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 - Software — leaderboard

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

Top models

#ModelScore
1GPT-5 Mini57.33
2GPT-5.254.1
3Qwen 3 32B48.47
4Qwen2.5-14B-Instruct-1M43.72
5Qwen 3 14B39.6
6Qwen 3 8B38.42
7Gemini 2.5 Flash38.38
8Claude 3.5 Haiku25.07

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