NPHardEval - TSP D — leaderboard
Metric: Accuracy (%). Source: huggingface.co. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 2 | 87.27 |
| 2 | Claude Instant | 72.36 |
| 3 | Mistral 7B Instruct (v0.1) | 62.73 |
| 4 | Yi 34B (Chat) | 43.09 |
| 5 | Qwen-14B-Chat | 41.64 |
| 6 | GPT-3.5 Turbo | 21.45 |
| 7 | GPT-4 Turbo | 14 |
| 8 | vicuna-13B-v1.3 | 2.91 |
| 9 | Phi-2 | 1.45 |
| 10 | Phi-1.5 | 0 |
| 11 | mpt-30B Instruct | 0 |
Interactive version: theaggregate.ai/benchmark?slug=nphardeval-tsp-d · How the rankings work · Data refreshed daily, snapshot 2026-07-22.