τ²-bench
Can the model plan, use tools, and finish a multi-step task?
Agents8 ranked models11 reported values2 reportsHigher is better
Top rankings
One row per model, using its best reported score across effort settings.
| Rank | Model | Best score | Best reported setting |
|---|---|---|---|
| 1 | Claude Opus 4.6Anthropic | 99.3% | max effortGoogle report2 values · 2 reportsFeb 19, 2026 · source |
| 2 | Gemini 3.1 ProGoogle | 99.3% | high effortGoogle report1 value · 1 reportFeb 19, 2026 · source |
| 3 | GPT-5.2OpenAI | 98.7% | xhigh effortGoogle report2 values · 2 reportsFeb 19, 2026 · source |
| 4 | Claude Opus 4.5Anthropic | 98.2% | Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source |
| 5 | Gemini 3 ProGoogle | 98.0% | high effortGoogle report2 values · 2 reportsFeb 19, 2026 · source |
| 6 | Claude Sonnet 4.6Anthropic | 97.9% | max effortGoogle report1 value · 1 reportFeb 19, 2026 · source |
| 7 | MiniMax M2.5MiniMax | 97.8% | Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source |
| 8 | MiniMax M2.1MiniMax | 87.0% | Reported configurationMiniMax report1 value · 1 reportFeb 12, 2026 · source |
Effort curve
Every sourced cost-linked effort value for this exact version. Lines connect complete sweeps only.
No cost-linked effort sweep for this version.
Definition and comparison boundarypublic methodology
Can the model plan, use tools, and finish a multi-step task?
Agentic execution across tools, environments, or long-running workflows. Higher is better. The value is the percentage reported in this lab's table.
Harness, tools, prompts, attempt count, and benchmark version can materially change the result. Compare within one reporting context.
Method / source