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%
Leaderboard 821 current results
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #601nova-2-0-lite-reasoning-lowAmazon Web Services | 3.79% | aa_slug=nova-2-0-lite-reasoning-low · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #602nova-2-0-omni-reasoning-lowAmazon Web Services | 3.79% | aa_slug=nova-2-0-omni-reasoning-low · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #603gpt-4.1-nanoOpenAI | 3.79% | aa_slug=gpt-4-1-nano · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #604qwen3-omni-30b-a3b-reasoningAlibaba Group | 3.79% | aa_slug=qwen3-omni-30b-a3b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #605Qwen3 14BQwen | 3.79% | aa_slug=qwen3-14b-instruct-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #606nvidia-nemotron-3-nano-4bNVIDIA | 3.75% | aa_slug=nvidia-nemotron-3-nano-4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #607gpt-5-miniOpenAI | 3.75% | aa_slug=gpt-5-mini · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #608gpt-4.1-nanoOpenAI | 3.75% | aa_slug=gpt-4-1-nano · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #609Llama 4 ScoutMeta AI | 3.75% | aa_slug=llama-4-scout · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #610gpt-5-6-luna-xhighOpenAI | 3.54% | aa_slug=gpt-5-6-luna-xhigh · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #611granite-4.1-8bIBM | 3.37% | aa_slug=granite-4-1-8b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #612midm-250-pro-rsnsftKorea Telecom | 3.03% | aa_slug=midm-250-pro-rsnsft · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #613grok-4-6-lowSpaceXAI | 3.03% | aa_slug=grok-4-6-low · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #614claude-sonnet-4-6-adaptiveAnthropic | 3.03% | aa_slug=claude-sonnet-4-6-adaptive · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #615Llama-3.1-70BMeta AI | 3.03% | aa_slug=llama-3-1-instruct-70b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #616solar-pro-2-reasoningUpstage | 3.03% | aa_slug=solar-pro-2-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #617agnes-2-5-pro-alphaSapiens AI | 3.03% | aa_slug=agnes-2-5-pro-alpha · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #618glm-4-6vZ.ai (Zhipu AI) | 3.03% | aa_slug=glm-4-6v · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #619Qwen3 32BQwen | 3.03% | aa_slug=qwen3-32b-instruct-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #620MiniMax-M1-80kMiniMax | 3.03% | aa_slug=minimax-m1-80k · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #621gemma-4-E2BGoogle | 3.03% | aa_slug=gemma-4-e2b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #622deepseek-v4-flash-0420-highDeepSeek | 3.03% | aa_slug=deepseek-v4-flash-0420-high · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #623Llama 3.3 70BMeta AI | 3.03% | aa_slug=llama-3-3-instruct-70b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #624Qwen3.5-2BQwen | 3% | aa_slug=qwen3-5-2b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #625granite-4.1-30bIBM | 2.62% | aa_slug=granite-4-1-30b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #626deepseek-v4-flash-0420DeepSeek | 2.53% | aa_slug=deepseek-v4-flash-0420 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #627qwen3-8-27b-lowAlibaba Group | 2.53% | aa_slug=qwen3-8-27b-low · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #628claude-sonnet-5-lowAnthropic | 2.53% | aa_slug=claude-sonnet-5-low · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #629gpt-5-6-luna-highOpenAI | 2.53% | aa_slug=gpt-5-6-luna-high · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #630mi-dm-k-2-5-pro-dec28Korea Telecom | 2.27% | aa_slug=mi-dm-k-2-5-pro-dec28 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #631Claude Haiku 3.5Anthropic | 2.27% | aa_slug=claude-3-5-haiku · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #632gemma-4-e2b-non-reasoningGoogle | 2.27% | aa_slug=gemma-4-e2b-non-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #633granite-4.1-3bIBM | 2.27% | aa_slug=granite-4-1-3b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #634sarvam-30bSarvam | 2.27% | aa_slug=sarvam-30b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #635granite-4.1-30bIBM | 2.27% | aa_slug=granite-4-1-30b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #636qwen3-30b-a3b-instruct-reasoningAlibaba Group | 2.27% | aa_slug=qwen3-30b-a3b-instruct-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #637falcon-h1r-7bTII UAE | 2.27% | aa_slug=falcon-h1r-7b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #638Qwen3 VL 8B InstructQwen | 2.27% | aa_slug=qwen3-vl-8b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #639solar-open-100b-reasoningUpstage | 2.27% | aa_slug=solar-open-100b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #640tri-21b-think-previewTrillion Labs | 2.27% | aa_slug=tri-21b-think-preview · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #641MiniMax-M1-40kMiniMax | 2.27% | aa_slug=minimax-m1-40k · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #642llama-3-1-nemotron-ultra-253b-v1-reasoningNVIDIA | 2.27% | aa_slug=llama-3-1-nemotron-ultra-253b-v1-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #643sarvam-m-reasoningSarvam | 2.27% | aa_slug=sarvam-m-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #644gemma-3n-e4bGoogle | 2.27% | aa_slug=gemma-3n-e4b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #645qwen3-8b-instructAlibaba Group | 2.27% | aa_slug=qwen3-8b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #646jamba-1-7-largeAI21 Labs | 2.27% | aa_slug=jamba-1-7-large · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #647Qwen3 8BQwen | 2.27% | aa_slug=qwen3-8b-instruct-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #648granite-4-0-h-smallIBM | 2.27% | aa_slug=granite-4-0-h-small · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #649gemini-2-5-flash-liteGoogle | 2.27% | aa_slug=gemini-2-5-flash-lite · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #650Qwen3 8BQwen | 