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 · grok-4-6-xhigh 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.
- 88.01%aa_slug=grok-4-6-xhigh · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
- 17.17%aa_slug=grok-4-6-xhigh · 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 |
|---|---|---|---|---|---|---|
| #501Qwen3 VL 32B InstructQwen | 8.33% | aa_slug=qwen3-vl-32b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #502k2-v2-mediumMBZUAI Institute of Foundation Models | 8.33% | aa_slug=k2-v2-medium · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #503qwen3-5-omni-flashAlibaba Group | 8.33% | aa_slug=qwen3-5-omni-flash · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #504gpt-4oOpenAI | 8.33% | aa_slug=gpt-4o · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #505nemotron-3-nano-omni-30b-a3bNVIDIA | 8.33% | aa_slug=nemotron-3-nano-omni-30b-a3b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #506Llama 4 MaverickMeta AI | 7.87% | aa_slug=llama-4-maverick · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #507qwen3-vl-32b-reasoningAlibaba Group | 7.58% | aa_slug=qwen3-vl-32b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #508Qwen3 Next 80B A3B InstructQwen | 7.58% | aa_slug=qwen3-next-80b-a3b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #509Mistral Small 3.1Mistral AI | 7.58% | aa_slug=mistral-small-3-1 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #510gpt-4.1-miniOpenAI | 7.58% | aa_slug=gpt-4-1-mini · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #511ring-flash-2-0inclusionAI | 7.58% | aa_slug=ring-flash-2-0 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #512Solar Pro 3Upstage | 7.58% | aa_slug=solar-pro-3 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #513gemma-4-e4b-non-reasoningGoogle | 7.58% | aa_slug=gemma-4-e4b-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #514gemini-2-5-flash-lite-preview-09-2025Google | 7.58% | aa_slug=gemini-2-5-flash-lite-preview-09-2025 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #515Gemini 3.6 FlashGoogle | 7.07% | aa_slug=gemini-3-6-flash · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #516claude-sonnet-5-xhighAnthropic | 7.07% | aa_slug=claude-sonnet-5-xhigh · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #517agnes-3-0-flashSapiens AI | 7.07% | aa_slug=agnes-3-0-flash · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #518Muse Spark 1.2Meta AI | 7.07% | aa_slug=muse-spark-1-2 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #519o3-miniOpenAI | 6.82% | aa_slug=o3-mini · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #520Seed-OSS-36B-InstructByteDance | 6.82% | aa_slug=seed-oss-36b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #521nova-2-0-liteAmazon Web Services | 6.82% | aa_slug=nova-2-0-lite · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #522nvidia-nemotron-3-nano-4bNVIDIA | 6.82% | aa_slug=nvidia-nemotron-3-nano-4b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #523Llama-3.1-405BMeta AI | 6.82% | aa_slug=llama-3-1-instruct-405b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #524k2-think-v2MBZUAI Institute of Foundation Models | 6.82% | aa_slug=k2-think-v2 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #525glm-4-5vZ.ai (Zhipu AI) | 6.82% | aa_slug=glm-4-5v · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #526nova-premierAmazon Web Services | 6.82% | aa_slug=nova-premier · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #527Llama 4 MaverickMeta AI | 6.82% | aa_slug=llama-4-maverick · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #528ring-1tinclusionAI | 6.82% | aa_slug=ring-1t · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #529qwen3-30b-a3b-instructAlibaba Group | 6.82% | aa_slug=qwen3-30b-a3b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #530deepseek-v3DeepSeek | 6.82% | aa_slug=deepseek-v3 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #531Qwen3 VL 235B A22B InstructQwen | 6.82% | aa_slug=qwen3-vl-235b-a22b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #532gpt-5-nano-minimalOpenAI | 6.82% | aa_slug=gpt-5-nano-minimal · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #533nova-2-0-omniAmazon Web Services | 6.82% | aa_slug=nova-2-0-omni · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #534k-exaone-non-reasoningLG AI Research | 6.82% | aa_slug=k-exaone-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #535Mistral Small 3.2Mistral AI | 6.82% | aa_slug=mistral-small-3-2 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #536qwen3-next-80b-a3b-reasoningAlibaba Group | 6.74% | aa_slug=qwen3-next-80b-a3b-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #537nemotron-3-nano-omni-30b-a3bNVIDIA | 6.74% | aa_slug=nemotron-3-nano-omni-30b-a3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #538nvidia-nemotron-3-nano-30b-a3b-reasoningNVIDIA | 6.74% | aa_slug=nvidia-nemotron-3-nano-30b-a3b-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #539Gemini 3.5 FlashGoogle | 6.57% | aa_slug=gemini-3-5-flash · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #540devstral-smallMistral AI | 6.06% | aa_slug=devstral-small · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #541mistral-large-2Mistral AI | 6.06% | aa_slug=mistral-large-2 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #542qwen3-235b-a22b-instruct-reasoningAlibaba Group | 6.06% | aa_slug=qwen3-235b-a22b-instruct-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #543qwen3-235b-a22b-instructAlibaba Group | 6.06% | aa_slug=qwen3-235b-a22b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #544deepseek-r1-0120DeepSeek | 6.06% | aa_slug=deepseek-r1-0120 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #545nova-proAmazon Web Services | 6.06% | aa_slug=nova-pro · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #546qwen3-30b-a3b-2507Alibaba Group | 6.06% | aa_slug=qwen3-30b-a3b-2507 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #547o3 Mini HighOpenAI | 6.06% | aa_slug=o3-mini-high · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #548Qwen3 VL 30B A3B InstructQwen | 6.06% | aa_slug=qwen3-vl-30b-a3b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #549Devstral Small 1.0Mistral AI | 