ProLLM - StackEval: leaderboard
ProLLM benchmark evaluating LLMs on Stack Overflow coding questions. Measures acceptance rate on real developer problems across languages and frameworks.
Metric: Score (%). Source: www.prollm.ai. Saturation forecast: Estimated already saturated. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 | 98.6 | #248 |
| 2 | GPT-4.1 Mini | 98.4 | #355 |
| 3 | DeepSeek V3 | 97.6 | #321 |
| 4 | O3 Mini (Medium) | 97.4 | #272 (O3 Mini) |
| 5 | GPT-4.5 | 97.3 | #274 |
| 6 | O3 Mini (High) | 97.1 | #272 (O3 Mini) |
| 7 | GPT-4o | 96.1 | #343 |
| 8 | DeepSeek R1 | 95.6 | #251 |
| 9 | GPT-4.1 Nano | 95.2 | #731 |
| 10 | Llama 3.1 Nemotron 70B Instruct | 94.6 | #554 |
| 11 | GPT-4 Turbo | 94.3 | #404 |
| 12 | Gemini 1.5 Pro | 94.3 | #445 |
| 13 | Gemini 2.0 Flash | 94.2 | #342 |
| 14 | MiniMax-Text-01 | 92.8 | #513 |
| 15 | Llama 4 Maverick Instruct | 92.3 | #456 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=prollm-stackeval · How It Works · Data refreshed daily, snapshot 2026-10-20.