Benchmark
τ³-Bench · Banking Knowledge · Atria run
Scores are percentages. Higher is better.
Benchmark sourceScores from BenchBoard docs.
- Models measured
- 6
- Scores recorded
- 6
- Sources
- 1
- IQ weight
- 0.16
Score distribution
- 45.4%
- Mean
- 46.9%
- Median
- 5.9%
- Std dev
- 40.2%
- 10th percentile
- 55.2%
- 90th percentile
- 37.1%
- Min
This benchmark has a weight of 0.16 for chat models, measured over 6 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 | Qwen3.8 MaxAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 97 Banking Knowledge tasks · modified Tau2/Tau3 runner from commit a2c0247 · alltools BM25/dense/shell retrieval · GPT-5.2 low judge and simulator · 200-step limit· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.2% |
| 2 | Claude Opus 5Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 97 Banking Knowledge tasks · modified Tau2/Tau3 runner from commit a2c0247 · alltools BM25/dense/shell retrieval · GPT-5.2 low judge and simulator · 200-step limit· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 48.7% |
| 3 | GPT-5.6 SolAtria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 97 Banking Knowledge tasks · modified Tau2/Tau3 runner from commit a2c0247 · alltools BM25/dense/shell retrieval · GPT-5.2 low judge and simulator · 200-step limit· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 46.9% |
| 4 | DeepSeek V4 Pro 0813Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 97 Banking Knowledge tasks · modified Tau2/Tau3 runner from commit a2c0247 · alltools BM25/dense/shell retrieval · GPT-5.2 low judge and simulator · 200-step limit· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.3% |
| 5 | GLM 5.3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 97 Banking Knowledge tasks · modified Tau2/Tau3 runner from commit a2c0247 · alltools BM25/dense/shell retrieval · GPT-5.2 low judge and simulator · 200-step limit· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 40.2% |
| 6 | Kimi K3Atria Dawn Preview official card / report Table 1 · published comparison run · model snapshots and reasoning tiers not specified unless stated · 97 Banking Knowledge tasks · modified Tau2/Tau3 runner from commit a2c0247 · alltools BM25/dense/shell retrieval · GPT-5.2 low judge and simulator · 200-step limit· Reported by Shanghai AI Laboratory· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.1% |