Reasoning
Results are only compared within a matching group, so a model tested one way is never ranked against a model tested another way.
Solve novel multi-step reasoning tasks
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 | 1.951 | 2 |
| 2 | claude-fable-5.1 | 1.842 | 2 |
| 3 | gemini-3.1-pro-preview | 1.593 | 2 |
| 4 | gpt-5.4-pro | 1.565 | 2 |
| 5 | gpt-5.4 | 1.382 | 2 |
| 6 | claude-opus-4.7 | 1.378 | 2 |
| 7 | gemini-3-pro-preview | 1.081 | 2 |
| 8 | gpt-5.2 | 1.044 | 2 |
| 9 | gpt-5.6-sol | 0.973 | 1 |
| 10 | claude-opus-5.5 | 0.964 | 1 |
| 11 | claude-opus-5 | 0.929 | 1 |
| 12 | gpt-5-pro | 0.921 | 2 |
| 13 | gpt-6-sol | 0.887 | 1 |
| 14 | claude-fable-5 | 0.879 | 1 |
| 15 | gemini-3.8-flash | 0.849 | 1 |
| 16 | gpt-5 | 0.824 | 2 |
| 17 | gpt-5.5 | 0.808 | 1 |
| 18 | gemini-3.7-flash | 0.793 | 1 |
| 19 | gpt-5.5-pro | 0.786 | 1 |
| 20 | muse-spark | 0.782 | 1 |
| 21 | gemini-3-deep-think-preview | 0.779 | 1 |
| 22 | gpt-5.1 | 0.765 | 2 |
| 23 | claude-opus-4.5.20251101 | 0.761 | 2 |
| 24 | kimi-k2.5 | 0.758 | 2 |
| 25 | gpt-5.6-terra | 0.757 | 1 |
| 26 | claude-opus-4.6 | 0.661 | 1 |
| 27 | claude-opus-4.8 | 0.650 | 1 |
| 28 | o3 | 0.650 | 2 |
| 29 | gemini-3.5-flash | 0.644 | 1 |
| 30 | claude-opus-4.6_120k | 0.625 | 1 |
| 31 | grok-4.6 | 0.584 | 1 |
| 32 | gpt-5-mini | 0.575 | 2 |
| 33 | grok-4.20 | 0.561 | 1 |
| 34 | o4-mini | 0.545 | 2 |
| 35 | deepseek-v4-flash-0731 | 0.528 | 1 |
| 36 | deepseek-v4-pro-0813 | 0.517 | 1 |
| 37 | claude-sonnet-4.6 | 0.512 | 1 |
| 38 | kimi-k3 | 0.507 | 1 |
| 39 | gemini-3.6-flash | 0.502 | 1 |
| 40 | gpt-5.6-luna | 0.486 | 1 |
| 41 | gpt-6-luna | 0.481 | 1 |
| 42 | gemini-2.5-pro-preview-06.05 | 0.463 | 1 |
| 43 | gpt-5.2-pro | 0.447 | 1 |
| 44 | grok-4.5 | 0.423 | 1 |
| 45 | claude-sonnet-4.5.20250929 | 0.406 | 2 |
| 46 | inkling-small | 0.378 | 1 |
| 47 | claude-opus-4.5.20251101_64k | 0.369 | 1 |
| 48 | gemini-2.5-pro-exp-03.25 | 0.361 | 1 |
| 49 | inkling | 0.361 | 1 |
| 50 | gemini-3-flash-preview | 0.356 | 1 |
| 51 | kimi-k3 eqbench-creative-writing-v3:kimi-k3 | 0.333 | 1 |
| 52 | gemini-2.5-pro-preview-05.06 | 0.324 | 1 |
| 53 | claude-opus-4.5.20251101_16k | 0.307 | 1 |
| 54 | glm-5.2 | 0.303 | 1 |
| 55 | gpt-5.4-mini | 0.299 | 1 |
| 56 | gemini-2.5-flash-preview-05.20 | 0.294 | 2 |
| 57 | grok-4.0709 | 0.276 | 1 |
| 58 | claude-opus-4.5.20251101_8k | 0.273 | 1 |
| 59 | claude-sonnet-4.5.20250929_32k | 0.265 | 1 |
| 60 | gemini-2.5-flash-preview-04.17 | 0.256 | 1 |
| 61 | claude-opus-4.20250514 | 0.251 | 2 |
| 62 | gemini-3.5-flash-lite | 0.247 | 1 |
| 63 | claude-opus-4.1.20250805 | 0.241 | 1 |
| 64 | claude-opus-4.20250514_16k | 0.233 | 1 |
| 65 | claude-sonnet-4.5.20250929_8k | 0.219 | 1 |
| 66 | claude-sonnet-4.5.20250929_16k | 0.216 | 1 |
| 67 | tiny-recursion-model | 0.206 | 1 |
| 68 | claude-sonnet-4.20250514_16k | 0.199 | 1 |
| 69 | claude-sonnet-4.5.20250929_1k | 0.196 | 1 |
| 70 | gemini-3.1-flash-lite | 0.195 | 1 |
| 71 | gpt-5.4-nano | 0.192 | 1 |
| 72 | grok-4-fast | 0.186 | 1 |
| 73 | glm-4.5 | 0.181 | 1 |
| 74 | glm-5 | 0.173 | 1 |
| 75 | gemini-2.5-pro_32k | 0.170 | 1 |
| 76 | minimax-m2.5 | 0.167 | 1 |
| 77 | o1-pro | 0.167 | 1 |
| 78 | o3-pro | 0.164 | 1 |
| 79 | claude-opus-4.20250514_8k | 0.157 | 1 |
| 80 | glm-4.5-air | 0.153 | 1 |
| 81 | claude-haiku-4.5.20251001_32k | 0.148 | 1 |
| 82 | claude-sonnet-4.20250514 | 0.147 | 2 |
| 83 | gemini-2.5-pro_16k | 0.145 | 1 |
| 84 | claude-3.7-sonnet-20250219 | 0.140 | 2 |
| 85 | deepseek-v3.2 | 0.139 | 1 |
| 86 | o1 | 0.126 | 1 |
| 87 | o3-mini | 0.124 | 1 |
| 88 | gemini-2.5-pro_8k | 0.119 | 1 |
| 89 | claude-haiku-4.5.20251001_16k | 0.116 | 1 |
| 90 | gpt-5-nano | 0.110 | 1 |
| 91 | gemini-2.5-flash-preview-05.20_23k | 0.107 | 1 |
| 92 | gemini-2.5-flash-preview-05.20_1k | 0.102 | 1 |
| 93 | gemini-2.5-flash-preview-05.20_8k | 0.099 | 1 |
| 94 | claude-sonnet-4.20250514_8k | 0.096 | 1 |
| 95 | gemini-2.5-flash-preview-05.20_16k | 0.082 | 1 |
| 96 | claude-haiku-4.5.20251001_8k | 0.064 | 1 |
| 97 | gemini-2.0-flash-thinking-exp-01.21 | 0.054 | 1 |
| 98 | gemini-2.0-flash-001 | 0.051 | 1 |
| 99 | deepseek-r1 | 0.048 | 1 |
| 100 | codex-mini | 0.043 | 1 |
| 101 | llama-4-maverick-17b-128e-instruct | 0.043 | 2 |
| 102 | claude-haiku-4.5.20251001 | 0.036 | 1 |
| 103 | qwen3.235b-a22b-instruct-2507 | 0.033 | 1 |
| 104 | claude-haiku-4.5.20251001_1k | 0.031 | 1 |
| 105 | deepseek-r1.0528 | 0.028 | 1 |
| 106 | claude-3.7-sonnet-20250219_8k | 0.024 | 1 |
| 107 | gpt-4.5-preview | 0.023 | 2 |
| 108 | claude-sonnet-4.20250514_1k | 0.019 | 1 |
| 109 | gpt-4.1 | 0.010 | 2 |
| 110 | o1-mini | 0.007 | 1 |
| 111 | gemini-1.5-pro-002 | 0.005 | 2 |
| 112 | gpt-4o | 0.000 | 2 |
| 113 | amazon.nova-lite-v1:0 | 0.000 | 1 |
| 114 | amazon.nova-pro-v1:0 | 0.000 | 1 |
| 115 | claude-3.5-sonnet-20241022 | 0.000 | 1 |
| 116 | claude-3.7-sonnet-20250219_16k | 0.000 | 1 |
| 117 | claude-3.7-sonnet-20250219_1k | 0.000 | 1 |
| 118 | claude-opus-4.20250514_1k | 0.000 | 1 |
| 119 | gemini-2.5-pro-preview-06.05_1k | 0.000 | 1 |
| 120 | gpt-4.1-mini | 0.000 | 1 |
| 121 | gpt-4.1-nano | 0.000 | 1 |
| 122 | gpt-4o-mini | 0.000 | 1 |
| 123 | grok-3 | 0.000 | 1 |
| 124 | grok-3-mini | 0.000 | 1 |
| 125 | grok-4.5 eqbench-creative-writing-v3:grok-4.5 | 0.000 | 1 |
| 126 | llama-4-scout-17b-16e-instruct | 0.000 | 1 |
| 127 | magistral-medium-2506 | 0.000 | 1 |
| 128 | magistral-small-2506 | 0.000 | 1 |
| 129 | mistral-medium-2505 | 0.000 | 1 |
Model configuration · Direct prompt
Exploratory - not a ranked winner yetrg-reasoning-model-configuration-direct-prompt-model-configuration-v1Explorer evidence
