Skip to content

The Aggregate

Unified LLM rankings, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Guesswork Metrics
The Aggregate
Loading data...

NPHardEval - TSP — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 12 models tracked.

Top models

#ModelScore
1GPT-4 Turbo8.18
2Claude 22
3Claude Instant2
4GPT-3.5 Turbo1.64
5Qwen-14B-Chat1.27
6Phi-21.09
7Yi 34B (Chat)0.55
8Phi-1.50
9Mistral 7B Instruct (v0.1)0
10vicuna-13B-v1.30
11mpt-30B Instruct0

Interactive version: theaggregate.ai/benchmark?slug=nphardeval-tsp · How the rankings work · Data refreshed daily, snapshot 2026-07-22.

Built by Mikhail Doroshenko — AI researcher, co-author of Humanity’s Last Exam. Independent project; no affiliation with any AI lab.