FMG-Bench - Guided Harness: leaderboard
Metric: Judge-panel score (0-100; guided default harness). Source: github.com. 14 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 94.58 |
| 2 | Kimi K2.6 | 94.14 |
| 3 | GPT-5.4 | 93.9 |
| 4 | Grok 4.20 | 93.85 |
| 5 | Qwen 3.6 Plus | 93.83 |
| 6 | DeepSeek V4 Pro | 92.81 |
| 7 | GLM-5.1 | 92.65 |
| 8 | Gemini 3.1 Pro (Preview) | 91.68 |
| 9 | Nemotron 3 Super | 90.99 |
| 10 | MiMo-V2.5-Pro | 90.93 |
| 11 | Mistral Large 3 | 89.92 |
| 12 | MiniMax-M2.7 | 88.95 |
| 13 | Seed 2.0 Lite | 88.35 |
| 14 | Llama 4 Maverick | 79.3 |
Interactive version: theaggregate.ai/benchmark?slug=fmg-bench-guided-harness · How It Works · Data refreshed daily, snapshot 2026-09-19.