ARC-AGI-2
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | gpt-6-astra_max 2026-09-03config_459ac8dc316851dc4e50c105aee8cd97974594979a58b278e5fc558abc01696a | 95% | Unknown | 1 |
| 2 | gpt-6-astra_xhigh 2026-09-03config_01fa4b20161c1bdf682ddb566827c57cdf4c6af2840694fa8d27a1ef29753976 | 93% | Unknown | 1 |
| 3 | gpt-5.6-sol_max 2026-07-09config_754c0ab021ba6f8a46654f4bb97ea19533aabab5920731757714e1b600fb019c | 93% | Unknown | 1 |
| 4 | claude-opus-5-5_xhigh 2026-09-22config_8d844d418af40e1b2e2be2417ec7c705d393f0614fd73b59315c80b28eb6f940 | 93% | Unknown | 1 |
| 5 | gpt-6-astra_high 2026-09-03config_4a61134a89c8c322be80e423e6dad2ee46a2757c726c4d035f9985eb2118797c | 92% | Unknown | 1 |
| 6 | gpt-6-astra_medium 2026-09-03config_4b222f5741b250aed06a506403d08dd0234e0cd90b24a24f9a33b8fafe0a33b9 | 92% | Unknown | 1 |
| 7 | claude-opus-5-5_max 2026-09-22config_8c9469fb0c79a91ec7f7339631f7a41a866bd351cc8cca585db3b09da43f8055 | 92% | Unknown | 1 |
| 8 | claude-opus-5_max 2026-07-24config_5bca1297b30f2dd722dfdb818565823ac3180a4c7f32117817c77367563f863b | 90% | Unknown | 1 |
| 9 | claude-fable-5-1_max 2026-09-01config_20d24ff21090d461494707eb0ed4633e918505be367c5191e52636dcc9cbf8fe | 90% | Unknown | 1 |
| 10 | gpt-5.6-sol_xhigh 2026-07-09config_a6212bf3d85efd40676193246413c07f3e96545c5f9184d0e3a6a696eee0d61a | 90% | Unknown | 1 |
| 11 | claude-fable-5-1_xhigh 2026-09-01config_ac459e99ea04d071a60495d458c8ffe2d614dd1d6415acd6193fda9b92a8f717 | 90% | Unknown | 1 |
| 12 | gpt-5.6-sol_xhigh 2026-07-09config_c5d87137affb18057458141a2201c1093e72c743adf2326fb6ff1ec20768df33 | 90% | Unknown | 1 |
| 13 | gpt-6-sol_max 2026-09-22config_a89bd445f30b3c6ba0948fca959b7de745da7aba56fa547de9f703d6f06b8339 | 90% | Unknown | 1 |
| 14 | claude-fable-5_max 2026-06-09config_39f7206b2a3f48c00ae0256dcb233300e9af283b95f49ada037fd8b88406b2da | 89% | Unknown | 1 |
| 15 | claude-fable-5-1_high 2026-09-01config_27766728e0a0bf7657bc8a5e76395ae8a6fd01b00e4c59c4981c169549102918 | 89% | Unknown | 1 |
| 16 | claude-fable-5_xhigh 2026-06-09config_cbb7a788c8497948fb5eb4bb21043cafea82e09549b4de3720e36fd183cab421 | 88% | Unknown | 1 |
| 17 | claude-opus-5_high 2026-07-24config_3fee4cb95a5b55d4119bb8a372b0881865b15e90dbdfef7f23735cdd95d29cdd | 88% | Unknown | 1 |
| 18 | claude-opus-5_max 2026-07-24config_7a2113af2b6cd5388d95fd15d6436031ea32d56a965e132423fc0302fcdbcad6 | 88% | Unknown | 1 |
| 19 | claude-fable-5_high 2026-06-09config_5ed5bcb342e8ab6ce8bc93bd0ea64a933eadc30b52e8c0b0c357a72b113bb0b9 | 88% | Unknown | 1 |
| 20 | claude-fable-5-1_medium 2026-09-01config_5354f250502ccf7d091af654f1a16a73f76f3fa88763b3680a58a4d077b346c5 | 86% | Unknown | 1 |
| 21 | gpt-5.6-sol_high 2026-07-09config_09dd4673bc766c763c65d49d602d243472ca2f09b3aaf81a1d208d39495fbcf8 | 85% | Unknown | 1 |
| 22 | gpt-6-astra_low 2026-09-03config_2730aa242fabab2a424069b63462fdbc8362e5ba5ceec28bd9cc4057422ee7ba | 85% | Unknown | 1 |
| 23 | gpt-5.5_xhigh 2026-04-23config_7afd6634ea3788f264d7437df49085a9994ce79c3a242b2a89345da618b84c93 | 85% | Unknown | 1 |
| 24 | gpt-5.5_xhigh 2026-04-23config_b830a8bef566eaa2c4015bf50a090865d199e9dab6e498f5d8a7dfee9be2e86b | 85% | Unknown | 1 |
| 25 | gemini-3.7-flash_high 2026-08-13config_33f22ae7a384cd21402e26fda58a9e657505aa8cadbbc9e8067f860321792f8e | 85% | Unknown | 1 |
| 26 | gpt-5.5-pro_high 2026-04-23config_96521c0cc7fdbf001df890da67909758dda57f9352da6868f02cf9821836d6ef | 85% | Unknown | 1 |
| 27 | gemini-3-deep-think-preview 2026-02-12config_fe8c3b03e939fb540a31049027dd4980a7a1935397371bcd49f046d359216029 | 85% | Unknown | 1 |
| 28 | gpt-5.5-pro_xhigh 2026-04-23config_5d70d7cbabb6eab6c6d7764c951fe4255bb7258098996cd903d8eaf22421f955 | 84% | Unknown | 1 |
| 29 | gpt-5.5-pro_xhigh 2026-04-23config_e8ecc274bfef3d506b4fbadd4d7a55a1d55549f4cba36c151094fcd8ace18726 | 84% | Unknown | 1 |
| 30 | gpt-5.6-terra_max 2026-07-09config_ee67687c955bc9f26fc4db66d5f2cc4b55b08ccc28ec113eed5e34df38deb85c | 84% | Unknown | 1 |
| 31 | gpt-5.4-pro-2026-03-05_xhighconfig_0fa56b7c101efcf7fe44fe017dcfa86cc7bb31480b0545411a04227831f7fd07 | 83% | Unknown | 1 |
| 32 | gpt-5.4-pro-2026-03-05_xhighconfig_9030de77d4bcf89e2649dd6094966d47c92ae92e4fe342ce92e668b6e8ae4db4 | 83% | Unknown | 1 |
| 33 | gpt-5.5_high 2026-04-23config_e5a59f69c290299c8fcec0331e4ddc88025c9d1e8c6bba4df7654586fdeb308d | 83% | Unknown | 1 |
| 34 | claude-fable-5_medium 2026-06-09config_be318768dcd05da8d6b29df2a772afdcea83e9b9dafb362d72f5230e1373328a | 83% | Unknown | 1 |
| 35 | claude-fable-5-1_low 2026-09-01config_07e6ddbc981a7e823c17bad657c9f2219f44f2df6379d6494ee68a9344398db2 | 78% | Unknown | 1 |
| 36 | gpt-6-sol_xhigh 2026-09-22config_e959c7bb557edbd4246d4dc44b76fdca6f2dc5cf3da444a05bf6ab250a89ba07 | 78% | Unknown | 1 |
| 37 | gemini-3.1-pro-preview 2026-02-19config_2a4a841c7b914b1a8a2d25ab6e9eeb8accce14e7fe19f79cb0bd5724f23e65c9 | 77% | Unknown | 1 |
| 38 | gemini-3.1-pro-preview 2026-02-19config_98f1ee35041dc71b596af09b1ff1f25a97e8f8eb9a2908995e51df6607270f6d | 77% | Unknown | 1 |
| 39 | claude-fable-5_low 2026-06-09config_4a2b695eb09237203229707a3f6d88d91cf12ed6c15269691057e09b3b2d4eed | 77% | Unknown | 1 |
| 40 | claude-opus-4-7_max 2026-04-16config_8b5ace24a05b5c6a29201f3a6df807af10dfdadfd87f90d594bff89213802ff3 | 76% | Unknown | 1 |
| 41 | claude-opus-4-7_max 2026-04-16config_9e768253f804f9aa257bb2909640d54cf74ef696e454265ac8303936197c36f9 | 76% | Unknown | 1 |
| 42 | gpt-5.6-terra_xhigh 2026-07-09config_21757d060692dcfebf04f054b43775afbf68a295fc63a60c22afeaddbbf98981 | 74% | Unknown | 1 |
| 43 | gpt-5.6-terra_xhigh 2026-07-09config_47f7f8cc3d1917dad79a3f3ccb581424903d62ddaf92ea9c6efb1ebc56b523e5 | 74% | Unknown | 1 |
