BenchmarkActivecategory · agentic
quality57
Updated 9 h ago · first seen 11 Sept 2026
bench_01M293SPFPKK4MF90JEDK0PH8C
- Metric
- accuracy · %
- Direction
- Higher is better
- Results
- 821
- Leader
- Claude Fable 5.1 91.39%
Score history · Claude Opus 5 2 rows
Not enough history to chart — 2 observations, all dated 11 Sept 2026. Rows under different configurations count separately; the list below shows each one.
- 89.14%aa_slug=claude-opus-5 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
- 48.99%aa_slug=claude-opus-5 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
Leaderboard 821 current results
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #201gpt-6-astra-lowOpenAI | 41.92% | aa_slug=gpt-6-astra-low · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #202MiMo-V2.5Xiaomi | 41.67% | aa_slug=mimo-v2-5-0424 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #203deepseek-v4-pro-0424-highDeepSeek | 41.67% | aa_slug=deepseek-v4-pro-0424-high · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #204gemini-3-proGoogle | 41.67% | aa_slug=gemini-3-pro · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #205qwen3-6-35b-a3b-non-reasoningAlibaba Group | 41.57% | aa_slug=qwen3-6-35b-a3b-non-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #206Claude Opus 4.5Anthropic | 40.91% | aa_slug=claude-opus-4-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #207mimo-v2-proXiaomi | 40.91% | aa_slug=mimo-v2-pro · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #208Qwen3.5 397B A17BQwen | 40.91% | aa_slug=qwen3-5-397b-a17b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #209grok-4-20-0309SpaceXAI | 40.91% | aa_slug=grok-4-20-0309 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #210Gemini 3.5 FlashGoogle | 40.91% | aa_slug=gemini-3-5-flash · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #211qwen3-5-35b-a3b-non-reasoningAlibaba Group | 40.82% | aa_slug=qwen3-5-35b-a3b-non-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #212k-exaone-2-0-0803LG AI Research | 40.45% | aa_slug=k-exaone-2-0-0803 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #213claude-fable-5-1-lowAnthropic | 40.4% | aa_slug=claude-fable-5-1-low · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #214gpt-5-6-solOpenAI | 39.9% | aa_slug=gpt-5-6-sol · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #215Grok 4.3xAI | 39.7% | aa_slug=grok-4-3 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #216MiniMax M2.7MiniMax | 39.39% | aa_slug=minimax-m2-7 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #217gemini-3-5-flash-mediumGoogle | 39.39% | aa_slug=gemini-3-5-flash-medium · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #218glm-5-non-reasoningZ.ai (Zhipu AI) | 39.39% | aa_slug=glm-5-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #219Step 3.7 FlashStepFun | 39.33% | aa_slug=step-3-7-flash · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #220a-x-k2SK Telecom | 38.95% | aa_slug=a-x-k2 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #221gpt-5-6-luna-non-reasoningOpenAI | 38.95% | aa_slug=gpt-5-6-luna-non-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #222Gemma 4 26B A4BGoogle | 38.95% | aa_slug=gemma-4-26b-a4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #223Gemini 3 Flash PreviewGoogle | 38.64% | aa_slug=gemini-3-flash-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #224deepseek-v4-flash-0420-highDeepSeek | 38.64% | aa_slug=deepseek-v4-flash-0420-high · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #225Nemotron 3 SuperNVIDIA | 38.58% | aa_slug=nvidia-nemotron-3-super-120b-a12b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #226Qwen3 Coder NextQwen | 38.2% | aa_slug=qwen3-coder-next · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #227gpt-5-4-non-reasoningOpenAI | 37.88% | aa_slug=gpt-5-4-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #228GPT-5-CodexOpenAI | 37.88% | aa_slug=gpt-5-codex · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #229Grok 4.3xAI | 37.88% | aa_slug=grok-4-3 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #230Grok 4.20xAI | 37.88% | aa_slug=grok-4-20 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #231grok-4SpaceXAI | 37.88% | aa_slug=grok-4 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #232gpt-5 (medium)OpenAI | 37.88% | aa_slug=gpt-5-medium · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #233kimi-k2-6-non-reasoningMoonshot AI | 37.88% | aa_slug=kimi-k2-6-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #234GPT-5.2-CodexOpenAI | 37.12% | aa_slug=gpt-5-2-codex · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #235o3OpenAI | 37.12% | aa_slug=o3 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #236Gemma 4 31BGoogle | 36.36% | aa_slug=gemma-4-31b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #237deepseek-v4-pro-0424-non-reasoningDeepSeek | 36.36% | aa_slug=deepseek-v4-pro-0424-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #238Nemotron 3 UltraNVIDIA | 36.36% | aa_slug=nvidia-nemotron-3-ultra-550b-a55b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #239claude-4-sonnet-thinkingAnthropic | 36.33% | aa_slug=claude-4-sonnet-thinking · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #240claude-4-5-sonnet-thinkingAnthropic | 35.61% | aa_slug=claude-4-5-sonnet-thinking · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #241qwen3-5-397b-a17b-non-reasoningAlibaba Group | 35.61% | aa_slug=qwen3-5-397b-a17b-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #242DeepSeek V3.2DeepSeek | 35.61% | aa_slug=deepseek-v3-2-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #243deepseek-v4-flash-0420DeepSeek | 35.61% | aa_slug=deepseek-v4-flash-0420 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #244mimo-v2-omni-0327Xiaomi | 35.61% | aa_slug=mimo-v2-omni-0327 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #245glm-5-1-non-reasoningZ.ai (Zhipu AI) | 35.61% | aa_slug=glm-5-1-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #246Step 3.7 FlashStepFun | 35.61% | aa_slug=step-3-7-flash · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #247mimo-v2-5-pro-non-reasoningXiaomi | 35.61% | aa_slug=mimo-v2-5-pro-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #248North Mini Code (free)Cohere | 35.58% | aa_slug=north-mini-code · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #249gpt-5.6-terraOpenAI | 35.35% | aa_slug=gpt-5-6-terra · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #250gpt-5OpenAI | 35.21% | aa_slug=gpt-5 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #251Qwen3.6 35B A3BQwen | 34.85% | aa_slug=qwen3-6-35b-a3b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #252MiniMax M2.5MiniMax | 34.85% | aa_slug=minimax-m2-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #253Qwen3.6 27BQwen | 34.85% | aa_slug=qwen3-6-27b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #254deepseek-v3-2-specialeDeepSeek | 34.85% | aa_slug=deepseek-v3-2-speciale · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #255mimo-v2-omniXiaomi | 34.85% | aa_slug=mimo-v2-omni · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #256GPT-5.1-CodexOpenAI | 34.85% | aa_slug=gpt-5-1-codex · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #257Kimi K2.5Moonshot AI | 34.85% | aa_slug=kimi-k2-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #258gpt-5-5-instant-06-26OpenAI | 34.83% | aa_slug=gpt-5-5-instant-06-26 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #259claude-4-1-opus-thinkingAnthropic | 34.34% | aa_slug=claude-4-1-opus-thinking · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #260claude-opus-5-mediumAnthropic | 34.34% | aa_slug=claude-opus-5-medium · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #261Hy3 previewTencent | 34.09% | aa_slug=hy3-preview · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #262deepseek-v4-flash-0420-non-reasoningDeepSeek | 34.09% | aa_slug=deepseek-v4-flash-0420-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #263gemini-3-pro-lowGoogle | 34.09% | aa_slug=gemini-3-pro-low · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #264gpt-5-4-mini-mediumOpenAI | 34.09% | aa_slug=gpt-5-4-mini-medium · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #265grok-4-3-non-reasoningSpaceXAI | 34.08% | aa_slug=grok-4-3-non-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #266gpt-5-miniOpenAI | 33.33% | aa_slug=gpt-5-mini · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #267GLM 5 TurboZ.ai (Zhipu AI) | 33.33% | aa_slug=glm-5-turbo · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #268Mistral Medium 3.5Mistral AI | 33.33% | aa_slug=mistral-medium-3-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #269GPT-5.1-Codex MiniOpenAI | 33.33% | aa_slug=gpt-5-1-codex-mini · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #270gpt-5-4-nano-mediumOpenAI | 33.33% | aa_slug=gpt-5-4-nano-medium · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #271Muse Spark 1.3Meta AI | 33.33% | aa_slug=muse-spark-1-3 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #272GLM 5.3 FlashZ.ai (Zhipu AI) | 32.83% | aa_slug=glm-5-3-flash · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #273Qwen3.5-27BQwen | 32.58% | aa_slug=qwen3-5-27b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #274gpt-5OpenAI | 32.58% | aa_slug=gpt-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #275DeepSeek V3DeepSeek | 32.58% | aa_slug=deepseek-v3-2 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #276g9v3-39a5bAI9Stars | 32.58% | aa_slug=g9v3-39a5b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #277step-3-5-flashStepFun | 32.58% | aa_slug=step-3-5-flash · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #278GLM 