A benchmark that evaluates whether language models can use tools to complete complex tasks in realistic environments.
Browse the latest scores, model modes, release dates, and parameter sizes for Tool Decathlon.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
| Rank | Model | License | |||
|---|---|---|---|---|---|
 Muse Spark 1.1 Thinking EnabledTools | 75.60 | 2026-07-09 | Unknown | Closed | |
 Kimi K2.6 Thinking EnabledTools | 50.00 | 2026-04-20 | 1000B | Free Commercial | |
 Hy3 Thinking Level · HighTools | 48.50 | 2026-07-06 | 295B | Free Commercial | |
4 |  GPT-5.4 mini Thinking Level · Extra HighTools | 42.90 | 2026-03-17 | Unknown | Closed |
5 |  GLM 5.1 Thinking EnabledTools | 40.70 | 2026-03-27 | 75.4B | Free Commercial |
6 |  Qwen 3.6 Plus Preview Thinking EnabledTools | 39.80 | 2026-03-31 | Unknown | Closed |
7 | Qwen3.5-397B-A17B Thinking EnabledTools | 38.30 | 2026-02-16 | 39.7B | Free Commercial |
8 | GPT-5.4 nano Thinking Level · Extra HighTools | 35.50 | 2026-03-17 | Unknown | Closed |
9 | Qwen3.6-35B-A3B Thinking Enabled | 26.90 | 2026-04-16 | 35B | Free Commercial |