| 44 | gpt-5.4-2026-03-05_xhighconfig_9ad540e2b10c3da26922fd48dbf4e330bd4e8bbae4a529f978777601e917fd7e | 74% | Unknown | 1 |
| 45 | gpt-5.4-2026-03-05_xhighconfig_e9052ab8517a74b7ae787639204a0e401e49e965d65eab90ded6b2b768af0313 | 74% | Unknown | 1 |
| 46 | claude-opus-4-8_high 2026-05-28config_2901e4a46d7c43fbf1304f3abb5dc5d7467a8538ace891805875181e7cc7d65f | 72% | Unknown | 1 |
| 47 | gemini-3.5-flash_high 2026-05-19config_390526fd99a083b7192062a0cd537e06256b47ee7d3069129f616628b7cf8bde | 72% | Unknown | 1 |
| 48 | claude-opus-4-8_medium 2026-05-28config_d344417ea43608d113dc50a3e182255034ba6958c07b75d57522add31ff56499 | 72% | Unknown | 1 |
| 49 | gpt-5.5_medium 2026-04-23config_af6b5690f3be09f0c3060a270b1749f2a1e54019ada6c5e7ce17dd889a760615 | 70% | Unknown | 1 |
| 50 | claude-opus-4-6_120K 2026-02-05config_a013a724ae41098d7580e39f8319fe8782ee22ffa4aab4b981644b90ef4a6703 | 69% | Unknown | 1 |
| 51 | gpt-6-sol_high 2026-09-22config_cede3be5deb4df7e753b7817ad55218130ad31c0896193f50159949bb6c366a7 | 69% | Unknown | 1 |
| 52 | claude-opus-4-6_120K 2026-02-05config_2c5135060ccc397a858ce204fc986700b811ea9464efca04349da5a00aea9654 | 69% | Unknown | 1 |
| 53 | claude-opus-4-7_high 2026-04-16config_576b7240f1d8e337adb628cd156ebacdce9ba28739ed25bbfb6a6ac3e4896344 | 68% | Unknown | 1 |
| 54 | claude-opus-4-7_high 2026-04-16config_d3c78a01530277f37306926bbc80d0735b46b3bf8aac1ce4fabfc474a4885821 | 68% | Unknown | 1 |
| 55 | gpt-5.4-2026-03-05_highconfig_115bb099596ca7d5aa11f0202f0c5981302591bb21f538fe41a8bcae55b3d41c | 68% | Unknown | 1 |
| 56 | claude-opus-4-7_medium 2026-04-16config_93aee180efa4479a1a8d1d64a1d0d59068071bad2b8e16ce14d062797c4e2a64 | 68% | Unknown | 1 |
| 57 | grok-4.6_xhigh 2026-08-12config_29b18ef8e9f7b37d951af9a5368d1e2b6969f58f1ab83935116074e114334da9 | 67% | Unknown | 1 |
| 58 | gpt-5.6-terra_high 2026-07-09config_169ff121b1a860195c4831f3262a2fc8051385bae12512ec3561690f6ea95334 | 67% | Unknown | 1 |
| 59 | gpt-5.6-sol_medium 2026-07-09config_26692174c93318a353e8f900a3d0718cf761a0f3b2b1cd5d16ffa8205e822395 | 67% | Unknown | 1 |
| 60 | claude-opus-4-6_120K 2026-02-05config_3c41d120cc61bca5081d35a8893583423e0b7f21b99e4fa297957377da08db91 | 66% | Unknown | 1 |
| 61 | grok-4-20 2026-02-17config_b8598946b187d4457e88f112c3f8dbaab31fc7dab6fcdd29fbe4b94b9f8cd64b | 65% | Unknown | 1 |
| 62 | grok-4.6_high 2026-08-12config_740edaa78ca55598fe4da4f3ec13156ec451e623fe87cd1c0001b17f4eb7830c | 65% | Unknown | 1 |
| 63 | claude-opus-4-6_120K 2026-02-05config_3c805069257fb7fa4e1b77aca20a5d9361eca900c7c5bc8923406647b529e403 | 65% | Unknown | 1 |
| 64 | gemini-3.7-flash_medium 2026-08-13config_f23a2989c021a0521977017290b5fc5dadc083222007c07593dff7d1b7c0c21d | 64% | Unknown | 1 |
| 65 | claude-opus-4-8_low 2026-05-28config_24717277bc617033c35888e1da1c6335395a378b37525fb5b5f2c7d998bd7a83 | 62% | Unknown | 1 |
| 66 | claude-opus-4-7_low 2026-04-16config_25456eb7ea2020bd0d8d243f3474eae341ee66a45cb758841559aa00cffde052 | 62% | Unknown | 1 |
| 67 | deepseek-v4-flash-0731_max 2026-07-31config_65747885072a9d795f2d8d1bc0e7497a43d4d5e9c6b5aff38be425192100db8a | 61% | Unknown | 1 |
| 68 | grok-4.6_medium 2026-08-12config_9fac37c35da2df6f815eb842df6451185c8264b25a3d38e375c62efae452cad6 | 61% | Unknown | 1 |
| 69 | deepseek-v4-pro-0813_max 2026-08-13config_b62b7a05e1a62d6b54026f563dceefeb675c991c86b329d264b1fe65d16c4c1f | 61% | Unknown | 1 |
| 70 | claude-sonnet-4-6_high 2026-02-17config_9ab5c6ec8596b85cf302601ed53f374db8efd607ba97e75af0029519ecac60e5 | 60% | Unknown | 1 |
| 71 | kimi-k3_max 2026-07-16config_d707a33ef8e8b94ed2cdf47b839b4e654183a727a95543e4e877618d832b2112 | 60% | Unknown | 1 |
| 72 | gemini-3.6-flash_high 2026-07-21config_db4a45c2def6fe6e591043d15ed89e65b5205501b8aae28cba7a0e5283b37977 | 60% | Unknown | 1 |
| 73 | deepseek-v4-pro-0813_high 2026-08-13config_929c2e5f1f6ebf0b3227cc7a580b2e7a8d0e7a32cf1cb1de16a37c56148c3d59 | 60% | Unknown | 1 |
| 74 | gpt-6-astra_none 2026-09-03config_0f9ba9bba4bd6d65bcf2c949b713d195713aa4635e9fe3a253804962e1ef579f | 60% | Unknown | 1 |
| 75 | gpt-5.6-luna_max 2026-07-09config_e587502fdc3b99d900e303059a9701e54e761d87c3795cff54c722c68dfa0a90 | 60% | Unknown | 1 |
| 76 | gpt-6-luna_max 2026-09-22config_094f403a72365841df9ab1f46c22fa61ac61c04909e6b2e2f0ec085342959df4 | 59% | Unknown | 1 |
| 77 | claude-sonnet-4-6_max 2026-02-17config_c433e7b9c596564e10f4113916700ea60ac13b197f2d7cc68a05a2078e7a3036 | 58% | Unknown | 1 |
| 78 | gpt-6-sol_medium 2026-09-22config_7b8e8339811e7cf29e87ab4a75379ae6b6acc970f2154f720cf53b3f76854dba | 58% | Unknown | 1 |
| 79 | deepseek-v4-pro-0813_low 2026-08-13config_7a951c994ca4cc1835d9319ed61152e73e8cb76f5b7e792f25adb0ed7cbd3b9a | 56% | Unknown | 1 |
| 80 | deepseek-v4-flash-0731_high 2026-07-31config_f7a9261779df7da9a677c86b67a9d9fbb2e3c6cce7e7972382fa2a26a50ac232 | 56% | Unknown | 1 |
| 81 | gpt-5.4-2026-03-05_mediumconfig_58ccbb8154d77e5c49d8bd895df025b1d5fba5cefefd8ec0bbc2a406d8f875cf | 55% | Unknown | 1 |
| 82 | kimi-k3_high 2026-07-16config_fb243b451243979dea9599d64ee045512cad795f0a703e57e8c87c1eb99b94a9 | 55% | Unknown | 1 |
| 83 | gpt-5.2-pro-2025-12-11_highconfig_70286df95a057e62644c7f7efa5e97bac8639178d8b86e799023ceb3738376bd | 54% | Unknown | 1 |
| 84 | gemini-3.7-flash_low 2026-08-13config_349173cc48ad97cf0b137ea9e01e45e27bee6511c30cda942165dd14e7add434 | 53% | Unknown | 1 |
| 85 | gpt-5.2-2025-12-11_xhighconfig_1cc8838aea2fd625ac3891c32d87a4dcbaac8a1248d85193220a4e61374dce4b | 53% | Unknown | 1 |
| 86 | gpt-5.2-2025-12-11_xhighconfig_3b673dcad3a76f543b9308fe815701b7011ddc7eadfe4ddc74c137f6ded883b8 | 53% | Unknown | 1 |
