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 - SAS — leaderboard

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

Top models

#ModelScore
1GPT-4 Turbo100
2GPT-3.5 Turbo94.18
3Qwen-14B-Chat70.55
4Yi 34B (Chat)62
5Claude 244.55
6Claude Instant44.18
7Phi-219.09
8Mistral 7B Instruct (v0.1)14.91
9vicuna-13B-v1.311.27
10Phi-1.50
11mpt-30B Instruct0

Interactive version: theaggregate.ai/benchmark?slug=nphardeval-sas · 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.