NPHardEval - KSP — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4 Turbo | 18.73 |
| 2 | Claude 2 | 0.18 |
| 3 | GPT-3.5 Turbo | 0 |
| 4 | Phi-1.5 | 0 |
| 5 | Phi-2 | 0 |
| 6 | Mistral 7B Instruct (v0.1) | 0 |
| 7 | vicuna-13B-v1.3 | 0 |
| 8 | mpt-30B Instruct | 0 |
| 9 | Yi 34B (Chat) | 0 |
| 10 | Qwen-14B-Chat | 0 |
| 11 | Claude Instant | 0 |
Interactive version: theaggregate.ai/benchmark?slug=nphardeval-ksp · How the rankings work · Data refreshed daily, snapshot 2026-07-22.