Skip to content

Benchmark

τ³-Bench · Banking Knowledge · Atria run

Scores are percentages. Higher is better.

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
37.1%55.2%
The band covers the middle 80% of scores. The line marks the median.

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

#ModelScore
1Qwen3.8 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%
2Claude 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%
3GPT-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%
4DeepSeek 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%
5GLM 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%
6Kimi 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%

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.