | xiaomi/mimo-v2.6-flash terminal-bench-4-0-vals:xiaomi/mimo-v2.6-flash | defaultconfig_b4c12e159d3c1da18bc2ad79d30a270af23c7e08657ecd1ac356edab523754c6 | 24% | Unknown | 1 |
| 18 | anthropic/claude-opus-4-8 terminal-bench-4-0-vals:anthropic/claude-opus-4-8 | compute=maxconfig_540adb5f78ac9fe44082a7a2694b705c2cca2b92f3ebd8b49c7dde4a3c4ab2f2 | 23% | Unknown | 1 |
| 19 | openai/gpt-5.6-terra terminal-bench-4-0-vals:openai/gpt-5.6-terra | reasoning=maxconfig_0993015166c262f4b216603f11ec54adbf3936f66223f0e7e760e42c79c6a861 | 23% | Unknown | 1 |
| 20 | fireworks/ember-1 terminal-bench-4-0-vals:fireworks/ember-1 | defaultconfig_a0c6ecd1e9b60e1d8d6b418da5cd611d6c029fd5073728fee74db05f506c790f | 20% | Unknown | 1 |
| 21 | deepseek/deepseek-v4.1-flash terminal-bench-4-0-vals:deepseek/deepseek-v4.1-flash | reasoning=highconfig_c4355251c294cf15f1fb54f6a338c4c1e3ea8eadc92a124142e83c831b98a8c9 | 20% | Unknown | 1 |
| 22 | google/gemini-3.8-flash terminal-bench-4-0-vals:google/gemini-3.8-flash | reasoning=highconfig_a30cac704fbf79d0b165856bd68d8ed0af95f405bd50e0b68ecc51b31b7dfc19 | 19% | Unknown | 1 |
| 23 | deepseek/deepseek-v4-flash-0731 terminal-bench-4-0-vals:deepseek/deepseek-v4-flash-0731 | reasoning=highconfig_0204198771df2c3f1bef5557f3686b47d1e55a01ff50d1bcfb3db139aec2b74b | 19% | Unknown | 1 |
| 24 | grok/grok-4.6 terminal-bench-4-0-vals:grok/grok-4.6 | reasoning=highconfig_9e8d633448661f79c0fdb1c08509456cb720cc89337254ec884ecbea47ad5147 | 17% | Unknown | 1 |
| 25 | kimi/kimi-k3 terminal-bench-4-0-vals:kimi/kimi-k3 | reasoning=maxconfig_be64bf8ed01d55f5c88b49670194f946577ea65d4a4a197ac80f2d2a2758b835 | 17% | Unknown | 1 |
| 26 | deepseek/deepseek-v4-pro-0813 terminal-bench-4-0-vals:deepseek/deepseek-v4-pro-0813 | reasoning=maxconfig_b83e2f5246663d4d6928cdf32f606f927bef1925ee1ee2eb8179bb59a5122730 | 14% | Unknown | 1 |
| 27 | openai/gpt-6-luna terminal-bench-4-0-vals:openai/gpt-6-luna | reasoning=maxconfig_5cb7a67653491267af1fd8a5e97656645d5b80b6d2ea0408b00df1963a744d77 | 14% | Unknown | 1 |
| 28 | google/gemini-3.7-flash terminal-bench-4-0-vals:google/gemini-3.7-flash | reasoning=highconfig_82c97f298a4f94bfe7873ce46e54168646d28e702fbf7a03a26a2c5c91d02d81 | 12% | Unknown | 1 |
| 29 | openai/gpt-5.6-luna terminal-bench-4-0-vals:openai/gpt-5.6-luna | reasoning=maxconfig_eb87fed710f68897414f2529ba062cd0d122a5cae2bc1170ca337f9b5c16eb7d | 12% | Unknown | 1 |
| 30 | deepseek/deepseek-v4-pro terminal-bench-4-0-vals:deepseek/deepseek-v4-pro | reasoning=maxconfig_b46069b13f6cc75c94a1cd4c6b94aeb68169646ee9915ec82c7e2e3b320bce96 | 11% | Unknown | 1 |
| 31 | meta/muse_spark_1_3 terminal-bench-4-0-vals:meta/muse_spark_1_3 | reasoning=xhighconfig_918c0d6b60ddf45f2aa9956a1bc68b8418596e27bcefc46c1302a706d2165873 | 11% | Unknown | 1 |
Not enough independent evidence for a top set
- Calibration has not been validated
- Configuration overlap is below the required threshold
- Independent benchmark-family coverage is below the required threshold
Model configuration · Direct prompt
Exploratory - not a ranked winner yetrg-coding-general-model-configuration-direct-prompt-model-configuration-v1Explorer evidence
SciCode
Single source. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | claude-opus-5-5_max 2026-09-22config_615286dd45fabfebf02aefcba78d965a472ffb6a11779de817616fbe5e28d0c1 | 67% | Unknown | 1 |
| 2 | claude-opus-5-5_xhigh 2026-09-22config_ba8636b94b5dd27a0e19d53863c7014f0c548be6d5ebe64a1b0f7cbe300a456d | 65% | Unknown | 1 |
| 3 | claude-fable-5-1_max 2026-09-01config_a6076001bf935f1296f984fa9162c7ccdc76d4c9c97658005d83358294040f04 | 63% | Unknown | 1 |