| 87 | gpt-5.2-2025-12-11_xhighconfig_9bd4af1c2e247f626d878134c179bdf0c8ba58516464f224b82ed263f4cde901 | 53% | Unknown | 1 |
| 88 | grok-4.5_high 2026-07-08config_6627d3698d23a77db1377ba90223df3c8b40d39fef1961f8a668172f30846503 | 53% | Unknown | 1 |
| 89 | grok-4.5_medium 2026-07-08config_aa5808b61a36fd59f4d4e7204c16d938fd5a6c8a53dc0e10a725217c7b3b56e2 | 53% | Unknown | 1 |
| 90 | gemini-3.6-flash_medium 2026-07-21config_99750ef5b5dd571ee570fac195e80a1a3a8d7fd1fb2d31bd5d71e5f071396de9 | 50% | Unknown | 1 |
| 91 | gpt-5.6-luna_xhigh 2026-07-09config_15ab9e2f092a10508d3e82acb34ef1fae3615d15f0f416e77b1232d8d89f7d23 | 48% | Unknown | 1 |
| 92 | gpt-5.6-luna_xhigh 2026-07-09config_1ae7e4d090d373a31478ac4e1034d451bb404f33f81735ebd552818e51a37b6a | 48% | Unknown | 1 |
| 93 | deepseek-v4-flash-0731_low 2026-07-31config_e1479e5d25438dfb1ca10cf178967f19d3f7b22f64aab9335111b72cc9a2673d | 46% | Unknown | 1 |
| 94 | gemini-3-deep-think-preview 2026-02-12config_55d25ad5185a0555739d8fc373edf98ede9c96137e5cc3df02b035884dc9cf49 | 45% | Unknown | 1 |
| 95 | gpt-5.2-2025-12-11_highconfig_c902fa5dfe9449b34ac52ce34345dcbf410cca4afe2a9a22905a8382ebf72025 | 43% | Unknown | 1 |
| 96 | gpt-5.6-sol_low 2026-07-09config_a144462859844e2b3836fc10c764249d8f7beacdeea07e54303302202497d4cd | 43% | Unknown | 1 |
| 97 | gpt-6-luna_xhigh 2026-09-22config_6a394e57ab1ac324e17dce833d85f7eac02411272aa396807af5c0c8fd3dd383 | 42% | Unknown | 1 |
| 98 | inkling-small_xhigh 2026-07-15config_173d36caa3ea41263da1ce48df909cee87da8ce2920290487f50960e300acac9 | 40% | Unknown | 1 |
| 99 | gpt-5.2-pro-2025-12-11_mediumconfig_222b23971acbd7d18bd370e8a7a35aeb7250868622f33309a71d48e1b380e0c0 | 38% | Unknown | 1 |
| 100 | claude-opus-4-5-20251101_64K 2025-11-24config_df1b8c7d44d387c2098bd72d816a90b819338a07b2c41ea8f0e1b0e173292c0b | 38% | Unknown | 1 |
| 101 | gpt-5.6-terra_medium 2026-07-09config_0d4e5a2402aaff31642ebd7721b23cab7eb8b1609c31e74acac46dfba223c118 | 38% | Unknown | 1 |
| 102 | Inkling 2026-07-15config_a2d04d678e4ebc1eb55c791400f25c4a099721ebc4d0bda05c4dab68d22f13cf | 37% | Unknown | 1 |
| 103 | gemini-3-flash-preview 2025-12-17config_c5cf4d3a0cc1ac0ad48a1c3059ef240e4b36661f1442687bb216a78c20a32c6b | 34% | Unknown | 1 |
| 104 | gpt-5.5_low 2026-04-23config_5ba66f8f64e7abda1eefcca714b2a4e29e6df336bbcc02a4f6eef6427dec0c17 | 33% | Unknown | 1 |
| 105 | grok-4.5_low 2026-07-08config_25ea5badbe63fca576b088b55eae5c563282b7bc22bee0c3e359a874b8307a71 | 33% | Unknown | 1 |
| 106 | inkling-small_high 2026-07-15config_86fa604e2d39ede6f49c1d2922a1e91372fbd5e3409ef6dcc8d80eca89c98223 | 33% | Unknown | 1 |
| 107 | gpt-6-sol_low 2026-09-22config_07edbaa3e394c3fb46319648c01a6548fd7329cbef16deff411a83e81966b3ac | 32% | Unknown | 1 |
| 108 | gpt-6-luna_high 2026-09-22config_572094e4a437a964e8cdd9baf543b8707332e7d40676f47168607b00c4b8c780 | 31% | Unknown | 1 |
| 109 | gemini-3-pro-preview 2025-11-18config_02b4f95f319f40dab248ced8ba29f4607359351dcda054995f1fc3c43ab57a5d | 31% | Unknown | 1 |
| 110 | gemini-3.6-flash_low 2026-07-21config_17d84a71f9462c5c0853b90d7557e0c6563cfca83f6dc0bddf0b97c76466f3d0 | 30% | Unknown | 1 |
| 111 | gpt-5.6-luna_high 2026-07-09config_6028644d4e821f0579c6cbc821b016bc174f1f7894f663314e8af46a81ff60f1 | 29% | Unknown | 1 |
| 112 | gpt-5.4-2026-03-05_lowconfig_9af476f4288b7b9ae7f2cd146e5bbc30b562e3d1130e657f885b5a72d9d36654 | 29% | Unknown | 1 |
| 113 | grok-4.6_low 2026-08-12config_abfa7afa2b24605e220da4c04163a9159ff9d55db5a093c00026959a676ee884 | 28% | Unknown | 1 |
| 114 | gpt-5.2-2025-12-11_mediumconfig_74284bd9f08284b0b766cb218d6609ef15fe359b04871c0f5fb7c57289a01007 | 27% | Unknown | 1 |
| 115 | claude-opus-4-5-20251101_16K 2025-11-24config_6bbce85f5b3fd99c6ac3b40d5bf254dc0605a7607b2184830740eaee79dc6155 | 23% | Unknown | 1 |
| 116 | glm-5.2_unknown 2026-06-16config_ff23a2838211ff13843b33b3bbd03488292be316658a70da82938693b6d2a9bd | 23% | Unknown | 1 |
| 117 | gpt-5.4-mini-2026-03-17_xhighconfig_624731a68cc6f43197ebf1496da288dae8aae258acfd43b0a6a7f0a9ce50ae30 | 19% | Unknown | 1 |
| 118 | gpt-5.4-mini-2026-03-17_xhighconfig_7d3ae160db3d1d396f01251dd2e453bfe06631afdf6722b8ebfdc6b03845f59d | 19% | Unknown | 1 |
| 119 | gpt-5.6-terra_low 2026-07-09config_1ca335de2c353f962770d692fbdbde405136c4651fc7ffb237e919fdf5e16f74 | 19% | Unknown | 1 |
| 120 | gpt-5-pro-2025-10-06_unknown 2025-10-07config_498862ea9473f95b4002c6d02787c62f66cb2cfa78dcfe3920afbfbcd2c2c0db | 18% | Unknown | 1 |
| 121 | gpt-6-luna_medium 2026-09-22config_287bd865fe379818fbb256e3a010d2e31fde1366ec4f27f72824561ef4c85ef9 | 18% | Unknown | 1 |
| 122 | gpt-5.1-2025-11-13_highconfig_56e6155f909f76dbf0113a300a2987807995332ca3cc9485d4c741dae3fe649b | 18% | Unknown | 1 |
| 123 | grok-4-0709 2025-07-09config_bff840fc356c7c3470b6318f52c90859b4692cfc124e6aa8665f1a8279252fe6 | 16% | Unknown | 1 |
| 124 | claude-opus-4-5-20251101_8K 2025-11-24config_a5f55c1ae90c6f1e9d98f88254ae875208125850c3ca6dc8494527cb4cc16f7c | 14% | Unknown | 1 |
| 125 | inkling-small_medium 2026-07-15config_a9733e101ee5d6ec5cac420d76b14e986ac94801ebc089cf5be24ec92c3f6346 | 14% | Unknown | 1 |
| 126 | claude-sonnet-4-5-20250929_32K 2025-09-29config_53daa4f20a8637cacbe2092213c824730106d0610a2aae8ebc4eb9dfbe8cdf4e | 14% | Unknown | 1 |
| 127 | gpt-5.4-mini-2026-03-17_highconfig_3c50f9a5d27bd8f0b2ef96c6ae8747c533fcf232aba7fe339589e6e47334f408 | 13% | Unknown | 1 |
| 128 | gemini-3-flash-preview 2025-12-17config_4dcc90ef06dba7c7866525cc6df1528d4fa2f36c69397a64374032f07e9b4d65 | 13% | Unknown | 1 |
| 129 | kimi-k3_low 2026-07-16config_6958f9c23200d1d6d10fbac93b3c78d531c6ec598604eb85f1ec2d293445ff01 | 12% | Unknown | 1 |
