Official benchmarks map / ifstruct-v1.0
FINAL-Bench/Darwin-180B-RSI is ranked first on the ifstruct-v1.0 leaderboard with 98.95, 6.1% ahead of InternScience/Agents-A1. Read live from the Hugging Face API on November 6, 2026.
| # | Model | Organization | Score |
|---|---|---|---|
| 1 | FINAL-Bench/Darwin-180B-RSI | FINAL-Bench | 98.95 |
| 2 | InternScience/Agents-A1 | InternScience | 93.25 |
| 3 | openai/gpt-oss-20b | openai | 91.95 |
| 4 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | nvidia | 86.8 |
| 5 | ibm-granite/granite-4.1-8b | ibm-granite | 68.45 |
| 6 | ibm-granite/granite-4.0-h-tiny | ibm-granite | 38.75 |
ifstruct-v1.0 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/LiquidAI/ifstruct-v1.0
Part of the Hugging Face official benchmarks map by QuantID. Unofficial. Not affiliated with or endorsed by Hugging Face.