| 4 | claude-sonnet-5-5_max 2026-09-28config_671729f3f704d6e6ccaab98533c53f5f60ad871b1ee20ae8e493ac4e6d798964 | 61% | Unknown | 1 |
| 5 | claude-fable-5_max 2026-06-09config_8d34c7dd565f0a64b9d80273b41cbbdfa54d2e2a9f8e5b9fc3802846f3aa05c4 | 61% | Unknown | 1 |
| 6 | claude-fable-5-1_xhigh 2026-09-01config_884a261d5d22ca698359dd9e09cc5f0963e79ad4a66f796a782f93dbcedd5fcb | 61% | Unknown | 1 |
| 7 | gemini-3.7-flash_medium 2026-08-13config_5fd6c4e19fcadb7a4b0958eb38718afb7f782eb6e4d690af40907dd1c7ff1e63 | 60% | Unknown | 1 |
| 8 | muse-spark-1.3_xhigh 2026-09-02config_2a3349f3ecee52da8e72f0826fc36b0e1f37d7c3a3a53f99b9baa0a7214ea9c2 | 60% | Unknown | 1 |
| 9 | kimi-k3_max 2026-07-16config_791ec027f5af4a572a0f86ba7fd19468c86cf9465f642ce5d917dc169ab4bec5 | 59% | Unknown | 1 |
| 10 | glm-5.3_max 2026-08-14config_42192399c396e73e6c0205ae00ee0856a5002bf83bc2eedd49770b9da8c7c2e4 | 59% | Unknown | 1 |
| 11 | gemini-3.1-pro-preview 2026-02-19config_76cb6b8fc4da622a11f59e9b038fb836eaadd1f9bffb7e86002237b552cc9843 | 59% | Unknown | 1 |
| 12 | step-5-preview_unknown 2026-09-18config_bdf4856c7934b836ce742a9b876094f7a53a68aabb69d91e776432c75f0b52b8 | 59% | Unknown | 1 |
| 13 | muse-spark-1.1 2026-07-09config_6680c7d899264ddc8f1d2f7d9f6853c6228654243b1a5537a6bb29a4ef3cc99e | 59% | Unknown | 1 |
| 14 | muse-spark-1.3_max 2026-09-02config_c13fa994d7158c6a853f80b6102a28d6ad871ea5df34526328281dfd0132b747 | 59% | Unknown | 1 |
| 15 | kimi-k3_unknown 2026-07-16config_c9aa04521808d1807739cae4874472c3e1b7bf1138f50ef1fd7b2827e58e79ae | 59% | Unknown | 1 |
| 16 | gpt-6-sol_max 2026-09-22config_44ae9f94f7d14cc2bdafe2a6f01e7d755c48a41faa56aecbf2a435e87f9915ef | 58% | Unknown | 1 |
| 17 | claude-fable-5-1_high 2026-09-01config_63c28d8c765c4a2a84620cb3ea9b414c74113aa2c0e49e706e6a7181a1b0aa96 | 58% | Unknown | 1 |
| 18 | grok-4.7_xhigh 2026-09-21config_62bc8052a93c4c9a8770401180676ea071b8723bca32f13b1905e39effc3cb88 | 57% | Unknown | 1 |
| 19 | claude-sonnet-5-5_xhigh 2026-09-28config_0693c125ec2782955539f5f58f84b407eb6896d4c0c777a2216b139c6783b82f | 57% | Unknown | 1 |
| 20 | gpt-5.6-sol_max 2026-07-09config_e9bcda6fe53e43ea0987c97fedca02faba145cf031cd812a774962378408bf5d | 57% | Unknown | 1 |
| 21 | gpt-5.6-sol_high 2026-07-09config_b1c49e08e997de1c153eed302e14b36503eb947024c48ad2dcc7ceb1c8cdd8df | 57% | Unknown | 1 |
| 22 | gemini-3.7-flash_high 2026-08-13config_252b2194b7913190676c7285c409d58d1f7ced98f0c23d17f5e70112c57d97aa | 57% | Unknown | 1 |
| 23 | gpt-5.4-2026-03-05_xhighconfig_669ac29314d587df9c29b141b60d7f18b676f6c745cdec1c00fbdf054590d742 | 57% | Unknown | 1 |
| 24 | gemini-3.8-flash_high 2026-09-02config_ece8382f182be858981c48e45b5072a7d0521f5beedb12676ef8c39f252432a8 | 57% | Unknown | 1 |
| 25 | grok-4.6_high 2026-08-12config_2c3ae454f76941bc7e0e035803e9e0b06353263df02f4817bf426751cb03901b | 56% | Unknown | 1 |
| 26 | gpt-6-astra_max 2026-09-03config_5267daaa34626e1a85d5ac3f6fb418a7a7330bdc531aaef28ace49e29107e25f | 56% | Unknown | 1 |
| 27 | gpt-5.6-sol_medium 2026-07-09config_eea78c5408e90b7ad45d3b13df0096eeebff4bfb700d3eeb4b76832c41b2493e | 56% | Unknown | 1 |
| 28 | muse-spark-1.2_xhigh 2026-08-05config_a685bdd6550d69ac8d80e8ba4fa11f5106e949969df50bd0dc4065f83a39653a | 56% | Unknown | 1 |
| 29 | claude-opus-5_max 2026-07-24config_d37ed7f2218f8db72bc665b7698b73d353a4c7b7f2f08e1fb26a6c337af15f1c | 56% | Unknown | 1 |
| 30 | gpt-5.5_xhigh 2026-04-23config_6bdb619e31ddb97012a20bec5ed65bc5153c6e17d25f78a533b07021da71dd73 | 56% | Unknown | 1 |
| 31 | gpt-5.6-sol_xhigh 2026-07-09config_fbb700dd2a4d6ed3826e845aafdbdbdd23516b66b7a13378e55580eedf64efc9 | 56% | Unknown | 1 |
