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. Status: saturation imminent. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 62 |
| 2 | Mistral Medium 3.1 | 61 |
| 3 | GPT-4.1 Mini | 56 |
| 4 | Claude Sonnet 4 (20250514) | 55 |
| 5 | Kimi K2 | 53 |
| 6 | Qwen 3 235B A22B 2507 Instruct | 53 |
| 7 | Qwen 2.5 72B Instruct | 51 |
| 8 | Gemini 2.5 Flash Lite | 47 |
| 9 | GLM 4.5 Air | 44 |
| 10 | Gemini 2.5 Pro | 43 |
| 11 | Grok 4 | 42 |
| 12 | DeepSeek V3 | 40 |
| 13 | GPT-4.1 Nano | 38 |
| 14 | Gemini 2.5 Flash | 38 |
| 15 | Qwen 3 235B A22B (Thinking) | 34 |
Interactive version: theaggregate.ai/benchmark?slug=galileo-agent-leaderboard · How the rankings work · Data refreshed daily, snapshot 2026-07-22.