TraceEval: leaderboard
Metric: Average F1 (self-reported). Source: benchmarklist.com. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.6 | 72.9 |
| 2 | Claude Sonnet 4.6 | 64.5 |
| 3 | DeepSeek V3.2 | 62.1 |
| 4 | GPT-5.4 | 60 |
| 5 | GPT-5.4 Mini | 56.5 |
| 6 | Qwen 2.5 Coder 32B Instruct | 46.6 |
| 7 | Llama 3.3 70B Instruct | 44.3 |
| 8 | Gemini 3.1 Pro (Preview) | 31.8 |
| 9 | Qwen 2.5 Coder 7B Instruct | 27.1 |
| 10 | Qwen2.5-Coder-1.5B-Instruct | 9.5 |
Interactive version: theaggregate.ai/benchmark?slug=traceeval · How It Works · Data refreshed daily, snapshot 2026-09-05.