SEAL - Agentic Tool Use (Enterprise): leaderboard
Scale SEAL evaluation of multi-tool reasoning in enterprise scenarios with 485 prompts testing complex tool composition.
Metric: Score. Source: scale.com. Saturation forecast: Estimated already saturated. 35 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | O1 (2024-12-17) | 70.14 | #149 |
| 2 | Gemini 2.5 Pro (Preview 03-25) | 68.75 | #123 |
| 3 | O1 Pro | 67.01 | #228 |
| 4 | O1 Preview | 66.43 | #193 |
| 5 | DeepSeek R1 | 65.27 | #251 |
| 6 | Claude 3.7 Sonnet (Thinking) | 65.27 | #249 (Claude 3.7 Sonnet) |
| 7 | O3 Mini (High) | 65.27 | #272 (O3 Mini) |
| 8 | Claude 3.7 Sonnet (20250219) | 64.93 | #201 |
| 9 | O3 Mini (Medium) | 64.93 | #272 (O3 Mini) |
| 10 | GPT-4o (2024-05-13) | 64.58 | #325 |
| 11 | GPT-4.5 (Preview) | 63.76 | #244 |
| 12 | Gemini 2.0 Flash (Thinking) | 63.19 | #342 (Gemini 2.0 Flash) |
| 13 | DeepSeek V3 | 62.5 | #321 |
| 14 | Gemini 2.0 Pro (Preview 02-05) | 61.45 | #307 |
| 15 | GPT-4 Turbo (Preview) | 60.76 | #397 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=seal-agentic-tool-use-enterprise · How It Works · Data refreshed daily, snapshot 2026-10-20.