Content-safety classification

Results are only compared within a matching group, so a model tested one way is never ranked against a model tested another way.

Classify text as safe or unsafe, flagging unsafe content with high recall while rarely flagging harmless text that only sounds unsafe

Ranking groups use separate scales. Compare configurations only inside the same group; EvalRank never flattens unlike systems into one leaderboard.

Cross-benchmark consensus

One ranking of models across this topic's admitted benchmarks, weighted the same way decisions are. Each score is the model's share of the best result.

RankModelShare of bestBenchmarks
1nemotron3ultra550ba55b100.0%1
2gemini31flashlite99.7%1
3beam10501ba23b99.6%1
4gemini31flashlitepreview99.5%1
5gpt61solpro99.3%1
6gemini3flashpreview99.1%1
7claudesonnet5599.1%1
8minimaxm399.0%1
9gpt61terra98.9%1
10minimaxm2798.9%1
11minimaxm2598.8%1
12step5preview98.8%1
13gpt6sol98.8%1
14gemma431bit98.6%1
15gemma426ba4bit98.5%1
16gpt61sol98.5%1
17kimik2698.4%1
18gpt6solpro98.4%1
19musesparkopen98.3%1
20glimpse98.2%1
21qwen35397ba17b98.2%1
22nemotron35supervl98.1%1
23deepseekv41flash101797.9%1
24minimaxm31flash97.9%1
25deepseekv4flashvisionexp97.8%1
26gemini35flash97.6%1
27gpt61terrapro97.4%1
28mimov26flash97.4%1
29museglimmer30b97.3%1
30deepseekv4pro081397.3%1
31glm5297.2%1
32glm4796.9%1
33gemini36flash96.9%1
34gemini4argon96.8%1
35deepseekv3296.8%1
36qwen3527b96.8%1
37gemini35flashlite96.6%1
38claudehaiku5596.6%1
39deepseekv41flash96.6%1
40glm53flash96.5%1
41gpt5196.4%1
42qwen3627b96.1%1
43deepseekv4pro95.9%1
44glm5395.4%1
45qwen3827b95.4%1
46gpt6lunapro95.3%1
47granite428b95.1%1
48gpt56lunapro95.0%1
49nemotron3super120ba12b94.9%1
50qwen3635ba3b94.9%1
51deepseekv4flash94.8%1
52gpt6luna94.6%1
53gpt54mini94.6%1
54gpt56luna94.4%1
55deepseekv4flash073192.4%1
56glm47flash92.0%1
57gpt51codex92.0%1
58gpt51codexmini91.5%1
59glm590.3%1
60nemotron35lightning90.1%1
61gpt51codexmax89.8%1
62gpt54nano88.2%1
63claudesonnet588.1%1
64qwen3535ba3b80.5%1

Model configuration · Direct prompt

Exploratory - not a ranked winner yet
rg-content-safety-classification-model-configuration-direct-prompt-model-configuration-v1

Explorer evidence

Content-safety classification board (EvalRank)

Single source. Observed ; fresh until .

