ClinSQL - Diagnostic Procedures: leaderboard
Metric: Execution Score (%). Source: arxiv.org. Saturation forecast: Around December 2026. 22 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 75.64 |
| 2 | GPT-4.1 | 75.44 |
| 3 | GPT-5 Chat | 75.38 |
| 4 | Gemini 2.5 Pro | 72.36 |
| 5 | DeepSeek V3.1 | 71.46 |
| 6 | DeepSeek R1 0528 | 70.16 |
| 7 | Qwen 3 235B A22B 2507 Instruct | 69.55 |
| 8 | Gemini 2.5 Flash | 67.1 |
| 9 | O4 Mini (2025-04-16) | 66.04 |
| 10 | Qwen 3 Coder 480B A35B Instruct | 63.86 |
| 11 | Grok 4 Fast (Reasoning) | 63.81 |
| 12 | GPT-5 Nano | 58.29 |
| 13 | Qwen 3 Next 80B A3B Instruct | 57.37 |
| 14 | Llama 4 Maverick Instruct | 51.65 |
| 15 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 47.17 |
Interactive version: theaggregate.ai/benchmark?slug=clinsql-diagnostic-procedures · How It Works · Data refreshed daily, snapshot 2026-09-25.