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 - Text2SQL — leaderboard

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

Top models

#ModelScore
1GPT-5 Mini83.44
2GPT-5.283.14
3Gemini 2.5 Flash62.57
4Qwen 3 32B45.61
5Qwen2.5-14B-Instruct-1M38.44
6Qwen 3 14B37.78
7Claude 3.5 Haiku35.23
8Qwen 3 8B33.62

Interactive version: theaggregate.ai/benchmark?slug=ama-bench-text2sql · 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.