| 130 | kimi-k2.5 2026-01-27config_bde253257a79ed79bc1615543f3e0d2dc6ead302f2f0b16ad54fd2d160c9ffce | 12% | Unknown | 1 |
| 131 | gemini-3.5-flash-lite_high 2026-07-21config_901ad1303c9c31f60eaad7432884576f257ac868caa98cebb17b19ffe6a098a3 | 10% | Unknown | 1 |
| 132 | gpt-5-2025-08-07_highconfig_2e3e5b6612e479d838606a6dd6ae863c5557bc73ab47fc8928357b9b11ffe031 | 10% | Unknown | 1 |
| 133 | gpt-5.2-2025-12-11_lowconfig_ed33ae702b784bf1c563d128a99bccdc840482ffd40dab893e3db384bc1917b6 | 10% | Unknown | 1 |
| 134 | gemini-3.5-flash_minimal 2026-05-19config_3aa8a5558bcc47163dfb63fb4e5504d7958d25dafe4638bebc8961613a97e26c | 9% | Unknown | 1 |
| 135 | claude-opus-4-20250514_16K 2025-05-22config_8ec5f1c2a1be3bec1a36b956a31495e0a38aac720e6c0b9f24a3d0ca7494662b | 9% | Unknown | 1 |
| 136 | claude-opus-4-5-20251101 2025-11-24config_d15abd72cc925522d52e1a39aaed2359cf359d89a08c5b44a6b63c2fe2bb2593 | 8% | Unknown | 1 |
| 137 | gpt-5-2025-08-07_mediumconfig_dd301de319f6e39caa709e27e518b4fcaa82f9a36e022e94c6e8d8a1adba7a98 | 7% | Unknown | 1 |
| 138 | gpt-5.6-luna_medium 2026-07-09config_23b1b1ada3c318e22831143fced18c5f9115955751b3090d82103681b08b8862 | 7% | Unknown | 1 |
| 139 | claude-sonnet-4-5-20250929_8K 2025-09-29config_17f6f66c115d4b83681c4040610d9954d9c6b8818923f4d3b0fc117a633fe18d | 7% | Unknown | 1 |
| 140 | claude-sonnet-4-5-20250929_16K 2025-09-29config_24cbf77041af70a66a70128985bbd7c98266bbcb7630e894f57f1767e56847f1 | 7% | Unknown | 1 |
| 141 | gpt-5.1-2025-11-13_mediumconfig_19afb259ef5f60fbb4adab23aecda63fa83de6adedca537459880663e914d14f | 7% | Unknown | 1 |
| 142 | o3-2025-04-16_highconfig_c2d6cfbd0a94956851698b38478bfc9eb4425f89214116fdf43c3fd7863af722 | 7% | Unknown | 1 |
| 143 | tiny-recursion-model 2025-10-06config_496259b66893124294abf85711cb542685ac4954c42a14fda67e728d01001ce9 | 6% | Unknown | 1 |
| 144 | o4-mini-2025-04-16_highconfig_c0ec93b5c64f4c950a3f4b608590da18fb7b6610f2bf050b83eb8524dd4be0f7 | 6% | Unknown | 1 |
| 145 | claude-sonnet-4-20250514_16K 2025-05-22config_c07f33143bff33af6280ef9bfe66cd9a188bee941b12af0fe346d2c5963dae19 | 6% | Unknown | 1 |
| 146 | claude-sonnet-4-5-20250929_1K 2025-09-29config_dde2d040a590fe588244d1a4a1887fa6f3fe6df860ed5bee501cbc98c006b810 | 6% | Unknown | 1 |
| 147 | gpt-5.4-nano-2026-03-17_xhighconfig_74f74f43071a4d6ffc92d8e12bf1ba4d9a5927068a5537160205b71b958015b5 | 6% | Unknown | 1 |
| 148 | gpt-5.4-nano-2026-03-17_xhighconfig_edb42e08dcf1226f01383a6338985b84d6b372fdb65f9606aba0d1dd16d2851a | 6% | Unknown | 1 |
| 149 | grok-4-fast 2025-09-19config_518b0cfe940bba68d4369ae13ed7baeec4104ba3914ce3ab7353a712bc19fb35 | 5% | Unknown | 1 |
| 150 | gemini-3.5-flash-lite_medium 2026-07-21config_496bd9cd1b2fd54fcfa216e45b607f0244a55628a4aa92a08340a34c1edbb99c | 5% | Unknown | 1 |
| 151 | gpt-5.6-luna_low 2026-07-09config_e6ac58dadc7a9a4b0e1e46d1b8971b6a6d9281bfda7e67ff0bd38f457794daeb | 5% | Unknown | 1 |
| 152 | inkling-small_low 2026-07-15config_5fef7e5cf1274a1db8f73f6f3fbdcc38950ed1895b64413e3f0191f92a3b570c | 5% | Unknown | 1 |
| 153 | glm-5 2026-02-11config_17adf8e138bc6b475c6b315200a9260ddf510879ee4724f852ada5053c73ab0a | 5% | Unknown | 1 |
| 154 | gemini-2.5-pro_32K 2025-06-17config_817294017ccabd93e3c06154072b902c8252ed4655c13f2c0975f5bd68fe32a4 | 5% | Unknown | 1 |
| 155 | MiniMax-M2.5 2026-02-12config_f00ae7bcba118364b90fc9b9a0df5dd273ef0c8290628fe699f215bbb6eeefe9 | 5% | Unknown | 1 |
| 156 | o3-pro-2025-06-10_highconfig_f44f52e8fd573c795447b5df494a4bf5a5e41b22b612b68e667437718a46f37d | 5% | Unknown | 1 |
| 157 | gpt-6-luna_low 2026-09-22config_dd54c70b7aee8c8d54cd45377c8d963079eb38f90cdcbde58dd49822cf42a86c | 5% | Unknown | 1 |
| 158 | claude-opus-4-20250514_8K 2025-05-22config_59c0a6dedc17ef8da155763e34cea17b11bb5da2aa7416fb32990b0177ae7b08 | 5% | Unknown | 1 |
| 159 | gpt-5-mini-2025-08-07_highconfig_4fbd1737c6a3b53bc29f96420781b4d91365b1307fa687dfb52b7b124a15dead | 4% | Unknown | 1 |
| 160 | gpt-5.4-mini-2026-03-17_mediumconfig_54644e87a30fa13abeadb8763c27c8c0bdcf9f183a489a87b6024f4a0ec91de5 | 4% | Unknown | 1 |
| 161 | claude-haiku-4-5-20251001_32K 2025-10-15config_0f3f2b1a0d60e8b6a27b16cfce8bbd42f6d576f350943efda7a52276f8a4c46a | 4% | Unknown | 1 |
| 162 | gemini-2.5-pro_16K 2025-06-17config_567903eee4b5954fe37316a7af1f0dbe8013f57f5f398cb08c9ecd4dc8678fc1 | 4% | Unknown | 1 |
| 163 | gpt-5-mini-2025-08-07_mediumconfig_7904c047631fd36e887ceeb2f7e44b1058892e9d2ae63cb328e88d802758f8bf | 4% | Unknown | 1 |
| 164 | deepseek/deepseek-v3.2 2025-12-01config_c516999fd8d25aee770ae07ae8709af8f34ac7baf73cd39413d5a84d65c059fd | 4% | Unknown | 1 |
| 165 | inkling-small_minimal 2026-07-15config_9c591e27477571ae46d44dfd5a325db3ac97b41c1008029c410312e211652be6 | 4% | Unknown | 1 |
| 166 | claude-sonnet-4-5-20250929 2025-09-29config_776fffa5b50b5dd93bba35760ca6ac22eab41e66ad5f82d92af73a04af1ecb21 | 4% | Unknown | 1 |
| 167 | gpt-5.4-nano-2026-03-17_highconfig_231347245ef952db7ee1e5db6595a3692b1138bdb0c92b74492fa9a90a2b51e9 | 4% | Unknown | 1 |
| 168 | gemini-3-flash-preview 2025-12-17config_6003ac5bf92b96020fbf11933db065a5848da8a7e51e47da6f4f05b619a7385e | 3% | Unknown | 1 |
| 169 | o3-mini-2025-01-31_highconfig_e4182d3bb24702133a1774ec25e0d6ad50fbd9c93dca7fb0b4fb936ac783c669 | 3% | Unknown | 1 |
| 170 | o3-2025-04-16_mediumconfig_2e69abe4ea1cb466d658cdf09c49cb532d2acb5fcc5c3458a90e55d523b3f93f | 3% | Unknown | 1 |
| 171 | gemini-2.5-pro_8K 2025-06-17config_ff6b1ebc99664f6628661d5ff5763e1eb379a36d8b36ad671186efa4aa32a845 | 3% | Unknown | 1 |