RankConfigurationCapabilityUncertaintyFamilies
1nvidia/nemotron-3-ultra-550b-a55b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_7d99eb067bf755ad2ac4eed492ded7c298113a972ed3482133ed762b1de16b78100%Unknown1
2google/gemini-3.1-flash-lite evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_c0740610436eb8ba7a4c51adfc38037e58a5793315d734e1937878f4649d3caf98%Unknown1
3reflection/beam-1.0-501b-a23b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_2155c6e9341ea1063997ef1c246a68b92344920065b206e8a532d5dd4039fb2898%Unknown1
4google/gemini-3.1-flash-lite-preview evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_4dd62c9832f9c5af54479fb9a4ab1798867614257d96152e7c372520ac11f08398%Unknown1
5openai/gpt-6.1-sol-pro evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_c3efa144559b10cd3f0dbd1f2744d19cd8f6f8744fcad431a5c8737bd883ba8096%Unknown1
6google/gemini-3-flash-preview evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_442b3254e105769c9f1fbafa2cf80ca2cf15b6eaa49b5a6befcc7744db4a57a796%Unknown1
7anthropic/claude-sonnet-5.5 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_9b18ddbe788f23e2328627ca091bbfa2b87facb463b3abe9156f46000953558196%Unknown1
8minimax/minimax-m3 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_fab1fceeb9494c0411fa9c92a0eaba632dc8409c976d16c209063dfe93ccdc2995%Unknown1
9openai/gpt-6.1-terra evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_1d22c134a1360bbfc2ae951d071b1056af11d422a2ba518bd8916e80994a3c0194%Unknown1
10minimax/minimax-m2.7 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_b23ed36c7637c457294b272eadb80afcead7d23f861e543d858fa7bdefd5b7d094%Unknown1
11minimax/minimax-m2.5 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_ddc9b3a2df0fb875265ef3ed132304ba7acc702751b37091056e002a5f1329f994%Unknown1
12stepfun/step-5-preview evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_ea728c9b0fca06110f24790229ec3a0e2a90693fcaca272afd50c4efa4aa8bf494%Unknown1
13openai/gpt-6-sol evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_fad8a2e4ecc1874a0f01ab8ef3a739d8b2384ea466ef8be154432a9a64592ad594%Unknown1
14google/gemma-4-31b-it evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_6f2bca52853c147b75881629111e70f00705ce89cdadd157111b158d296f5b7a93%Unknown1
15google/gemma-4-26b-a4b-it evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_43b6f57ea4f493c88995b41322c8d8e3e3b2cf02f67b9f56fc53750fbeecf59493%Unknown1
16openai/gpt-6.1-sol evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_a0dc3da2feef4024d38c3593705754bd8fd4590873de9806a763f792bb236ddb92%Unknown1
17moonshotai/kimi-k2.6 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_635e37df07b4bda8605aafb0b8e7b6a71187e5b293bece532dbc023f07fdc1b992%Unknown1
18openai/gpt-6-sol-pro evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_8fb82d4ae23949fa0e3b09224a701932e00db56e372b300563f6fc9696041d8192%Unknown1
19meta/muse-spark-open evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_7f227ac4a9e1b2c8f6e3f78a6434486ff5eaa964afe06e1ab7ef7d7141209bbd91%Unknown1
20elorian/glimpse evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_238f80b31c4c82b5210bf16843248970293dbaa425171d3c390e1d1cd5393d8a91%Unknown1
21qwen/qwen3.5-397b-a17b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_ad0d0fa0e3daf5c7f909972ba32614dbea12f65f4db742e32841b08fa389f2f391%Unknown1
22nvidia/nemotron-3.5-super-vl evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_115f5e3115fa9e1af3e6d8dc67b0b1a66b9cacaf359a50758cda8b35ef7a61d290%Unknown1
23deepseek/deepseek-v4.1-flash-1017 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_3dd050f56d024ad6316e2ea453b46bc3d39832b2aaf9abd34cf8e5e7ba34cf1f89%Unknown1
24minimax/minimax-m3.1-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_a5affc900ec149755655e39d490eac5d2e85880361ddf9f5a97becd6044e796489%Unknown1
25deepseek/deepseek-v4-flash-vision-exp evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_3d2d55c4242f8eb51b7b133145e82ef33971385ece7ee7fd0abc0f333643c6b189%Unknown1
26google/gemini-3.5-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_8610441536c049d3ee484d51228f0171f9aa0d86ede49e6031c3aac345c1941288%Unknown1
27openai/gpt-6.1-terra-pro evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_73f0264984f0b9978d96b597d40a7268f75362e2212bb641b5792a45d3644cf087%Unknown1
28xiaomi/mimo-v2.6-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_f4356f31a8b09b0ac18d413260140e3d740e4e498bf5b2d6e81d26348691a90986%Unknown1
29meta/muse-glimmer-30b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_6747ee32ad5046a79edfd2e3b261add7a9c324422df989ce7ed8f096f0ee3c2886%Unknown1
30deepseek/deepseek-v4-pro-0813 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_f9b97ce14e997236c72e6daade92cde3c60dac1f0ba7c984c6669fc68f7e9c1d86%Unknown1
31z-ai/glm-5.2 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_120dd6c22755d4cbdc9272d709391f21fd17a896d825e04a03e75f2f1843a56086%Unknown1
32z-ai/glm-4.7 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_64619a046266e3fc27a85eb007cea8df376927c7f5df6177bbf9dff0d0e9a3aa84%Unknown1
33google/gemini-3.6-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_5f1804314139414d4217c30c800f66773418cc18c9daf8252c03693931fa947084%Unknown1