| 32 | gpt-5.5_high 2026-04-23config_6fe8b127afb282f826d52a71c04ab196a4600fdf79ad25bee81b3ca82ec68ee6 | 56% | Unknown | 1 |
| 33 | gpt-6.1-sol_high 2026-09-29config_99715aec0fb0b8749d02f8b96ec050f3f0d06b44ecd14e5f572f1679d75ec2bd | 56% | Unknown | 1 |
| 34 | gpt-6-astra_xhigh 2026-09-03config_78d846c401c8e0d64f64bee090b543d5e5854859ac52ed584dd1405fa7e37e7b | 56% | Unknown | 1 |
| 35 | gpt-6.1-sol_xhigh 2026-09-29config_ea4c74932b8d2bf79da57596e4bf6630ef4eece91f32436e7ddf922ca47a828c | 56% | Unknown | 1 |
| 36 | claude-fable-5-1_low 2026-09-01config_ffdbf24b07f612a5e2615ed2f60e07994588d0257fcb12ad05823c5d72143b86 | 56% | Unknown | 1 |
| 37 | gpt-5.6-sol_low 2026-07-09config_a459e72f9c5ae0f7fb7d3c28bd95da1989a9f357a698c18222bff2fe09d603df | 55% | Unknown | 1 |
| 38 | gpt-6-astra_high 2026-09-03config_f2e8017e7bcb2ad35f5d7b374d2b765fafe68c3c5b817615d704188f6dbd094f | 55% | Unknown | 1 |
| 39 | claude-fable-5-1_medium 2026-09-01config_12706c36d8a018a242732abf19894b40b15e63df68f961cd0fc36bdaaf316417 | 55% | Unknown | 1 |
| 40 | gpt-6-sol_xhigh 2026-09-22config_1cdcd93fe75fc1b74a8822a43819402494b442f6123da83eb6dd2637053a6712 | 55% | Unknown | 1 |
| 41 | claude-opus-5_xhigh 2026-07-24config_312386a3a2ba3625b9836322e87ace7d81d1f6e72e39756cb61b78b92c57360a | 55% | Unknown | 1 |
| 42 | gpt-5.6-terra_max 2026-07-09config_db7181a1fd41f70a11857a1dcfce4aa056fe82eea448f6622f23c133b4493ef7 | 55% | Unknown | 1 |
| 43 | gpt-6-sol_high 2026-09-22config_bdc9a0fee5a0491133abb3cbf3a5e3c373c3972c6751d7139991c045114be06f | 55% | Unknown | 1 |
| 44 | gpt-6-luna_max 2026-09-22config_16765158e580fa584d9f2e0e672cd9f2252f807f8158052be80add739edd60e2 | 55% | Unknown | 1 |
| 45 | grok-4.6_medium 2026-08-12config_67191731d5fd8381636a6f1d5a3a912bd2d5e6ac70f198ca5cab6d35a6a6941f | 55% | Unknown | 1 |
| 46 | claude-opus-4-7_max 2026-04-16config_762f169f1a30ab912f52f0d6c4ff6e3bfab1e423fb035deee5c85a4291f012fe | 55% | Unknown | 1 |
| 47 | gemini-3.8-flash_medium 2026-09-02config_acf00b5edb3e1de1eb0d349772aace957a6160319fcaea20186a1c394ea755e3 | 54% | Unknown | 1 |
| 48 | gemini-3.8-flash_low 2026-09-02config_82e6cd6528274b837b58e927600386addf2b04cc0d527705ffe8be51062b6fad | 54% | Unknown | 1 |
| 49 | claude-opus-5_high 2026-07-24config_e9999c2aeeab0e14fcf36e83362dfeaf1edd3fec4048f59500790d96b703dc66 | 54% | Unknown | 1 |
| 50 | gpt-6-astra_medium 2026-09-03config_7e4a36fee2e9492463224b6685d7622dcb68bab1b619ba395cca309edad8ef3e | 54% | Unknown | 1 |
| 51 | gpt-6.1-sol_max 2026-09-29config_feb79dc487de98f5515eafdc7b2e85af82d83d017ec55b42965e6a483e3d9301 | 54% | Unknown | 1 |
| 52 | gpt-6-astra_low 2026-09-03config_cf1c15ea587fe4d9c76ac14b65833322007a6caf34e83c79ecd245a866017cf4 | 54% | Unknown | 1 |
| 53 | grok-4.5_high 2026-07-08config_d688c3f6fe1bde5d205a6f530c34747b650591d51a7413cf665117d6db083a43 | 54% | Unknown | 1 |
| 54 | gpt-6-sol_medium 2026-09-22config_a4ca601ea10480c7da7c194470e18fe4fd02a4485a6d792346e448b79be917a4 | 54% | Unknown | 1 |
| 55 | claude-sonnet-5-5_high 2026-09-28config_f070acda043f5bafadd5fa7314c71b7f79065416d3febbe31d343463b7fcdee1 | 54% | Unknown | 1 |
| 56 | gpt-5.6-luna_max 2026-07-09config_989b322cd958cd6fb81306abf29cd34ec8dd8c9ba3a20a591476d31b6a5939cf | 54% | Unknown | 1 |
| 57 | claude-sonnet-5_max 2026-06-30config_a7307c6e09f25db9ed990b968b511109dfa6c72816ae60d119dc20d2da0030f2 | 54% | Unknown | 1 |
| 58 | gemini-3.7-flash_low 2026-08-13config_d3c884e85f28bda9e9edd3e8e47ed833e033b90c23589e4d55aa4f69527b52c7 | 54% | Unknown | 1 |
