Benchmark
τ²-bench Retail
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 14
- Scores recorded
- 17
- Sources
- 1
- IQ weight
- 1.75
Score distribution
- 84.1%
- Mean
- 85.5%
- Median
- 6.8%
- Std dev
- 79.5%
- 10th percentile
- 90.8%
- 90th percentile
- 62.8%
- Min
This benchmark has a weight of 1.75 for chat models, measured over 14 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 91.9% |
| 2 | Claude Sonnet 4.6adaptive thinking · max effort · 10 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 91.7% |
| 3 | Gemini 3.1 Pro Preview· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 90.8% |
| 4 | Claude Opus 4.5Claude Opus 4.1 user simulator · prompt addendum· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.9% |
| 5 | Claude Opus 4.5Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 88.9% |
| 6 | Gemma 4 31B ITGemma 4 Technical Report · Table 5 · thinking mode unless noted· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.4% |
| 7 | Claude Sonnet 4.5Claude Opus 4.1 user simulator · prompt addendum· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.2% |
| 8 | Claude Sonnet 4.5Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 86.2% |
| 9 | Gemma 4 26B A4BGemma 4 Technical Report · Table 5 · thinking mode unless noted· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.5% |
| 10 | Gemini 3 Pro PreviewOpus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 85.3% |
| 11 | Claude Haiku 4.5launch-page setting· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 83.2% |
| 12 | GPT 5.2Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82% |
| 13 | GPT 5.2xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82% |
| 14 | DeepSeek V3.2Thinking mode · temperature 1.0 · 128K context · model itself as user agent· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 81.1% |
| 15 | MiMo V2 FlashDeepSeek-V3.2 user agent · Retail· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 79.5% |
| 16 | Nova 2 LiteAmazon Nova 2 Lite official launch chart / technical report · Verified · avg@3, v1· Reported by Amazon Web Services, Amazon AGI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76.5% |
| 17 | Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · default prompt· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.8% |