Smolagents - GAIA (Tool Calling): leaderboard
Metric: Accuracy (%). Source: huggingface.co. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 70B Instruct | 18.75 |
| 2 | Qwen 2.5 Coder 32B Instruct | 18.75 |
| 3 | GPT-4o | 15.63 |
| 4 | DeepSeek R1 Distill Qwen 32B | 12.5 |
| 5 | Llama 3.1 8B Instruct | 6.25 |
| 6 | Claude 3.5 Sonnet | 0 |
Interactive version: theaggregate.ai/benchmark?slug=smolagents-gaia-tool-calling · How It Works · Data refreshed daily, snapshot 2026-10-09.