BenchmarkActivecategory · agentic
τ²-bench
dual-control tool-agent-user interaction (telecom, retail, airline)
quality51
Updated 9 h ago · first seen 11 Sept 2026
bench_01M293SPH15XRN6880KKHSKM5P
- Metric
- pass^1 · %
- Direction
- Higher is better
- Results
- 440
- Leader
- Z.ai GLM 5.2 99.12%
Score history · gpt-4.1-mini 1 row
Not enough history to chart — a single observation (52.92% on 11 Sept 2026). Rows under different configurations count separately; the list below shows each one.
- 52.92%aa_slug=gpt-4-1-mini · evaluator=Artificial Analysis · index_version=4.311 Sept 2026
Leaderboard 440 current results
Select models with +, then open Compare.
| # | Model | Score | Config | Evaluated | Source | Actions |
|---|---|---|---|---|---|---|
| #101qwen3-6-35b-a3b-non-reasoningAlibaba Group | 85.09% | aa_slug=qwen3-6-35b-a3b-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #102Claude Opus 4.6Anthropic | 84.8% | aa_slug=claude-opus-4-6 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #103gpt-5-6-sol-xhighOpenAI | 84.8% | aa_slug=gpt-5-6-sol-xhigh · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #104gpt-5OpenAI | 84.8% | aa_slug=gpt-5 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #105gpt-5.2OpenAI | 84.8% | aa_slug=gpt-5-2 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #106MiniMax M2.7MiniMax | 84.8% | aa_slug=minimax-m2-7 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #107qwen3-5-122b-a10b-non-reasoningAlibaba Group | 84.5% | aa_slug=qwen3-5-122b-a10b-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #108qwen3-5-omni-flashAlibaba Group | 84.5% | aa_slug=qwen3-5-omni-flash · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #109gpt-5 (low)OpenAI | 84.21% | aa_slug=gpt-5-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #110mimo-v2-flashXiaomi | 83.92% | aa_slug=mimo-v2-flash · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #111qwen3-5-397b-a17b-non-reasoningAlibaba Group | 83.92% | aa_slug=qwen3-5-397b-a17b-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #112gpt-5-5-lowOpenAI | 83.92% | aa_slug=gpt-5-5-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #113ernie-5-0-thinking-previewBaidu | 83.92% | aa_slug=ernie-5-0-thinking-preview · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #114Qwen3 Max ThinkingQwen | 83.63% | aa_slug=qwen3-max-thinking · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #115qwen3-max-thinking-previewAlibaba Group | 83.63% | aa_slug=qwen3-max-thinking-preview · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #116gpt-5.4-miniOpenAI | 83.33% | aa_slug=gpt-5-4-mini · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #117gpt-5-6-sol-highOpenAI | 83.33% | aa_slug=gpt-5-6-sol-high · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #118Nemotron 3 UltraNVIDIA | 83.33% | aa_slug=nvidia-nemotron-3-ultra-550b-a55b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #119GPT-5.1-CodexOpenAI | 83.04% | aa_slug=gpt-5-1-codex · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #120minicpm5-1b-non-reasoningOpenBMB | 82.46% | aa_slug=minicpm5-1b-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #121gpt-5.1OpenAI | 81.87% | aa_slug=gpt-5-1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #122nex-n2-proNex AGI | 81.58% | aa_slug=nex-n2-pro · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #123qwen3-5-2b-non-reasoningAlibaba Group | 81.58% | aa_slug=qwen3-5-2b-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #124kimi-k2-5-non-reasoningMoonshot AI | 81.29% | aa_slug=kimi-k2-5-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #125gpt-5-6-sol-mediumOpenAI | 80.99% | aa_slug=gpt-5-6-sol-medium · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #126minicpm5-1bOpenBMB | 80.99% | aa_slug=minicpm5-1b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #127tri-21b-think-v0-5Trillion Labs | 80.99% | aa_slug=tri-21b-think-v0-5 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #128o3OpenAI | 80.7% | aa_slug=o3 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #129command-a-plusCohere | 80.7% | aa_slug=command-a-plus · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #130nova-2-0-omni-reasoning-mediumAmazon Web Services | 80.41% | aa_slug=nova-2-0-omni-reasoning-medium · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #131gpt-5-6-terra-xhighOpenAI | 80.41% | aa_slug=gpt-5-6-terra-xhigh · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #132Gemini 3 Flash PreviewGoogle | 80.41% | aa_slug=gemini-3-flash-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #133Claude Sonnet 4.6Anthropic | 79.53% | aa_slug=claude-sonnet-4-6 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #134longcat-flash-liteLongCat | 79.53% | aa_slug=longcat-flash-lite · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #135Qwen3 Coder NextQwen | 79.53% | aa_slug=qwen3-coder-next · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #136DeepSeek V3DeepSeek | 78.95% | aa_slug=deepseek-v3-2 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #137claude-sonnet-4-6-non-reasoning-low-effortAnthropic | 78.95% | aa_slug=claude-sonnet-4-6-non-reasoning-low-effort · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #138gpt-5-6-terra-highOpenAI | 78.36% | aa_slug=gpt-5-6-terra-high · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #139claude-4-5-sonnet-thinkingAnthropic | 78.07% | aa_slug=claude-4-5-sonnet-thinking · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #140exaone-4-5-33bLG AI Research | 78.07% | aa_slug=exaone-4-5-33b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #141GLM 4.6Z.ai (Zhipu AI) | 76.9% | aa_slug=glm-4-6 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #142gpt-5.4-nanoOpenAI | 76.02% | aa_slug=gpt-5-4-nano · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #143gpt-5-6-sol-lowOpenAI | 76.02% | aa_slug=gpt-5-6-sol-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #144nova-2-0-lite-reasoning-mediumAmazon Web Services | 75.73% | aa_slug=nova-2-0-lite-reasoning-medium · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #145claude-sonnet-4-6-adaptiveAnthropic | 75.73% | aa_slug=claude-sonnet-4-6-adaptive · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #146Grok Build 0.1xAI | 75.73% | aa_slug=grok-code-fast-1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #147grok-4SpaceXAI | 74.85% | aa_slug=grok-4 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #148gpt-5-4-lowOpenAI | 74.56% | aa_slug=gpt-5-4-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #149k-exaoneLG AI Research | 74.27% | aa_slug=k-exaone · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #150gpt-5-2-mediumOpenAI | 74.27% | aa_slug=gpt-5-2-medium · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #151Qwen3 MaxQwen | 74.27% | aa_slug=qwen3-max · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #152claude-opus-4-7-non-reasoningAnthropic | 73.98% | aa_slug=claude-opus-4-7-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #153Kimi K2 0905Moonshot AI | 73.39% | aa_slug=kimi-k2-0905 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #154Claude Opus 4Anthropic | 73.39% | aa_slug=claude-4-opus-thinking · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #155gpt-5-6-terra-mediumOpenAI | 72.81% | aa_slug=gpt-5-6-terra-medium · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #156nova-2-0-lite-reasoningAmazon Web Services | 72.81% | aa_slug=nova-2-0-lite-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #157mimo-v2-5-pro-non-reasoningXiaomi | 72.51% | aa_slug=mimo-v2-5-pro-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #158nova-2-0-lite-reasoning-lowAmazon Web Services | 71.93% | aa_slug=nova-2-0-lite-reasoning-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #159nova-2-0-proAmazon Web Services | 71.64% | aa_slug=nova-2-0-pro · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #160claude-4-1-opus-thinkingAnthropic | 71.37% | aa_slug=claude-4-1-opus-thinking · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #161gpt-5-mini-mediumOpenAI | 71.05% | aa_slug=gpt-5-mini-medium · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #162Mercury 2Inception | 70.76% | aa_slug=mercury-2 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #163Claude Sonnet 4.5Anthropic | 70.47% | aa_slug=claude-4-5-sonnet · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #164glm-4-6-reasoningZ.ai (Zhipu AI) | 70.47% | aa_slug=glm-4-6-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #165grok-4-20-0309-non-reasoningSpaceXAI | 69.59% | aa_slug=grok-4-20-0309-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #166gpt-5-5-non-reasoningOpenAI | 69.3% | aa_slug=gpt-5-5-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #167apriel-v1-6-15b-thinkerServiceNow | 69.3% | aa_slug=apriel-v1-6-15b-thinker · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #168Qwen3.5-2BQwen | 69.01% | aa_slug=qwen3-5-2b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #169apriel-v1-5-15b-thinkerServiceNow | 68.42% | aa_slug=apriel-v1-5-15b-thinker · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #170gpt-5-miniOpenAI | 68.42% | aa_slug=gpt-5-mini · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #171gemini-3-pro-lowGoogle | 68.13% | aa_slug=gemini-3-pro-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #172nova-2-0-omni-reasoning-lowAmazon Web Services | 