| 172 | claude-haiku-4-5-20251001_16K 2025-10-15config_bac57ca63ea1280337b6aadfc0abb34e402328bd5442c3880be38940c4718444 | 3% | Unknown | 1 |
| 173 | gemini-3.6-flash_minimal 2026-07-21config_60e8189b6a9766ea0ed6d50db9bd88f25da0c93ad33312e80de5530aab01b76d | 3% | Unknown | 1 |
| 174 | gpt-5-nano-2025-08-07_highconfig_e474cabd7951a6dac7c51123316397c395956931aa18a7b921cbdbd70664e5df | 3% | Unknown | 1 |
| 175 | gemini-2.5-flash-preview-05-20_23K 2025-05-20config_70b15d89585c0474ed609606731f628680cc5e92125dc6211f8ee0e15d75da31 | 3% | Unknown | 1 |
| 176 | o4-mini-2025-04-16_mediumconfig_12be17b71685704960c85bf890b38bb80c82fc559d8a65371cabe344713eb44a | 2% | Unknown | 1 |
| 177 | gemini-2.5-flash-preview-05-20_1K 2025-05-20config_b88c9014976266b4f212f69ee24fc8135b020c4dc467645247f7a49a4b50d7d3 | 2% | Unknown | 1 |
| 178 | gemini-2.5-flash-preview-05-20_8K 2025-05-20config_78175c7382e52d352f5969442a8a2e2d3ffc74f254418bd3581a9a8430b1dc58 | 2% | Unknown | 1 |
| 179 | claude-sonnet-4-20250514_8K 2025-05-22config_d9406ffb2172cae3918fee69406912f50dd5e165d17bfde63f3e440fe6ef5f43 | 2% | Unknown | 1 |
| 180 | deepseek-v4-flash-0731_none 2026-07-31config_79255a0c2c4909dc505f7c6ece0ebea2cf2794eb1cf644705d3ecca941fda713 | 2% | Unknown | 1 |
| 181 | o3-mini-2025-01-31_mediumconfig_9a56af7045290adb5d93b22d180332b8a018c1f49e1ccaa838952245b6f04b14 | 2% | Unknown | 1 |
| 182 | o3-pro-2025-06-10_lowconfig_921267b4a6c1fd211fa55d009d4d1f80e18c0a43ac279977bda241dfd3bdb4f2 | 2% | Unknown | 1 |
| 183 | o3-2025-04-16_lowconfig_a7347f7586623824fcfbee550645ebbf3bd718cd3895277ed1f4258983d15ea9 | 2% | Unknown | 1 |
| 184 | gemini-2.5-flash-preview-05-20_16K 2025-05-20config_e944bb314bc85cf16d89362299fe4cb2cce537258def8b75d359a51bf6b15856 | 2% | Unknown | 1 |
| 185 | gpt-5-2025-08-07_lowconfig_49cd7b6dd29f4a951f7f002d380544c00e3967c0a7b04fefffc82296ee8660c8 | 2% | Unknown | 1 |
| 186 | gpt-5.4-nano-2026-03-17_mediumconfig_8cd4fae039455267739b311627202f690fa7f3b190f198f9d387b2006d60a85c | 2% | Unknown | 1 |
| 187 | o3-pro-2025-06-10_mediumconfig_9c2091fbee4388af6494949c14989b24d0f566ec529584c75fed9c307c08839c | 2% | Unknown | 1 |
| 188 | gpt-5.1-2025-11-13_lowconfig_f94010985602bf346a3cacdcd1932323dc66025544c4d829ee48f0165e0671ca | 2% | Unknown | 1 |
| 189 | gemini-2.5-flash-preview-05-20 2025-05-20config_493a9334b881fd3024e2c897adfdc6c243cc4b0efc9b121d6e3ff025d0f8cebc | 2% | Unknown | 1 |
| 190 | o4-mini-2025-04-16_lowconfig_8c5404b58c740ce12def212c866d68f2127623ae64c42474afbeb14288533b4c | 2% | Unknown | 1 |
| 191 | claude-haiku-4-5-20251001_8K 2025-10-15config_b9f1e3d8df86d9008514b59dd514f75f309f951ec8dd7916cebdb3a7f28f2aea | 2% | Unknown | 1 |
| 192 | gpt-5-mini-2025-08-07_minimalconfig_cc84af6b73a0a45c1189899de85f922f7b518dbca128d9c71c992b190447152e | 2% | Unknown | 1 |
| 193 | gpt-6-sol_none 2026-09-22config_da4f7be3b8c02c4fdcb259211d2a3a452a0ebd84fec1882e1cab32f82dcea398 | 2% | Unknown | 1 |
| 194 | gpt-5.4-nano-2026-03-17_lowconfig_ca55e8624b335037a149f053d4a93546c554b08aa6775a0277f844cd6caaf1af | 2% | Unknown | 1 |
| 195 | gemini-3.5-flash-lite_low 2026-07-21config_b42c41f4f380410f5bf637ebf4cbb85e1430c2ba814f0095db5d75a25565e6f2 | 2% | Unknown | 1 |
| 196 | gemini-2.0-flash-001 2025-02-05config_94887e48cb18c726410b03af6dabf97b5f29cef52aeb2993f154c745e1d04a30 | 1% | Unknown | 1 |
| 197 | DeepSeek-R1 2025-01-20config_d74cd9a37607d3ac1200bed74fc5dc886bdbd22d1d6161e3afdd333612e49fa8 | 1% | Unknown | 1 |
| 198 | claude-sonnet-4-20250514 2025-05-22config_04179b1d64747c655e6913aee2fd00fe92961594ccf0dc6bc0c8771f7d26a1f7 | 1% | Unknown | 1 |
| 199 | codex-mini-2025-05-16config_0b25bf009e9ea322fbbb8e5923e6b6d797df6618bcb6548626bc7e004d8a6971 | 1% | Unknown | 1 |
| 200 | claude-opus-4-20250514 2025-05-22config_f9f88cc15855c3fb44c39a1529bdcacd2c3149ec887dd91df20c2281b964558b | 1% | Unknown | 1 |
| 201 | gemini-3-flash-preview 2025-12-17config_7396e5a13b4db3c462349d7c290d5b8e5a5e4f02a49e3ef6640fd06122233df0 | 1% | Unknown | 1 |
| 202 | claude-haiku-4-5-20251001 2025-10-15config_b3e281e03790711e2a573c7bddd7973a1e6f9d1222ec65404f979d799e17dacf | 1% | Unknown | 1 |
| 203 | Qwen3-235B-A22B-Instruct-2507 2025-07-25config_ce972cd5f15d902cd5f765094e4a62564a2b8af2d6bbcf80da2d8353372a964b | 1% | Unknown | 1 |
| 204 | claude-haiku-4-5-20251001_1K 2025-10-15config_d59222481dc96c1c6d66adf50715fab3a4b8cd4ca888dbf3c08b60ddfafff258 | 1% | Unknown | 1 |
| 205 | DeepSeek-R1-0528 2025-05-28config_ccbd70abd02ea5883edd80a9a07b91ffe61a47034632fb7e7a5720c334e5dff5 | 1% | Unknown | 1 |
| 206 | gpt-5.4-mini-2026-03-17_lowconfig_ccea703bab3b79e6076986f186b999cad42b6c15484a02cfe871eb9f9648d049 | 1% | Unknown | 1 |
| 207 | claude-3-7-sonnet-20250219_8K 2025-02-24config_42142cdb60104f88181a29130275c3ef9c87efc2885217fa59cc8a37287fc604 | 1% | Unknown | 1 |
| 208 | gpt-5-nano-2025-08-07_mediumconfig_cc4e13214953afec486b85a688ac7564b70f1efc3f7d4a0b1a944665a4286377 | 1% | Unknown | 1 |
| 209 | claude-sonnet-4-20250514_1K 2025-05-22config_6e07e672da56adce977550970c840a2a479cf0c00844cf0f4a9c1c09e376e685 | 1% | Unknown | 1 |
| 210 | gemini-3.5-flash-lite_minimal 2026-07-21config_67baccb6dbe8b9280a7ad42a586e244de688e83cd18753a792b973def8b37fdb | 1% | Unknown | 1 |
| 211 | deepseek-v4-pro-0813_none 2026-08-13config_9fe26210de3e7cf88113d4e923303c1d379e22bbf161c2b30a7df410eb72a7d2 | 1% | Unknown | 1 |
| 212 | gpt-5-mini-2025-08-07_lowconfig_2f9f2b48caa9aa3852aa338752d51bb9605e1b694fb8a11354d1832423cd7fc0 | 1% | Unknown | 1 |
| 213 | gpt-5.2-2025-12-11_unknownconfig_5d063395d20addb02fbb14a3c4c41b6148635f98ba1ca357e17e41e88136809c | 1% | Unknown | 1 |
| 214 | o1-mini-2024-09-12_unknownconfig_ec0ef473ebf9577f04ecad7b964706d6bcc275c8a49d93aec89bd31c756db34f | 1% | Unknown | 1 |