| 59 | kimi-k2.6 2026-04-20config_79715e092ebd32adbe6a8ef5b8a297d057b1344f6dab572c9d7bc5aceab3e4ad | 53% | Unknown | 1 |
| 60 | gpt-6-astra_none 2026-09-03config_9a499acab7ca7e601e1b9875cd1f22632cbad995914292c292dfae2f0b7fa1be | 53% | Unknown | 1 |
| 61 | gpt-5.5_medium 2026-04-23config_a6780722f3adc177d2e5e1cd2a3b4a788ec9cf7733dbbed578b87daa18b83977 | 53% | Unknown | 1 |
| 62 | claude-opus-4-8_max 2026-05-28config_c314fa4ba0dc0d51e164bc7dd183557311e01b2847a04dd5c261591fc008f795 | 53% | Unknown | 1 |
| 63 | gpt-6.1-sol_low 2026-09-29config_240009592373e6adea1b6d996efe1ab8f7ae42ac59a42d1c7dac2df226441ae4 | 53% | Unknown | 1 |
| 64 | gpt-6.1-sol_medium 2026-09-29config_fe4a753b47cd021e5a74d56153451ab29949c5ce041b50334ce3eed1eae69861 | 53% | Unknown | 1 |
| 65 | gemini-3.5-flash_high 2026-05-19config_f2cf13bd16c061b723ac04842a531b64710db17c84d0beef2d0ae13408ffa37c | 53% | Unknown | 1 |
| 66 | claude-sonnet-5-5_medium 2026-09-28config_ce0fa7ad82bc0ba8e27283bf054e7100ef84fe6a2cd3df9a7d5d63f2c85c8ae6 | 53% | Unknown | 1 |
| 67 | qwen3.8-max_unknown 2026-08-02config_e34335ece4d5650eb4163f01da8f9e9fd96a7beffdc8522c4869db34e6090376 | 53% | Unknown | 1 |
| 68 | gemini-3.6-flash_high 2026-07-21config_9d58866eb3ebe691a869604d6d411d345a0304b36738e139c704ef0f4bda13d2 | 53% | Unknown | 1 |
| 69 | qwen3.8-max-0902_unknown 2026-09-01config_f24232a8fe917b99a69105d2bcf33e5aaaa17945c17c7893d9df8cfdd0b95716 | 52% | Unknown | 1 |
| 70 | deepseek-v4.1-flash_max 2026-09-09config_f17a690b7481f04ee8090baa9c7e44dd2c5b5ec66d05fccabdd2eb59f76ad846 | 52% | Unknown | 1 |
| 71 | gpt-6-luna_xhigh 2026-09-22config_b8ead4c846a2061f5263e995721081153c46bef384863363add65bc9782ab756 | 52% | Unknown | 1 |
| 72 | gpt-5.6-terra_xhigh 2026-07-09config_251a7e7e7639b18501059f025164f936fd80db25cd528a28e82435ab5492afd6 | 52% | Unknown | 1 |
| 73 | grok-4.6_xhigh 2026-08-12config_463bb25e9e981dfb2245c95419db6651f6967b6778260621fcd1b8783a98e5a0 | 52% | Unknown | 1 |
| 74 | glm-5.3-flash_unknown 2026-08-20config_ba868af48ba4cb4c664c041039aef0abcf7fadae6f18013514bcd4e76a1e06af | 52% | Unknown | 1 |
| 75 | gpt-5.5_low 2026-04-23config_ec648392146d2532f4be837e945ad5a55f79b5a7208f1c8e3c5068f4503d69db | 52% | Unknown | 1 |
| 76 | muse-spark 2026-04-08config_d44b10f0e691c37e7c14b057261d6a0b88129cab973e5a6904128f219f34f30e | 52% | Unknown | 1 |
| 77 | kimi-k3_low 2026-07-16config_66d32224605aee43bf54df51128a98e1bd5e5c6bb1de424ac23df3814443afe3 | 51% | Unknown | 1 |
| 78 | deepseek-v4-pro-0813_max 2026-08-13config_86a6cc942f5d19f2ce63142182bc5c2feba0b24eea21990c1ca66962e918c819 | 51% | Unknown | 1 |
| 79 | gpt-6-luna_medium 2026-09-22config_69451fa34be1c5e88bbbbf0439e98621fc4d58df1521dfc9e4ad8f833a358b17 | 51% | Unknown | 1 |
| 80 | claude-opus-5_medium 2026-07-24config_6a7ee5b9215fb4c23727c8a8c3fc01013e9803f28750d5fe66268220e053baa8 | 51% | Unknown | 1 |
| 81 | gpt-5.6-luna_high 2026-07-09config_da7e43ddbb52e83bf9aa9050b977b50a26803619b115cb0faf356b5da2a4cced | 51% | Unknown | 1 |
| 82 | glm-5.2_max 2026-06-16config_571fdd7e9340dbf9f406957f65f04ee9c211d7f4bfbb3fc068978499bea908d0 | 50% | Unknown | 1 |
| 83 | gpt-6-luna_high 2026-09-22config_6459684371a0807917c1ff92edbc7c603a79cef173453ecf99a3c857eb6fa64e | 50% | Unknown | 1 |
| 84 | grok-build-0.1 2026-05-29config_22a107e3f9a2a93b4e0466b2196fdaeb6eb7e2fe864e7df301c890432f133884 | 50% | Unknown | 1 |
| 85 | mimo-v2.5-pro release-date-unknownconfig_5aa91367a1a7b6524aa888f2a77ede1c57279a85a010fe2f73a13968f68df68d | 50% | Unknown | 1 |
| 86 | gpt-6-sol_low 2026-09-22config_cbe5be89a1386820815d0f036e51f15c66edec3b914edce49efe0b79b877509b | 50% | Unknown | 1 |