6.06% | aa_slug=devstral-small-2505 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #550Muse Spark 1.1Meta AI | 6.06% | aa_slug=muse-spark-1-1 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #551ernie-4-5-300b-a47bBaidu | 6.06% | aa_slug=ernie-4-5-300b-a47b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #552g9v3-3bAI9Stars | 5.99% | aa_slug=g9v3-3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #553gpt-4o-miniOpenAI | 5.62% | aa_slug=gpt-4o-mini · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #554Mistral Small 3.2Mistral AI | 5.62% | aa_slug=mistral-small-3-2 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #555Qwen3.8 27BQwen | 5.56% | aa_slug=qwen3-8-27b · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #556gpt-oss-120b-lowOpenAI | 5.3% | aa_slug=gpt-oss-120b-low · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #557qwen3-vl-30b-a3b-reasoningAlibaba Group | 5.3% | aa_slug=qwen3-vl-30b-a3b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #558GLM 4.5VZ.ai (Zhipu AI) | 5.3% | aa_slug=glm-4-5v-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #559qwen3-14b-instructAlibaba Group | 5.3% | aa_slug=qwen3-14b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #560qwen3-30b-a3b-2507-reasoningAlibaba Group | 5.3% | aa_slug=qwen3-30b-a3b-2507-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #561llama-nemotron-super-49b-v1-5-reasoningNVIDIA | 5.3% | aa_slug=llama-nemotron-super-49b-v1-5-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #562step-3-vl-10bStepFun | 5.3% | aa_slug=step-3-vl-10b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #563Qwen3 32BQwen | 5.24% | aa_slug=qwen3-32b-instruct-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #564gpt-5-5-mediumOpenAI | 5.05% | aa_slug=gpt-5-5-medium · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #565claude-sonnet-5-highAnthropic | 5.05% | aa_slug=claude-sonnet-5-high · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #566qwen3-8-27b-mediumAlibaba Group | 5.05% | aa_slug=qwen3-8-27b-medium · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #567Llama 3.3 70BMeta AI | 4.87% | aa_slug=llama-3-3-instruct-70b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #568Qwen3 14BQwen | 4.87% | aa_slug=qwen3-14b-instruct-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #569qwen2-5-72b-instructAlibaba Group | 4.55% | aa_slug=qwen2-5-72b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #570llama-3-1-nemotron-instruct-70bNVIDIA | 4.55% | aa_slug=llama-3-1-nemotron-instruct-70b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #571Gemini 2.5 Flash-LiteGoogle | 4.55% | aa_slug=gemini-2-5-flash-lite-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #572Ministral 3 14BMistral AI | 4.55% | aa_slug=ministral-3-14b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #573Magistral Small 1.2Mistral AI | 4.55% | aa_slug=magistral-small-2509 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #574gpt-oss-20b-lowOpenAI | 4.55% | aa_slug=gpt-oss-20b-low · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #575magistral-smallMistral AI | 4.55% | aa_slug=magistral-small · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #576Hermes-4-70BNous Research | 4.55% | aa_slug=hermes-4-llama-3-1-70b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #577k2-v2-lowMBZUAI Institute of Foundation Models | 4.55% | aa_slug=k2-v2-low · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #578qwen3-4b-2507-instructAlibaba Group | 4.55% | aa_slug=qwen3-4b-2507-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #579LFM2.5-8B-A1BLiquid AI | 4.55% | aa_slug=lfm2-5-8b-a1b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #580Ministral 3 8BMistral AI | 4.55% | aa_slug=ministral-3-8b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #581solar-pro-2Upstage | 4.55% | aa_slug=solar-pro-2 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #582nvidia-nemotron-nano-12b-v2-vl-reasoningNVIDIA | 4.55% | aa_slug=nvidia-nemotron-nano-12b-v2-vl-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #583nova-2-0-omni-reasoning-mediumAmazon Web Services | 4.55% | aa_slug=nova-2-0-omni-reasoning-medium · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #584Gemma 3 27BGoogle | 4.49% | aa_slug=gemma-3-27b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #585LFM2.5-2.6B (free)Liquid AI | 4.49% | aa_slug=lfm2-5-2-6b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #586o3 Mini HighOpenAI | 4.49% | aa_slug=o3-mini-high · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #587Magistral Small 1.2Mistral AI | 4.49% | aa_slug=magistral-small-2509 · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #588Ministral 3 8BMistral AI | 4.12% | aa_slug=ministral-3-8b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #589Gemini 3.1 Pro PreviewGoogle | 4.04% | aa_slug=gemini-3-1-pro-preview · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #590exaone-4-0-32b-reasoningLG AI Research | 3.79% | aa_slug=exaone-4-0-32b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #591qwen3-vl-8b-reasoningAlibaba Group | 3.79% | aa_slug=qwen3-vl-8b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #592Qwen3.5-2BQwen | 3.79% | aa_slug=qwen3-5-2b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #593Gemini 2.0 FlashGoogle | 3.79% | aa_slug=gemini-2-0-flash · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #594Mistral Medium 3Mistral AI | 3.79% | aa_slug=mistral-medium-3 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #595motif-2-12-7bMotif Technologies | 3.79% | aa_slug=motif-2-12-7b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #596qwen3-5-2b-non-reasoningAlibaba Group | 3.79% | aa_slug=qwen3-5-2b-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #597Phi 4Microsoft | 3.79% | aa_slug=phi-4 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #598glm-4-7-flash-non-reasoningZ.ai (Zhipu AI) | 3.79% | aa_slug=glm-4-7-flash-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #599Gemma 3 27BGoogle | 3.79% | aa_slug=gemma-3-27b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #600llama-nemotron-super-49b-v1-5NVIDIA | 3.79% | aa_slug=llama-nemotron-super-49b-v1-5 · variant=hard · 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.