| 215 | gemini-1.5-pro-002 2024-09-24config_7fb265845a6ce2c4071d5231dcc2877d7484be687d08eeeb2b3c13ab639c50f9 | 1% | Unknown | 1 |
| 216 | gpt-4.5-preview-2025-02-27config_9c42b055dd14466abd0c399717449ba41a8ee0e9935c836493b2ba2afa847e8d | 1% | Unknown | 1 |
| 217 | claude-3-7-sonnet-20250219_16K 2025-02-24config_2b29a9b2fb95eac499bd7bbf264713c9d2fc2118d278680b3bddbc9a8ab52071 | 1% | Unknown | 1 |
| 218 | grok-3-mini_low 2025-06-24config_2ac0b32e8bdda73f7677785d26be48322bd6eec38f7f782a333bd70ba0123d4d | 0% | Unknown | 1 |
| 219 | gpt-4.1-2025-04-14config_a67b333bc674bfeeac2ad9cdff758ec774b29ebecc747428d1181b8eff72b440 | 0% | Unknown | 1 |
| 220 | gpt-5.1-2025-11-13_noneconfig_e382a346f3d090b234f74a252bdb6e14d4f283b2611a811d1fe96bc85aa8f50d | 0% | Unknown | 1 |
| 221 | claude-3-7-sonnet-20250219_1K 2025-02-24config_ce8c75462547a619952dbada44ac812f8c5287163eeab6832cce2cdee6411522 | 0% | Unknown | 1 |
| 222 | gpt-5-nano-2025-08-07_minimalconfig_0b2a7b2e3e124567362865e78ce2c876f0f8076b2981f6cf39974b05b54af318 | 0% | Unknown | 1 |
| 223 | gpt-5-2025-08-07_minimalconfig_222260cf5ddf76d57f8d08955cbdfa2e59ca88089dbb893571f2c43afb99cd27 | 0% | Unknown | 1 |
| 224 | gpt-5-nano-2025-08-07_lowconfig_30dd69b9382d205fd3dd389ab9c661c4a7a4f4ce044560db0ba39190ac431cf8 | 0% | Unknown | 1 |
| 225 | magistral-small-2506 2025-06-10config_3a61469ee0a54275a91f3f9153201a3f7bfec4b7ea7d9e918b6d7837579d24bf | 0% | Unknown | 1 |
| 226 | grok-3 2025-04-09config_4b42adcf3b8bebc79f3b3d10b2dfceb36d90919772412456858ff594a936b9b2 | 0% | Unknown | 1 |
| 227 | gpt-4o-2024-11-20config_6a0af78239c86eb0dc079ff427a9971ae6b89e97e2b0b14c71fc9433f21e599b | 0% | Unknown | 1 |
| 228 | o3-mini-2025-01-31_lowconfig_8e392b0161c315b6647a16f63f647ec489650a6ab3fc7913837a2edc1c8ac14c | 0% | Unknown | 1 |
| 229 | gpt-4.1-nano-2025-04-14config_90373e62bf352e88e6921f48ea8575ae536b8511c43c400c5adde5f03540acd7 | 0% | Unknown | 1 |
| 230 | gpt-6-luna_none 2026-09-22config_9bbb067aca89d4c3a1c0adc1f163031a21bcb4e23c9e1f42e47124654de0d0ff | 0% | Unknown | 1 |
| 231 | gemini-2.5-pro-preview-06-05_1K 2025-06-05config_aa98e620fa2f433a8a72674259a48b6273e58ce86aa6ee15eab1e2223ca3b010 | 0% | Unknown | 1 |
| 232 | Llama-4-Scout-17B-16E-Instruct 2025-04-05config_b21d653692fee94a640375573b07132485c5da4479865700f91c67bed9cd893d | 0% | Unknown | 1 |
| 233 | magistral-medium-2506 2025-06-10config_ba3f5ecfdcc32937d296f19dfe6ea9d0a3e82c6f4278272e0aafbb50c67574ea | 0% | Unknown | 1 |
| 234 | gpt-4o-mini-2024-07-18config_bd5c1aae7478cf497ae867a3bbdd9467bb8d9b1bc4f8d920fcab87e842a371e7 | 0% | Unknown | 1 |
| 235 | gpt-4.1-mini-2025-04-14config_c02e16ffc4d3bafffc1c036c0d61130dbf3e7946dbc87397b1d4616c8ce294d0 | 0% | Unknown | 1 |
| 236 | Llama-4-Maverick-17B-128E-Instruct 2025-04-05config_c85f902ef6cfd9a335fe0671f53a15c142fe7c28bfec02ab65d89f27dc1174e1 | 0% | Unknown | 1 |
| 237 | inkling-small_none 2026-07-15config_d5e27515499b1bd4209e30a7d9e0494a9c93f1939ac2ed62e0d93edf7a71acb4 | 0% | Unknown | 1 |
| 238 | claude-3-7-sonnet-20250219 2025-02-24config_e127eb3ecc2fb6196eea2e2d180e62211f2681bdb884219bf850b17e17b920cd | 0% | Unknown | 1 |
| 239 | claude-opus-4-20250514_1K 2025-05-22config_fcad5192d98de10084bffb45101e775f983a62af6d2db526289c30ffc37927f4 | 0% | Unknown | 1 |
| 240 | magistral-medium-2506 2025-06-10config_fe4a0f120ad12dc298baaeb937d87859915ade87275a835efee2a915c7403713 | 0% | Unknown | 1 |
Explorer evidence
Humanity's Last Exam
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | gpt-6-astra_unknown 2026-09-03config_25d6b325a941c5563b85c85173810b4fbc64817a6e1f08a3d7df5096ce655bc9 | 55% | Unknown | 1 |
| 2 | claude-fable-5-1_xhigh 2026-09-01config_f5f9bb4a158ecf32746eeb0a2871fcea455caebe04246ed1fa6e57fd5080d473 | 47% | Unknown | 1 |
| 3 | gemini-3.1-pro-preview 2026-02-19config_0a37726b43687109cc527d15526831b9210efc8c07cc9fcd4794dcdf673be19d | 46% | Unknown | 1 |
| 4 | gemini-3.8-flash_unknown 2026-09-02config_d77e4f67317bfea831bec1e5698dcbba759262c5dd1c225db89a6faeaf1327a5 | 45% | Unknown | 1 |
| 5 | gpt-5.4-pro-2026-03-05_unknownconfig_9eac1ca2ecc92af1861102e33adc3a3154c167fe2c635e024f46c5b7b96a42a8 | 44% | Unknown | 1 |
| 6 | muse-spark 2026-04-08config_d44b10f0e691c37e7c14b057261d6a0b88129cab973e5a6904128f219f34f30e | 41% | Unknown | 1 |
| 7 | gemini-3-pro-preview 2025-11-18config_39f5b0c0834e4eb701f5a68628426d42a419e026b082bf7115bc50f3e3d907b8 | 38% | Unknown | 1 |
| 8 | gpt-5.4-2026-03-05_xhighconfig_660fe730ff9f38f55eaadd5bbe09f26f010a5fe899800cd59640a605d4bfa47e | 36% | Unknown | 1 |
| 9 | claude-opus-4-7_unknown 2026-04-16config_48524c626d16f9676715d46d44b69126944826ff627123003a7fea5d3b00cf89 | 36% | Unknown | 1 |
| 10 | claude-opus-4-6_max 2026-02-05config_6973925ebcea60fa11b2f037b4359f8c4603e5f3037959da3c4d03c43f425966 | 34% | Unknown | 1 |
| 11 | gpt-5-pro-2025-10-06_unknown 2025-10-07config_59055441940a6bea9d63174a4af091e3c303a2ad55b1452719370a832bf7ba3f | 32% | Unknown | 1 |
| 12 | gpt-5.2-2025-12-11_unknownconfig_d304de2673e41c09968a2334bfa1af5655fbac2907a522ab042f259df382d90a | 28% | Unknown | 1 |
| 13 | gpt-5-2025-08-07_highconfig_69ecec6dacb41cc4f9c595637f81a8d34783313db732f1f343accdc4a69fe58e | 25% | Unknown | 1 |
| 14 | gpt-5-2025-08-07_unknownconfig_cf7756eb36f169fe7b7f9ca49a79060216346709cd86c0d0fb293e5a9e257ed1 | 25% | Unknown | 1 |
| 15 | claude-opus-4-5-20251101_unknown 2025-11-24config_fdb3a5ead63c23f6b3ac926f22faf563617a28316903e0191bf28cbac821cb35 | 25% | Unknown | 1 |
| 16 | kimi-k2.5 2026-01-27config_005459d229eaa2c83bc541c2ce7e8ac815663cce448d4b905c846bffbc058d1a | 24% | Unknown | 1 |