67.84% | aa_slug=nova-2-0-omni-reasoning-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #173Nemotron 3 SuperNVIDIA | 67.84% | aa_slug=nvidia-nemotron-3-super-120b-a12b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #174hy3-non-reasoningTencent | 67.54% | aa_slug=hy3-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #175gpt-5-minimalOpenAI | 66.96% | aa_slug=gpt-5-minimal · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #176gpt-oss-120bOpenAI | 65.79% | aa_slug=gpt-oss-120b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #177grok-4-3-non-reasoningSpaceXAI | 65.79% | aa_slug=grok-4-3-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #178grok-4-fast-reasoningSpaceXAI | 65.79% | aa_slug=grok-4-fast-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #179gemma-4-31b-non-reasoningGoogle | 65.5% | aa_slug=gemma-4-31b-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #180qwen3-5-0-8b-non-reasoningAlibaba Group | 65.2% | aa_slug=qwen3-5-0-8b-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #181claude-4-sonnet-thinkingAnthropic | 64.62% | aa_slug=claude-4-sonnet-thinking · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #182grok-4-1-fastSpaceXAI | 63.74% | aa_slug=grok-4-1-fast · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #183grok-4-fastSpaceXAI | 63.74% | aa_slug=grok-4-fast · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #184hypernova-60bMultiverse Computing | 63.16% | aa_slug=hypernova-60b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #185GPT-5.1-Codex MiniOpenAI | 62.87% | aa_slug=gpt-5-1-codex-mini · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #186o1OpenAI | 62.57% | aa_slug=o1 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #187nova-2-0-liteAmazon Web Services | 61.99% | aa_slug=nova-2-0-lite · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #188Kimi K2 0711Moonshot AI | 61.11% | aa_slug=kimi-k2 · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #189gpt-5-6-terra-lowOpenAI | 60.53% | aa_slug=gpt-5-6-terra-low · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #190gpt-oss-20bOpenAI | 60.23% | aa_slug=gpt-oss-20b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #191grok-4.20-0309-non-reasoningxAI | 59.94% | aa_slug=grok-4-20-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #192Gemma 4 31BGoogle | 59.94% | aa_slug=gemma-4-31b · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #193k-exaone-non-reasoningLG AI Research | 59.06% | aa_slug=k-exaone-non-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #194gemini-3-5-flash-minimalGoogle | 58.77% | aa_slug=gemini-3-5-flash-minimal · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #195doubao-seed-codeByteDance | 58.19% | aa_slug=doubao-seed-code · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #196o4-miniOpenAI | 55.56% | aa_slug=o4-mini · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #197claude-3-7-sonnet-thinkingAnthropic | 54.68% | aa_slug=claude-3-7-sonnet-thinking · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #198claude-4-5-haiku-reasoningAnthropic | 54.68% | aa_slug=claude-4-5-haiku-reasoning · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #199Gemini 2.5 ProGoogle | 54.09% | aa_slug=gemini-2-5-pro · evaluator=Artificial Analysis · index_version=4.3 | — (obs. 11 Sept 2026) | artificialanalysis.aiT2 | History | |
| #200qwen3-vl-235b-a22b-reasoningAlibaba Group | 54.09% | aa_slug=qwen3-vl-235b-a22b-reasoning · 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.
Definition
- Category
- agentic
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Task
- dual-control tool-agent-user interaction (telecom, retail, airline)
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Metric
- pass^1 · %
Source:AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2observed 9 h agomedium
- Direction
- Higher is better
- Paper
- https://arxiv.org/abs/2506.07982
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, gemma-4-12B, grok-4-3-low, GPT-5.1-Codex Mini, Qwen3 Coder Next, KAT-Coder-Pro V2, nova-2-0-lite-reasoning-medium, lfm2-24b-a2b +432(440 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 |
|---|---|---|---|---|---|
| pass^1 | → current | current | AI Atlas curated registry (YAML, versioned in git, every entry carries its source URL)T2 | medium | curated |
Paperpaper1
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| https://arxiv.org/abs/2506.07982 | → 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 |
|---|---|---|---|---|---|
| dual-control tool-agent-user interaction (telecom, retail, airline) | → 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 |
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 | 8 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.