| 87 | gpt-5.6-terra_high 2026-07-09config_b78128bff264e4562779e78cc2eb7e9d5716cf6a3bae36d45622c43e87640691 | 50% | Unknown | 1 |
| 88 | gpt-5.6-luna_xhigh 2026-07-09config_653dc4a5d4975f79eff61818cbc1e54a7065041af2e1ee8b5796dc1a5afae2bb | 50% | Unknown | 1 |
| 89 | deepseek-v4-pro_max 2026-04-24config_81a148910f4f5d063c4777c130c3a1c7ec9c31ee69404157936c264a9955c69e | 50% | Unknown | 1 |
| 90 | deepseek-v4-flash-0731_max 2026-07-31config_76e966a5ae67c85215c7c7be133d724a9883d671e92adae32024d7fbcf749462 | 50% | Unknown | 1 |
| 91 | gpt-5.4-mini-2026-03-17_xhighconfig_90113919307e454d6b5479bb60f895955d1bc9db4962a5fbf94e993d6f6c29c7 | 50% | Unknown | 1 |
| 92 | gpt-5.6-terra_medium 2026-07-09config_241b121c7d2e6b95f945238d34c885c6c3636edd335d093bcf97e8223ada0c6d | 50% | Unknown | 1 |
| 93 | gpt-5.6-terra_low 2026-07-09config_7dab082dd78507bd38fc749f982bbd00c6ad0a831fbf95ebc0013806920c6f53 | 49% | Unknown | 1 |
| 94 | claude-sonnet-5-5_low 2026-09-28config_db8e0da131a73ac0d606f57e460bd54014b03ea08c2f11c07bc1c2c10c678999 | 49% | Unknown | 1 |
| 95 | kimi-k2.5 2026-01-27config_20bd261d79345ca93b7e9f8fbffbe3ffb337c6bbc53984181992ebbf13c7bfa2 | 49% | Unknown | 1 |
| 96 | qwen3.7-max 2026-05-19config_b640a0f0f574deb0fe63a981004ecf305a377bedb269ae6fc804b2bbd575f11c | 49% | Unknown | 1 |
| 97 | inkling-small 2026-07-15config_58bd495dff29b35aab1d3c2e11ea2c2b58afae23c787418eeeac36880376d4ae | 49% | Unknown | 1 |
| 98 | claude-sonnet-5_high 2026-06-30config_23988381db43c57d763714bc3afbc1146f6ebd7bd60ad3f3918eff30e2ea45ac | 49% | Unknown | 1 |
| 99 | gpt-5.5-instant 2026-05-05config_b8dee1aa7b5f25e8f711bb4620aec7e478ad12818b8c3b266a6bd88950a4d836 | 49% | Unknown | 1 |
| 100 | grok-4.6_low 2026-08-12config_646eb5c4fc15d8d88989b154bf3b99aac4123ea2b34d8135d59e5fc9d1552a41 | 48% | Unknown | 1 |
| 101 | claude-opus-5_low 2026-07-24config_2c9a5523fed36b3b8deec3235a526f7cb7a36e630ca79a86dfd92ce8ed94c308 | 48% | Unknown | 1 |
| 102 | kimi-k2.7-code 2026-06-12config_60744ea1e7a29d77cbabcb1a95f52e174f0d596baf5b52657391d809e36c4e69 | 47% | Unknown | 1 |
| 103 | gpt-5.5_none 2026-04-23config_437fe38e94e8949f6b6881553245e45e95dc59f5c9f5a7f2b46863bf226428d7 | 47% | Unknown | 1 |
| 104 | gpt-6-sol_none 2026-09-22config_7c25f3bc88ee60db87d31f80ce3fdc6d557cd98f00d76766273a4a0c5794c301 | 47% | Unknown | 1 |
| 105 | grok-4.3_high 2026-04-17config_a1a2c651310bebb3494112d0f64a62aad3c2130a00966eb00a50d3301c566ccd | 47% | Unknown | 1 |
| 106 | gpt-5.6-sol_none 2026-07-09config_27d8490506ac6353a26b3829dfe8d385c7e65ff0402e082002ed6f3f2569e448 | 47% | Unknown | 1 |
| 107 | MiniMax-M3 2026-06-01config_3e0345326dec03865c1da9b9ff9ae505682cdfce8ebcac223715115d75e1bb2f | 47% | Unknown | 1 |
| 108 | MiniMax-M2.7 2026-03-18config_05fa227f49ebb1dccf5e37d0409c290368b83cb9423fe7dd4bdf6e5cde679f08 | 47% | Unknown | 1 |
| 109 | Inkling_xhigh 2026-07-15config_a3c17abae4ac37adac7664737b450c5b4424dc6c2c18e8db5b916196bbcc6cd6 | 47% | Unknown | 1 |
| 110 | gpt-5.4-nano-2026-03-17_xhighconfig_1006c1e67674b237aa77dce044a83d6821a42594ee504ed85e807772b57ec8d7 | 47% | Unknown | 1 |
| 111 | gpt-6-luna_low 2026-09-22config_a4d6cd3443b8b47f2ec839cf30a7d887046a580f6fbe3a0bcd6b608bcec8d349 | 47% | Unknown | 1 |
| 112 | claude-sonnet-4-6_max 2026-02-17config_d0372d242a2ba1e1b4e220a76be2b1396abc61a2d94cf69497d19520b1bb6a95 | 47% | Unknown | 1 |
| 113 | qwen3.8-27b_xhigh 2026-08-14config_1e9ee0b8b6d053f9b2a458a3e7d921d2141effc25178a2b7a1422faf38701c77 | 47% | Unknown | 1 |
| 114 | deepseek-v4-pro_high 2026-04-24config_4711a6c093dc5b8fb240f9f079eb13e040171a66491b39e8479c46d42f16c280 | 46% | Unknown | 1 |
