LLM2014 Code 2025-09 - Java — leaderboard
Metric: Score. Source: raw.githubusercontent.com. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini (High) | 9 |
| 2 | O4 Mini (High) | 7.89 |
| 3 | Claude Sonnet 4 (Thinking) | 7.13 |
| 4 | Gemini 2.5 Flash (Thinking) | 6.97 |
| 5 | Gemini 2.5 Pro | 6.49 |
| 6 | Grok 4 | 6.22 |
| 7 | Claude Sonnet 4 | 5.57 |
| 8 | Kimi K2 (0711) | 5.1 |
| 9 | DeepSeek V3.1 (Thinking) | 5.01 |
| 10 | GPT-OSS-120B (High) | 4.87 |
| 11 | Grok Code Fast 1 | 4.75 |
| 12 | Qwen 3 235B A22B 2507 Instruct | 4.32 |
| 13 | GPT-OSS-20B (High) | 3.92 |
| 14 | DeepSeek V3.1 | 3.73 |
| 15 | GLM-4.5 (Thinking) | 3.07 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-code-2025-09-java · How the rankings work · Data refreshed daily, snapshot 2026-07-22.