Results
| 1 | GLM 5.3 Flash (max) | |
|---|---|---|
| 2 | Kimi K3 (max) | |
| 3 | Claude Opus 4.8 (max) | |
| 4 | Muse Spark 1.2 (xhigh) | |
| 5 | DeepSeek V4 Pro 0813 (max) | |
| 6 | GPT-5.5 (xhigh) | |
| 7 | Gemini 3.5 Flash (high) |
Public leaderboard · Agents, tool use & computer use
Tests AI agents on long, multi-step tasks across many everyday software tools.
Long-horizon tasks that span many real applications and tools, checked by execution-based verification.
Pass@1 (%), with margin — higher is better.
| 1 | GLM 5.3 Flash (max) | |
|---|---|---|
| 2 | Kimi K3 (max) | |
| 3 | Claude Opus 4.8 (max) | |
| 4 | Muse Spark 1.2 (xhigh) | |
| 5 | DeepSeek V4 Pro 0813 (max) | |
| 6 | GPT-5.5 (xhigh) | |
| 7 | Gemini 3.5 Flash (high) |
Note: as_of is the most recent entry date shown; page has no explicit update date.
Source: Toolathlon team · toolathlon.xyz · results as of 2026-08-30 · retrieved 2026-11-17