| 115 | gpt-5.6-luna_medium 2026-07-09config_27bfdb387a4de1eadb3545d80dae8e599b9d58d004c053060cbfdd489441a039 | 46% | Unknown | 1 |
| 116 | gpt-5.6-luna_low 2026-07-09config_a1a6da6bd693ef055e1331128e4607802c4ba9e8deef96bf02c4522b68f3f3cc | 46% | Unknown | 1 |
| 117 | qwen3.7-plus 2026-06-02config_d901dbedd55623d8973f4873c3b1b477369eb1394f02ade85b320ce2e9e9bc98 | 45% | Unknown | 1 |
| 118 | glm-4.7 2025-12-22config_e90fe935b7223033014e06472037aac522adeb8392728db7ac0492c29e403528 | 45% | Unknown | 1 |
| 119 | deepseek-v4-flash_max 2026-04-24config_5c6c3baca5ad00d855c323b236f792df125149dfabe3e5c86587c0625ce30cde | 45% | Unknown | 1 |
| 120 | claude-sonnet-4-5-20250929_unknown 2025-09-29config_8a04dd7a8a2743318e8e500db970d741f511352ae3a1d5c202337bf9199b273a | 45% | Unknown | 1 |
| 121 | gpt-5.6-terra_none 2026-07-09config_9611de6513af4a2099149e6652d41274a05bc624c94f0daa1fc7df1c94f066e0 | 45% | Unknown | 1 |
| 122 | glm-5.1 2026-04-07config_e2805e433c7480c6933d82a7c7df43d82c39a8ab24bbabca1373901f98c3e1c8 | 44% | Unknown | 1 |
| 123 | gemma-4-31b-it 2026-04-02config_5d4ed362cd6b97e04954292d38c11698bdeee4f2da90f07076cf41141dcaf05f | 43% | Unknown | 1 |
| 124 | gpt-5.1-2025-11-13_unknownconfig_8b5491c3be63ebfdf517e9246d2ef5eec0787338aaeadbaeaf6d5316e49de141 | 43% | Unknown | 1 |
| 125 | claude-haiku-4-5-20251001_unknown 2025-10-15config_b52b218b85b2634fa04105db87a32de04aa538c93b99351d894658b8a6b46979 | 43% | Unknown | 1 |
| 126 | gpt-6-luna_none 2026-09-22config_860c68884b4d4ab198f28e1301359d2ead876a14f27af884020f8332484f8c86 | 43% | Unknown | 1 |
| 127 | mimo-v2.5 release-date-unknownconfig_f3bc5dd6afb01b14076a26df6e2a0b6dfe7736211da999280e4239c3f5926d17 | 43% | Unknown | 1 |
| 128 | gpt-5-2025-08-07_unknownconfig_2a460ed4a4ca6de1d7d8e878909ca11ac0024440d524db07689139f155781e7d | 43% | Unknown | 1 |
| 129 | gemini-2.5-pro 2025-06-17config_dec9e48828317d5256e58ace29fed0ecfaf24436f73789208651a601d05a99c6 | 43% | Unknown | 1 |
| 130 | nova-2.0-pro-preview_medium 2025-12-02config_c1afb4d3d186dcfb0a7a2dbae14282313fbc145f8637a0a2c7bcfe3c51121a58 | 43% | Unknown | 1 |
| 131 | Ring-2.6-1T 2026-05-14config_88561a1e72f466768164d0f4d1875455f40f137ac0478f166ce84d6552233455 | 42% | Unknown | 1 |
| 132 | qwen/qwen3-235b-a22b-thinking-2507 2025-07-25config_f65eacad809480c5d16bd941054fe6438d365ad2e7146ae25e3b58307a13cce6 | 42% | Unknown | 1 |
| 133 | deepseek-v4-flash_high 2026-04-24config_35f47baa2f1110762c9dca07efa1422791b7a7d96bb69a60df3e308304c77bfb | 42% | Unknown | 1 |
| 134 | gemini-3.1-flash-lite 2026-03-03config_64a7c3cc333e2660ef8fcbc28f443cfa085f4faa47601ce6b925d97e6f2a8e8d | 42% | Unknown | 1 |
| 135 | gemini-3.5-flash-lite 2026-07-21config_cd4b9ecaee2da72560e9d37627ea3673aaecf8e9f677e19099622072d109d984 | 41% | Unknown | 1 |
| 136 | cogito-671b-v2.1 2025-11-19config_81713fa14591c58e9fb5ea75f0cea65db071c4f219654a8a7ac7424cc799ca47 | 41% | Unknown | 1 |
| 137 | qwen3.6-plus 2026-03-31config_ba187e15c28e9dcb5bf3c4a6c1ae54e87ed4e2d6c30dc01a778ccb48a17de501 | 41% | Unknown | 1 |
| 138 | DeepSeek-V3.1-Terminus 2025-09-22config_1a01d1e19901054f66be56a4eae790458b0b4c6cb7b965c62d14903a4eb588f4 | 41% | Unknown | 1 |
| 139 | gpt-4.1-mini-2025-04-14config_6b85e11f7ab1ef935099dcca6871f92a6d903d7f57eb2b91ea9b4598d533d5ae | 40% | Unknown | 1 |
| 140 | nemotron-3-ultra 2026-06-04config_e433fc48f41447d0739be78ed3ccbc594d0a744da877a350c22483de9195211b | 40% | Unknown | 1 |
| 141 | mistral-medium-2604 2026-04-28config_4e5713daf77202aa06a42f29e4d949737d45ab429402d01fa166118cbbccf61b | 40% | Unknown | 1 |
