Skip to content

Benchmark

τ³-bench · Domain Unspecified

Scores are percentages. Higher is better.

Models measured
4
Scores recorded
4
Sources
1
IQ weight
No weight published

Score distribution

61.5%
Mean
63.2%
Median
3.3%
Std dev
58.3%
10th percentile
66%
90th percentile
58.3%
Min
58.3%66%
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Claude Opus 4.6SenseNova 6.7 Flash-Lite official benchmark chart · evaluated with GPT-5.2 as the user model · consistent with leaderboard settings· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.66%
2GLM 5SenseNova 6.7 Flash-Lite official benchmark chart · evaluated with GPT-5.2 as the user model · consistent with leaderboard settings· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.63.2%
3GPT 5.4SenseNova 6.7 Flash-Lite official benchmark chart · evaluated with GPT-5.2 as the user model · consistent with leaderboard settings· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.4%
4Step 3.5 FlashSenseNova 6.7 Flash-Lite official benchmark chart · evaluated with GPT-5.2 as the user model · consistent with leaderboard settings· Reported by SenseTime / OpenSenseNova· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.58.3%

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.