ResearchClawBench — leaderboard
ResearchClawBench evaluates model capability on agentic tasks from the linked upstream source with Average Score as the primary reported metric.
Metric: Overall (self-reported). Source: benchmarklist.com. Status: saturation imminent. 18 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 20.7 |
| 2 | Claude Opus 4.6 | 19.9 |
| 3 | Qwen 3.7 Max (Max) | 18.7 |
| 4 | GPT-5.4 | 18.4 |
| 5 | GLM-5.1 | 18.2 |
| 6 | Qwen 3.6 Plus | 18 |
| 7 | Gemini 3.5 Flash | 17.9 |
| 8 | DeepSeek V4 Pro | 17.1 |
| 9 | GPT-5.5 | 17 |
| 10 | MiMo-V2.5 | 16.9 |
| 11 | MiMo-V2-Pro | 15.3 |
| 12 | Qwen 3.5 397B A17B | 14.2 |
| 13 | Grok 4.1 | 13.5 |
| 14 | Gemini 3.1 Pro (Preview) | 13.3 |
| 15 | Grok 4.3 | 12.4 |
Interactive version: theaggregate.ai/benchmark?slug=researchclawbench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.