| 142 | gemma-4-26b-a4b 2026-04-02config_3f1c545a55462aa7cc63b40a36d332857ea8e7747de5cd63da7f0fd6b244922a | 40% | Unknown | 1 |
| 143 | step-3.7-flash 2026-05-29config_43ced50d4366da53bade6032e3f34a196c33ad7aad0caa5ff56f24abe5a8f4ef | 40% | Unknown | 1 |
| 144 | claude-sonnet-4-20250514_unknown 2025-05-22config_7dc87305abb3ebe9d2a98e595e01049d9ca214dfd79be3726a13addcdb0146a2 | 40% | Unknown | 1 |
| 145 | gpt-5.6-luna_none 2026-07-09config_6224d05383bc48cd3bb6b59d9ea9e64a3b6d9fe5872c8af125eec337c81c1507 | 40% | Unknown | 1 |
| 146 | qwen3.8-27b_low 2026-08-14config_c7c84d2aaf59c85ec74c7a51cbdba9377088473edbfda3ba01c629aff0a55b12 | 40% | Unknown | 1 |
| 147 | o3-mini-2025-01-31_highconfig_450cc2517c440acd4571f960842be14bd6b5eb04d4d3d5f95eed219122ef7940 | 40% | Unknown | 1 |
| 148 | magistral-medium-2509 2025-09-18config_522ad7ac268e3523a0b75597a349125b923f956d6994489847634c71a35f7c27 | 39% | Unknown | 1 |
| 149 | gpt-5-mini-2025-08-07_unknownconfig_5301094fd5f5ddffa482b7f86d87bcfcc9ceec55481e2ec4dc8c4e4de08035a6 | 39% | Unknown | 1 |
| 150 | DeepSeek-V3.2-Exp_thinking 2025-09-29config_6156beb18892bed933396e6758c2bfc7ab0fb8912e9b7971d38722f38f1cf223 | 39% | Unknown | 1 |
| 151 | mercury-2 release-date-unknownconfig_a91752b46680fd924fe1b0b1c99dfdfe1d42672eb8d1647ead9e647334275070 | 39% | Unknown | 1 |
| 152 | nova-2.0-pro-preview_low 2025-12-02config_e208597df5d4666c10b0c0f84f17a406a9b752cf6f506767458916e341aceeca | 39% | Unknown | 1 |
| 153 | glm-4.6 2025-09-30config_81d11e6642bfd30b4ada219aebe5cf98871e21289a9cf211a4140d8ca2cfe6c0 | 38% | Unknown | 1 |
| 154 | qwen3.8-27b_medium 2026-08-14config_2cf20c36ac28efda1871137db448642a27a2aff7109df9a472d5271a99c02fc4 | 38% | Unknown | 1 |
| 155 | command-a-plus-05-2026 2026-05-20config_5493facb85dbb26d691725454952fe078bbd87146c0c24775bd2cd520464917a | 38% | Unknown | 1 |
| 156 | qwen3.6-27b_none 2026-04-22config_e8510459f7c9464b252d9fa5007035686d441f03e0e106c9267c866cd9d769cb | 37% | Unknown | 1 |
| 157 | mistral-large-2512 2025-12-02config_a64c2db86ca74d1ae45a6d62a8ab90037d6857a6e800cf9ee4e530a483beaef7 | 36% | Unknown | 1 |
| 158 | glm-5.2_none 2026-06-16config_0879f349206e030c802fe410aa3c803e0c1c1c8bcd2a4161d4396dabc82138f7 | 36% | Unknown | 1 |
| 159 | trinity-large-thinking 2026-04-01config_188bc4dc2e65ef50be534bf6fa49dc10551fad8ec4bb95693bc7f3d64dbc04a2 | 36% | Unknown | 1 |
| 160 | nemotron-3-super 2026-03-11config_46af45918e1128ff007dff07f810f712b55fa57bc3c94598a9657952ab5f22fb | 36% | Unknown | 1 |
| 161 | openai/gpt-oss-120b_low 2025-08-05config_5efeadf639159b56101e9ec27c9c5e1440de969d0973ddbaa6b637906aec8840 | 36% | Unknown | 1 |
| 162 | qwen3.6-35b-a3b 2026-04-14config_050cb6baec8daf05b2f6cb82f435bad28f9126f2e06f6747616a824ad953baba | 36% | Unknown | 1 |
| 163 | DeepSeek-V3-0324 2025-03-24config_23bb0162ff1536ba7325eebf284efa88aa13b1b7830d459bb70e8f3ae451e2af | 36% | Unknown | 1 |
| 164 | DeepSeek-R1 2025-01-20config_7afa399dfb44106d86f16805e28e2cd12eea7ca40c633bfa59fc294ac49ac976 | 36% | Unknown | 1 |
| 165 | qwen3.5-122b-a10b_none 2026-02-24config_48a043346f3837173faeb7cf95698771d0ccb9e3e65d828bc7ec8232275506b9 | 36% | Unknown | 1 |
| 166 | qwen3.8-27b_none 2026-08-14config_8faab16bf0dd6906e8159a8f9cc3dd049de2b2f9ced9f3c2bd6b5a868187c090 | 36% | Unknown | 1 |
| 167 | Qwen3-32B 2025-04-29config_0e299bb5ddc73088dbdfedaa5ad96fb9732811f115f58fdb54298ff8f9a88f98 | 35% | Unknown | 1 |
| 168 | DeepSeek-V3 2024-12-26config_bad7c38702fcc9b2074f85ebe36cb005cfa52392bb54f670dc3fadf655301aa1 | 35% | Unknown | 1 |
| 169 | magistral-small-2509 2025-09-18config_232e116cd28cc4d2e0faac8ced4f80da93a6b798ffe66809ac21749fa2d59eac | 35% | Unknown | 1 |