| 17 | gpt-5.1-2025-11-13_unknownconfig_ab9c4f0fb10d5121fa55d0ca8aeb0dc7fa558aca12bfa1fe068bf59eb2592ddd | 24% | Unknown | 1 |
| 18 | gemini-2.5-pro-preview-06-05 2025-06-05config_520cb904234e435ed0d291db57c61343bbd9cd47b40a1cc6fbc9ab3cde2b19c3 | 22% | Unknown | 1 |
| 19 | o3-2025-04-16_highconfig_93e08c55882a962e28ab63ad269e729f3e294bd223dbc9b3bc26b74898baef75 | 20% | Unknown | 1 |
| 20 | gpt-5-mini-2025-08-07_unknownconfig_0873d593916fa6075904e237e0ca63995a6572e45ebdf6d3f89ee7ebcd6a9e27 | 19% | Unknown | 1 |
| 21 | o3-2025-04-16_mediumconfig_e383580877c10a76467bad15a4578fc2e2f463ad9b54ad8d3d2c698bce63fe8d | 19% | Unknown | 1 |
| 22 | claude-opus-4-6 2026-02-05config_d53d33bc2c05b5b373c9434c391f6ceb0afdb4204aebb579f37fb30e59574bf3 | 19% | Unknown | 1 |
| 23 | gemini-2.5-pro-exp-03-25 2025-03-25config_10a145fe7bf681ee6f54275e9f053cc8fbeda5757ccfee7c66d867863d8cbcbf | 18% | Unknown | 1 |
| 24 | o4-mini-2025-04-16_highconfig_dbd9d87bb365dab644590f8e33640376ba43512e4c52b2bf4024be74f8fb61af | 18% | Unknown | 1 |
| 25 | gemini-2.5-pro-preview-05-06 2025-05-06config_b0c2701b97c3c2f6c3f1dd40292e19e97fc1597aeae2313e85cb5c68ade98c5f | 18% | Unknown | 1 |
| 26 | o4-mini-2025-04-16_mediumconfig_f99ef8ea288a6cde886ccd45cd6989c4b0fb4f1b61c929903f71535e10832b05 | 14% | Unknown | 1 |
| 27 | claude-opus-4-5-20251101_unknown 2025-11-24config_49bf5d7860fdda190d62820d07cbba06e0c870254e8e91ad2526a74ca8d47d03 | 14% | Unknown | 1 |
| 28 | claude-sonnet-4-5-20250929_unknown 2025-09-29config_096bfafd4d12e8a3a13f4573307d1e76076e2de7b33dfafd6d8a1a6a2566c6d2 | 14% | Unknown | 1 |
| 29 | gemini-2.5-flash-preview-04-17 2025-04-17config_9d2efb708965c9c3c0fbc19a6db6375eac0b5a0e40afaceb182bf8cce9e1703f | 12% | Unknown | 1 |
| 30 | claude-opus-4-1-20250805_unknown 2025-08-05config_7e3cbe876975ab6a32afe3ceb60e7ef90a318b7452c5909652230b8a23d0a311 | 12% | Unknown | 1 |
| 31 | gemini-2.5-flash-preview-05-20 2025-05-20config_bbbc2b70cea1dbc9c8a4d681bb4d0f359191437401c99b5166129e6a85040562 | 11% | Unknown | 1 |
| 32 | claude-opus-4-20250514_unknown 2025-05-22config_65bc4378cbe1be090c451ec383a83cab2270270489e704bded064e8126a0a42b | 11% | Unknown | 1 |
| 33 | gemini-3.1-flash-lite 2026-03-03config_ffb3b8f054e094aaa4f2801bc7ecd1e11f97fb8a4cdc42090b617125bf40e34a | 9% | Unknown | 1 |
| 34 | glm-4.5 2025-08-03config_f2aa2e4a3dd92a504bf35a92a3028939fc89530567c0c624e4ff10693ddb2b9e | 8% | Unknown | 1 |
| 35 | o1-pro-2025-03-19config_9a17cfba04138c9382259270c442a16c728e1cf665f0d7f2195a6ea0e2bffa2e | 8% | Unknown | 1 |
| 36 | GLM-4.5-Air 2025-07-20config_c11079f6736b79cb813ce772789434f3095c0cfd3891036e34f185f3c6331b3f | 8% | Unknown | 1 |
| 37 | claude-3-7-sonnet-20250219_unknown 2025-02-24config_555c39c3172d3c7355c3b2d5ed97ae6ce93dcf7fe2c60de215a6266937ad18d5 | 8% | Unknown | 1 |
| 38 | o1-2024-12-17_unknownconfig_d457f10e94f0bbc5302b2dc756f9c3a3b6c5ecf26fbb8833775cbeaa171e5e6c | 8% | Unknown | 1 |
| 39 | claude-opus-4-1-20250805_unknown 2025-08-05config_534b97a421f480535aabf998cf9b61e0561e4144239115a271a759ba557ac425 | 8% | Unknown | 1 |
| 40 | claude-sonnet-4-20250514_unknown 2025-05-22config_3afb5081c41abb96aab5a2e55021857c819047dbe5d7da39dad8cd59ff5f63a6 | 8% | Unknown | 1 |
| 41 | claude-sonnet-4-5-20250929_unknown 2025-09-29config_122a7fb34b784dea798bb0c1475d7c20c53b156499ae3856f83533b65e27a1a9 | 8% | Unknown | 1 |
| 42 | gpt-5.1-2025-11-13_noneconfig_c799e3f9239d5edb2eedcde98bfc6420dba466b32ef931a09835053db036629e | 7% | Unknown | 1 |
| 43 | claude-opus-4-20250514_unknown 2025-05-22config_ac589ae25a74f51f26a1547ce5feff400675777b07a00d3cffa77e6d5b03604a | 7% | Unknown | 1 |
| 44 | gemini-2.0-flash-thinking-exp-01-21 2025-01-21config_38984fb90dcd226bb057e2f69279fd70306f0ff67aeb8f0377d0f0f75197759f | 7% | Unknown | 1 |
| 45 | Llama-4-Maverick-17B-128E-Instruct 2025-04-05config_c85f902ef6cfd9a335fe0671f53a15c142fe7c28bfec02ab65d89f27dc1174e1 | 6% | Unknown | 1 |
| 46 | claude-sonnet-4-20250514_unknown 2025-05-22config_0a826345ca7ce71aec37325caa311d17728bc2b0a88a31a9dd465dc5ce57b96f | 6% | Unknown | 1 |
| 47 | gpt-4.5-preview-2025-02-27config_82b0b596de11c8b2ebd692040e9fa1dbe1b5b5e387543063b09e9adf3642e7ce | 5% | Unknown | 1 |
| 48 | gpt-4.1-2025-04-14config_a67b333bc674bfeeac2ad9cdff758ec774b29ebecc747428d1181b8eff72b440 | 5% | Unknown | 1 |
| 49 | gemini-1.5-pro-002 2024-09-24config_15a08c634ca88c673eaffac846c70e57ed4a4d6ad603aaf105ce54da21e9fbb2 | 5% | Unknown | 1 |
| 50 | mistral-medium-2505 2025-05-07config_16aa593d4b9d123698a9910243824c241ce8990d08c579b9b49b93911060a898 | 5% | Unknown | 1 |
| 51 | amazon.nova-pro-v1:0 2024-12-03config_19a124f77431f7ba504b88a72e9903e275a98af44a9e1f423a1752ddbbf93f56 | 4% | Unknown | 1 |
| 52 | claude-3-5-sonnet-20241022 2024-10-22config_e7c81cb1468bb68568b41a781b84c3d8d031855865936688ba8db46784dcbd6c | 4% | Unknown | 1 |
| 53 | amazon.nova-lite-v1:0 2024-12-03config_a88cb2cee387b434a41ea8870d0836c9fba311a08dcf8a8ed38c4dfa7b804374 | 4% | Unknown | 1 |
| 54 | gpt-4o-2024-11-20config_9e4ddd087b6766c3fa7d7206d5d341b961d242105b347f69dbdb3a96612d1076 | 3% | Unknown | 1 |
Explorer evidence
LiveBench reasoning
Sources differ; shown separately, never averaged. Observed ; fresh until .
| Rank | Configuration | Capability | Uncertainty | Families |
|---|---|---|---|---|
| 1 | kimi-k3 eqbench-creative-writing-v3:kimi-k3config_d66c6e07fedc532103cff26a3a24b654216470b82fa4599cbb46193cc807d689 | 100% | Unknown | 1 |
| 2 | grok-4.5 eqbench-creative-writing-v3:grok-4.5config_f6bc46fa147cb6f6b9a67207d6897da9312ec39c66ddfa53a122fcc220190b9e | 0% | 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