5V TurboZ.ai (Zhipu AI) | 32.58% | aa_slug=glm-5v-turbo · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #279GLM 4.7Z.ai (Zhipu AI) | 31.82% | aa_slug=glm-4-7 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #280qwen3-5-27b-non-reasoningAlibaba Group | 31.82% | aa_slug=qwen3-5-27b-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #281hy3-non-reasoningTencent | 31.82% | aa_slug=hy3-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #282gpt-5-2-non-reasoningOpenAI | 31.82% | aa_slug=gpt-5-2-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #283DeepSeek V3.1 TerminusDeepSeek | 31.82% | aa_slug=deepseek-v3-1-terminus · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #284gemini-3-flashGoogle | 31.82% | aa_slug=gemini-3-flash · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #285gemini-3-1-flash-lite-previewGoogle | 31.09% | aa_slug=gemini-3-1-flash-lite-preview · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #286DeepSeek V3.2 ExpDeepSeek | 31.06% | aa_slug=deepseek-v3-2-reasoning-0925 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #287Qwen3.5-122B-A10BQwen | 31.06% | aa_slug=qwen3-5-122b-a10b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #288ling-2-6-1tinclusionAI | 31.06% | aa_slug=ling-2-6-1t · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #289Claude Opus 4Anthropic | 31.06% | aa_slug=claude-4-opus-thinking · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #290North Mini Code (free)Cohere | 31.06% | aa_slug=north-mini-code · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #291Kimi K2 ThinkingMoonshot AI | 31.06% | aa_slug=kimi-k2-thinking · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #292mimo-v2-0206Xiaomi | 31.06% | aa_slug=mimo-v2-0206 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #293claude-4-sonnet-thinkingAnthropic | 31.06% | aa_slug=claude-4-sonnet-thinking · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #294k-exaoneLG AI Research | 30.34% | aa_slug=k-exaone · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #295Devstral 2Mistral AI | 30.34% | aa_slug=devstral-2 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #296glm-4-7-non-reasoningZ.ai (Zhipu AI) | 30.3% | aa_slug=glm-4-7-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #297grok-4-3-mediumSpaceXAI | 30.3% | aa_slug=grok-4-3-medium · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #298deepseek-v3-1-terminus-reasoningDeepSeek | 30.3% | aa_slug=deepseek-v3-1-terminus-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #299gemma-4-31b-non-reasoningGoogle | 30.3% | aa_slug=gemma-4-31b-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #300nova-2-0-pro-reasoning-mediumAmazon Web Services | 29.59% | aa_slug=nova-2-0-pro-reasoning-medium · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History |
Scores are reported as published, with their evaluation configuration (harness, prompting, judge). The bar is relative to the best score on this page. Results with different configs are not directly comparable — see methodology.
The config filter matches a value inside each result's configuration (server-side, `config=` on the API). Chips are the values shared by several rows on the first page; per-model identifiers are not offered.
Definition
- Category
- agentic
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Task
- terminal tasks solved by agents
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Metric
- accuracy · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Direction
- Higher is better
- Website
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
Each value shows its source, tier and observation time. Missing rows mean no source stated them. How results are recorded →
- Evaluated models
- grok-3-mini-reasoning, claude-opus-5-medium, gemma-4-12B, deepseek-v4-flash, grok-4-3-low, GPT-5.1-Codex Mini, Qwen3 Coder Next, KAT-Coder-Pro V2 +523(531 total)
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history
5 claims · 5 properties
Categorycategory1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| agentic | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Metricmetric1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| accuracy | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Tasktask1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| terminal tasks solved by agents | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Unitunit1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| % | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Websitewebsite1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://www.tbench.ai | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Artificial Analysis | artificialanalysis.ai/leaderboards/models | leaderboard | T2· Quality secondary | 7 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.