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...

AMA-Bench - Game — leaderboard

Metric: Average Score (%). Source: huggingface.co. 24 models tracked.

Top models

#ModelScore
1GPT-5.281.13
2Qwen 3 14B54.3
3Qwen 3 32B53.55
4Claude 3.5 Haiku52.62
5GPT-5 Mini50.03
6Qwen2.5-14B-Instruct-1M50.01
7Qwen 3 8B46.84
8Gemini 2.5 Flash22.55

Interactive version: theaggregate.ai/benchmark?slug=ama-bench-game · 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.