Skip to main content
Evaluation sources/τ³-Banking
ParticipatingProfessional work

τ³-Banking

Mercor · Public model evaluation results from τ³-Banking.

Official evaluation
Source description

This source measures concrete delivery performance in Professional work; raw scores are shown separately from the normalized capability score.

Limitation: Different versions, reasoning settings, and test sets may change scores; read them with the data date.

How it is used

Participating sources affect capability scores; reference, cross-reference, and observing sources are for comparison and verification only.

Model results from this source

Gemini 4 Argon58.173.22026-11-05
Claude Fable 5.255.769.82026-11-10
Gemini 4 Carbon55.769.82026-11-11
Claude Opus 5.55568.72026-11-05
Claude Fable 5.15467.32026-11-05
Claude Sonnet 5.55467.32026-11-05
Muse Spark 1.352.264.72026-11-05
Muse Wonder51.964.22026-11-05
Gemini 3.8 Flash48.859.72026-11-05
Qwen3.8 Max46.756.62026-11-05
GPT-6 Astra46.756.62026-11-05
Grok 4.645.755.22026-11-05
Claude Opus 54452.72026-11-05
GPT-5.6 Sol4351.22026-11-05
GPT-6 Sol4351.22026-11-05
Claude Haiku 5.54351.22026-11-05
GPT-6.1 Sol4351.22026-11-05
DeepSeek V4.1 Flash 101741.649.22026-11-05
GLM 5.340.547.62026-11-05
GPT-6 Luna40.247.22026-11-05
DeepSeek V4 Pro 081340.247.22026-11-05
GPT-5.6 Terra38.845.12026-11-05
DeepSeek V4.1 Flash37.843.72026-11-05
GLM-5.3 Flash37.843.72026-11-05
GLM-5.3 Flash37.843.72026-10-18
GLM-5.3 Flash37.843.72026-10-17
GPT-6.1 Terra37.142.62026-11-05
MiniMax M3.1 Flash36.141.22026-11-05
GPT-5.6 Luna35.740.62026-11-05
Kimi K334.739.12026-11-05
Grok 4.732.636.12026-11-05
MiniMax-M32119.22026-11-05
Gemini 3.5 Flash Lite18.615.72026-11-05
Inkling15.511.22026-11-05

Frequently asked questions