2.25% | aa_slug=qwen3-8b-instruct-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #651gpt-5.4-miniOpenAI | 2.02% | aa_slug=gpt-5-4-mini · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #652MiniMax M3MiniMax | 2.02% | aa_slug=minimax-m3 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #653GLM 5.1Z.ai (Zhipu AI) | 2.02% | aa_slug=glm-5-1 · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #654claude-sonnet-5-mediumAnthropic | 2.02% | aa_slug=claude-sonnet-5-medium · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #655gemma-4-E4BGoogle | 1.87% | aa_slug=gemma-4-e4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #656Granite 4.0 MicroIBM | 1.52% | aa_slug=granite-4-0-micro · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #657gpt-5-6-terra-highOpenAI | 1.52% | aa_slug=gpt-5-6-terra-high · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #658Qwen3.7 MaxQwen | 1.52% | aa_slug=qwen3-7-max · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #659DeepSeek-R1-0528-Qwen3-8BDeepSeek | 1.52% | aa_slug=deepseek-r1-qwen3-8b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #660R1 Distill Llama 70BDeepSeek | 1.52% | aa_slug=deepseek-r1-distill-llama-70b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #661Llama 4 ScoutMeta AI | 1.52% | aa_slug=llama-4-scout · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #662sarvam-105bSarvam | 1.52% | aa_slug=sarvam-105b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #663nova-microAmazon Web Services | 1.52% | aa_slug=nova-micro · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #664exaone-4-0-32bLG AI Research | 1.52% | aa_slug=exaone-4-0-32b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #665qwen3-4b-2507-instruct-reasoningAlibaba Group | 1.52% | aa_slug=qwen3-4b-2507-instruct-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #666olmo-3-32b-thinkAllen Institute for AI | 1.52% | aa_slug=olmo-3-32b-think · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #667gpt-5-6-terra-lowOpenAI | 1.52% | aa_slug=gpt-5-6-terra-low · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #668qwen3-omni-30b-a3b-instructAlibaba Group | 1.52% | aa_slug=qwen3-omni-30b-a3b-instruct · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #669NVIDIA-Nemotron-Nano-9B-v2NVIDIA | 1.52% | aa_slug=nvidia-nemotron-nano-9b-v2-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #670qwen3-vl-4b-reasoningAlibaba Group | 1.52% | aa_slug=qwen3-vl-4b-reasoning · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #671qwen3-30b-a3b-2507-reasoningAlibaba Group | 1.5% | aa_slug=qwen3-30b-a3b-2507-reasoning · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #672Llama 3.1 8BMeta AI | 1.5% | aa_slug=llama-3-1-instruct-8b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #673nanbeige4-1-3bNanbeige | 1.12% | aa_slug=nanbeige4-1-3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #674granite-4.1-3bIBM | 1.12% | aa_slug=granite-4-1-3b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #675Qwen 3.7 PlusQwen | 1.01% | aa_slug=qwen3-7-plus · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #676quasar-438bMultiverse Computing | 1.01% | aa_slug=quasar-438b · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #677gpt-5-6-terra-mediumOpenAI | 1.01% | aa_slug=gpt-5-6-terra-medium · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #678Inkling SmallThinking Machines | 1.01% | aa_slug=inkling-small · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #679Kimi K2.7 CodeMoonshot AI | 1.01% | aa_slug=kimi-k2-7-code · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #680gpt-5-6-sol-lowOpenAI | 1.01% | aa_slug=gpt-5-6-sol-low · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #681Gemini 3.5 Flash-LiteGoogle | 1.01% | aa_slug=gemini-3-5-flash-lite · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #682InklingThinking Machines | 1.01% | aa_slug=inkling · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #683Gemma 3 4BGoogle | 0.76% | aa_slug=gemma-3-4b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #684gemma-3n-e2bGoogle | 0.76% | aa_slug=gemma-3n-e2b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #685llama-3-instruct-70bMeta AI | 0.76% | aa_slug=llama-3-instruct-70b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #686tri-21b-think-v0-5Trillion Labs | 0.76% | aa_slug=tri-21b-think-v0-5 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #687Command ACohere | 0.76% | aa_slug=command-a · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #688nova-liteAmazon Web Services | 0.76% | aa_slug=nova-lite · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #689ling-mini-2-0inclusionAI | 0.76% | aa_slug=ling-mini-2-0 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #690Llama 3.1 8BMeta AI | 0.76% | aa_slug=llama-3-1-instruct-8b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #691Claude 3 HaikuAnthropic | 0.76% | aa_slug=claude-3-haiku · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #692Gemma 3 12BGoogle | 0.76% | aa_slug=gemma-3-12b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #693llama-3-2-instruct-11b-visionMeta AI | 0.76% | aa_slug=llama-3-2-instruct-11b-vision · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #694jamba-reasoning-3bAI21 Labs | 0.76% | aa_slug=jamba-reasoning-3b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #695Olmo-3-7B-ThinkAllen Institute for AI | 0.76% | aa_slug=olmo-3-7b-think · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #696nvidia-nemotron-nano-9b-v2NVIDIA | 0.76% | aa_slug=nvidia-nemotron-nano-9b-v2 · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #697lfm2-2-6bLiquid AI | 0.76% | aa_slug=lfm2-2-6b · variant=hard · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #698gemma-3n-e4bGoogle | 0.75% | aa_slug=gemma-3n-e4b · variant=v2.1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #699Nemotron 3.5 LightningNVIDIA | 0.51% | aa_slug=nemotron-3-5-lightning · variant=v4.0 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #700command-a-plusCohere | 0.51% | aa_slug=command-a-plus · variant=v4.0 · 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.