34google/gemini-4-argon evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_f08e4ef4677affaf9bcf7fa8ad339cb268daa2169c1395f91ccdc3848dc38fa184%Unknown1
35deepseek/deepseek-v3.2 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:unavailableconfig_e46f182963294fd8ac9b13dd94e005481af49bb73d57f6b4c1ff58765f7ff36d83%Unknown1
36qwen/qwen3.5-27b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_59baf54cd1ce90bf480c5f8f6be017b9bcd32182817e84291a68b45e926a727583%Unknown1
37google/gemini-3.5-flash-lite evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_8ab35556769122f6730cb555f916447e1c8bf6185e10523f28b3ce5e50db27fb83%Unknown1
38anthropic/claude-haiku-5.5 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_2751fa6baf3817144e1312d65bc49b600a27ff9796b40b892cf5ed09e6b0056883%Unknown1
39deepseek/deepseek-v4.1-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_1d325a8aeb593573cca9ba825520046da0ffc4fcefcb06db061f8ef5fea91a5482%Unknown1
40z-ai/glm-5.3-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_fb52ad4ac1c4026292a3f1240a4dc2e1d12e16083e95646db8212b77ed57ea1b82%Unknown1
41openai/gpt-5.1 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_b8350fce891d7d514e0480df7b6234e491f02dbc8ae150fd6e704aa23b0191e682%Unknown1
42qwen/qwen3.6-27b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_a78ddb6cebf92f398affb21e6b7e3f795bc29270d9fd53deead33eaa1df411cb80%Unknown1
43deepseek/deepseek-v4-pro evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_7000fdb416cbab9f2be6b2f33119adc41118915abc07e7a7e8213ee7336d205a79%Unknown1
44z-ai/glm-5.3 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_12fe0ff251166fdeb583bf45c9ece4a19c1d3bb40b7c33662ba2c969d9850eaf76%Unknown1
45qwen/qwen3.8-27b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_be71109b07ef89f80a58dc5652e8da5649a32fa622ccbe7af6a01c49b662325f76%Unknown1
46openai/gpt-6-luna-pro evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_3b22b0a8f90d6a9c89cb944c4ada16295394fed726da9f02edcefa4b6454fb3876%Unknown1
47ibm-granite/granite-4.2-8b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_4c77c6e59730f431caf2e6018aa101251b026a28699cca491f6fcb57d134a63975%Unknown1
48openai/gpt-5.6-luna-pro evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_a84bda106ab3974d69df8143a7ecfd41ae25fa3af4034c9cda5232a494ed381d74%Unknown1
49nvidia/nemotron-3-super-120b-a12b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_65206ed835937e4a58e9249a2680b4d2872397bf3abf72b22d2c07dc044ed27174%Unknown1
50qwen/qwen3.6-35b-a3b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_099dfd7875cbd5ab4e85221be7656ef51863c17bb94c9af651a328e19a70a2e874%Unknown1
51deepseek/deepseek-v4-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_6bd0c5eb925bb5e63bef71def75efe0301ca52099eca2e0bbcf7981e2aceb51c73%Unknown1
52openai/gpt-6-luna evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_4dbbd2f0ab0d84b7c248fbce5e80ca7551aad370b42a727b4f69166c2026644073%Unknown1
53openai/gpt-5.4-mini evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_4b66200184124eb485b499c0dd56642e2430b644289885afea04aa641c22cda772%Unknown1
54openai/gpt-5.6-luna evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_5cde82caefa8a815fe6f4beb950c65f9fae31efceeda19d1f631601ccdd4b6d372%Unknown1
55deepseek/deepseek-v4-flash-0731 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_e28e0dd0460ebad70a0f394de212558dcc7fb3d62e127c067a94eea4d50e718461%Unknown1
56z-ai/glm-4.7-flash evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_79cff7558daca1c8edbb265f6a708011a390a18f0d07f3295f2944d16c65273159%Unknown1
57openai/gpt-5.1-codex evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_843a8c73b4ee4d1e2dca77b266a2d0a8c20288a24b00117aa916efad91b9562259%Unknown1
58openai/gpt-5.1-codex-mini evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_7791eec96f3a1571763eb0485f92474fc5c2326ef8138f86f49d13bdc8b9a5de57%Unknown1
59z-ai/glm-5 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_d92561080dcb2ec18134f028e6d589c34c5ff86933ce31cd0baef9e79281047050%Unknown1
60nvidia/nemotron-3.5-lightning evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_0d55bafe2f486b6d40691b51a77137b641a3498419487b57ed2952d7d09a348349%Unknown1
61openai/gpt-5.1-codex-max evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_lowconfig_7af97febe265676b35c339b4b079bd74568d699f56190ed97a84580bfe2c2ffb47%Unknown1
62openai/gpt-5.4-nano evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_0ab43c9a147fa575ea2d61319dfac2869684ccb48595d6ba5ef34cca75dc928640%Unknown1
63anthropic/claude-sonnet-5 evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_962021295d532bdfe74c91e367fbb71a3bdb956d6247cd8302ccca6d864db38839%Unknown1
64qwen/qwen3.5-35b-a3b evalrank-content-safety:946af6ce1f3654dc9cdffcd310e5dcbf13b451cfc96766af8572debd3783a687:reasoning_offconfig_8d6e5890ab2b84a55f734f9f18f5b5329413ddfa75155e2ecb7b4bd460f6dcf70%Unknown1
Compare configurations in this group
Not enough independent evidence for a top set
  • Calibration has not been validated
  • Independent benchmark-family coverage is below the required threshold
Back to all kinds of work