Galileo Agent Leaderboard: leaderboard
Galileo AI's leaderboard evaluating LLMs as autonomous agents across task completion benchmarks. Measures agent quality metrics including task success, accuracy, and grounding.
Metric: Avg Accuracy (%). Source: huggingface.co. Saturation forecast: Around January 2027. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 62 | #248 |
| 2 | Mistral Medium 3.1 | 61 | #408 |
| 3 | GPT-4.1 Mini | 56 | #355 |
| 4 | Claude Sonnet 4 (20250514) | 55 | #213 |
| 5 | Kimi K2 | 53 | #243 |
| 6 | Qwen 3 235B A22B 2507 Instruct | 53 | #300 |
| 7 | Qwen 2.5 72B Instruct | 51 | #454 |
| 8 | Gemini 2.5 Flash Lite | 47 | #422 |
| 9 | GLM 4.5 Air | 44 | #392 |
| 10 | Gemini 2.5 Pro | 43 | #152 |
| 11 | Grok 4 | 42 | #181 |
| 12 | DeepSeek V3 | 40 | #321 |
| 13 | Gemini 2.5 Flash | 38 | #245 |
| 14 | GPT-4.1 Nano | 38 | #731 |
| 15 | Qwen 3 235B A22B 2507 (Thinking) | 34 | #260 (Qwen 3 235B A22B 2507) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=galileo-agent-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.