| 170 | gpt-oss-20b_high 2025-08-05config_18fa4cb3e5d4b047a8af64ba854d4f9c4e236e299423e26f0ae545777075737f | 34% | Unknown | 1 |
| 171 | openai/gpt-oss-120b_high 2025-08-05config_9a4aef65c33423239cdc482e0eb1c4eb00d87b8123274c4e5a1937366fde5391 | 34% | Unknown | 1 |
| 172 | mistral-medium-2508 2025-08-12config_a9507a14d2181b09c54f36c4f3953de4a33cd4fe4f054f3c99eabe2d5bf15151 | 34% | Unknown | 1 |
| 173 | qwen3-30b-a3b-thinking-2507 2025-07-30config_3f600e20b035a28ca264beb701cf9ad19526a7e8ec5c5bef34e72618799d7b5b | 33% | Unknown | 1 |
| 174 | Llama-4-Maverick-17B-128E-Instruct 2025-04-05config_c85f902ef6cfd9a335fe0671f53a15c142fe7c28bfec02ab65d89f27dc1174e1 | 33% | Unknown | 1 |
| 175 | qwen3-coder-next 2026-02-02config_600578749286bb50d3412986980029a49b12ce3e4b9fcb44c49f5d22c9a22829 | 32% | Unknown | 1 |
| 176 | qwen3-14b 2025-04-29config_5e352c4923f4422a53c4de0b5d9891c078afaf2e4be4e40cc11b9c4701f8c074 | 32% | Unknown | 1 |
| 177 | qwen3.5-35b-a3b_none 2026-02-24config_63212679a488a043f4fee7b2530654eb3617356a8c01fdd8c9cde11fc25c90d7 | 29% | Unknown | 1 |
| 178 | devstral-small-2512 2025-12-09config_b56f55c736f65f3304afb2f87d95c059d055242417a84131397c7458a679dbb7 | 29% | Unknown | 1 |
| 179 | nova-2.0-pro-preview_none 2025-12-02config_70dc8941324f746c0145c24b1068f8b230e46bb5686c93d18f280d9304eb819a | 28% | Unknown | 1 |
| 180 | qwen3.5-9B 2026-02-24config_1d4841f3a9d99f6af9369d0bc707e19b00ea38053b4704ade484342a4e7c46cd | 28% | Unknown | 1 |
| 181 | claude-3-5-haiku-20241022 2024-10-22config_bc1c788c15732e087bf0e04531cf315be0ee2ae8d09782928fa8c9315a69b206 | 27% | Unknown | 1 |
| 182 | mistral-small-2503 2025-03-17config_0db03531b34465e4293aec44c885da8d0059d695abff9f224df7aecfeaaf42ff | 27% | Unknown | 1 |
| 183 | mistral-small-2506 2025-06-20config_266970c38c96d0a36822d4c2a09b64dd0fba1f2a4ea6cc1e38cfe419d02a5731 | 26% | Unknown | 1 |
| 184 | Llama-3.3-70B-Instruct 2024-12-06config_f283f7089dd453a21e2b322ef1b005f773c5a0408f3a7bd775ce7e68d436e291 | 26% | Unknown | 1 |
| 185 | gpt-4.1-nano-2025-04-14config_57a526430c1497f79df3593e90e3bc790196748862930bec1584ccbf2f83239b | 26% | Unknown | 1 |
| 186 | mimo-v2-flash release-date-unknownconfig_9f11e5e35c5e8730cfa7f076094217138d2a92aa75a484e95fad117608fff632 | 26% | Unknown | 1 |
| 187 | granite-4.1-30b 2026-04-29config_4a0ceef991c9b27047dfa9da454de8ef7d3d95568a05fb381a7678eef3fb8c7b | 26% | Unknown | 1 |
| 188 | solar-pro-3 2026-01-27config_dbe246b352f24f96a11ff7f0b3c83dd81214f11bcc102ba85f161d970cc88541 | 25% | Unknown | 1 |
| 189 | qwen3-8b 2025-04-28config_b038ff236370c0673c8385cf01423d8f6b8e3204cd2fce92c2175355b68c0fa8 | 23% | Unknown | 1 |
| 190 | gemma-3-27b-it 2025-03-12config_0f46612c63e309c62273adb8953f8aacd2cfc08bdde8a59736396b32c353725b | 21% | Unknown | 1 |
| 191 | gemma-3-12b-it 2025-03-12config_82323d495f30d6abb0efbc148e7caa6ee0fce1566a4b87060e4b7818237be914 | 17% | Unknown | 1 |
| 192 | Llama-4-Scout-17B-16E-Instruct 2025-04-05config_b21d653692fee94a640375573b07132485c5da4479865700f91c67bed9cd893d | 17% | Unknown | 1 |
| 193 | Llama-3.1-8B-Instruct 2024-07-23config_ee87ed8b6981548129b73849dcd7fbcd8975d48ed86ddfa4de194159c1cc83a0 | 13% | Unknown | 1 |
| 194 | Phi-4-mini-instruct 2025-02-27config_ec2fd6c7bc33682545d26d505f4acc66129205b66e0817cb96f1a9be4d3a664c | 11% | Unknown | 1 |
| 195 | qwen3.6-35b-a3b_none 2026-04-14config_d9b262eda59c0aa5a54c6dbdc9f8f4634f1f23832a865eaab974809a4079c0b6 | 1% | Unknown | 1 |
Not enough independent evidence for a top set
- Calibration has not been validated
- Independent benchmark-family coverage is below the required threshold