SEAL - Agentic Tool Use (Chat) — leaderboard
Scale SEAL evaluation of tool use in conversational settings, testing ability to select and chain tools for user requests.
Metric: Score. Source: scale.com. Status: saturation imminent. 35 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O3 Mini (High) | 63.45 |
| 2 | Gemini 2.5 Pro (03-25) | 62.43 |
| 3 | O3 Mini (Medium) | 62.42 |
| 4 | O1 Pro | 61.42 |
| 5 | DeepSeek R1 | 60.91 |
| 6 | O1 (2024-12-17) | 60.41 |
| 7 | DeepSeek V3 | 58.55 |
| 8 | Gemini 2.0 Pro (Preview 02-05) | 57.86 |
| 9 | Gemini 2.0 Flash (Thinking) | 57.36 |
| 10 | GPT-4o (2024-08-06) | 56.85 |
| 11 | GPT-4.5 (Preview) | 56.34 |
| 12 | Claude 3.7 Sonnet (20250219) | 56.25 |
| 13 | Claude 3.5 Sonnet (20240620) | 56.06 |
| 14 | Claude 3.7 Sonnet (Thinking) | 55.32 |
| 15 | O1 Preview | 55.1 |
Interactive version: theaggregate.ai/benchmark?slug=seal-agentic-tool-use-chat · How the rankings work · Data refreshed daily, snapshot 2026-07-22.