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 - Embodied AI — leaderboard

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

Top models

#ModelScore
1GPT-5.256.44
2Qwen 3 32B48.19
3GPT-5 Mini41.31
4Gemini 2.5 Flash39.78
5Qwen 3 14B37.99
6Qwen2.5-14B-Instruct-1M33.16
7Claude 3.5 Haiku30
8Qwen 3 8B29.45

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