Official benchmarks map / RedlineBench
crosbylegal/gemini-4-argon is ranked first on the RedlineBench leaderboard with 59.5, 4.6% ahead of crosbylegal/claude-opus-5. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | crosbylegal/gemini-4-argon | crosbylegal | 59.5 |
| 2 | crosbylegal/claude-opus-5 | crosbylegal | 56.9 |
| 3 | crosbylegal/gpt-5.6-sol | crosbylegal | 56.2 |
| 4 | crosbylegal/gpt-5.6-luna | crosbylegal | 55.5 |
| 5 | crosbylegal/gemini-3.8-flash | crosbylegal | 55.2 |
| 6 | crosbylegal/claude-opus-5-5 | crosbylegal | 53.5 |
| 7 | crosbylegal/gemini-3.6-flash | crosbylegal | 51 |
| 8 | crosbylegal/gpt-5.5 | crosbylegal | 50.5 |
| 9 | moonshotai/Kimi-K3 | moonshotai | 49.3 |
| 10 | crosbylegal/gpt-5.6-terra | crosbylegal | 49.3 |
RedlineBench is a dataset that Hugging Face marks as an official benchmark. Its leaderboard is built automatically from the .eval_results files that model repositories publish, so entries are mostly self-reported by model authors and evaluation settings differ between submissions. A verified tag appears only where Hugging Face marks an entry as verified.
Original board: huggingface.co/datasets/crosbylegal/RedlineBench
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.