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...

Vector Eval - GPQA-D — leaderboard

Metric: Accuracy (%). Source: huggingface.co. 11 models tracked.

Top models

#ModelScore
1O175.51
2O3 Mini73.65
3DeepSeek R170.45
4Claude 3.5 Sonnet60.98
5Gemini 1.5 Pro57.83
6GPT-4o51.01
7Mistral Large 2 (Jul)47.35
8Llama 3.1 70B Instruct43.18
9Gemini 1.5 Flash40.4
10GPT-4o Mini38.38
11Command-R+31.94

Interactive version: theaggregate.ai/benchmark?slug=vector-eval-gpqa-d · 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.