LLM2014 Code 2025-09 - C++ — leaderboard
Metric: Score. Source: raw.githubusercontent.com. 20 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini (High) | 7.29 |
| 2 | DeepSeek V3.1 (Thinking) | 6.19 |
| 3 | O4 Mini (High) | 6.04 |
| 4 | GLM-4.5 (Thinking) | 5.62 |
| 5 | Qwen 3 235B A22B 2507 Instruct | 5.08 |
| 6 | GPT-OSS-120B (High) | 4.87 |
| 7 | Grok Code Fast 1 | 4.66 |
| 8 | Kimi K2 (0711) | 4.65 |
| 9 | GLM-4.5 | 4.55 |
| 10 | Gemini 2.5 Pro | 4.51 |
| 11 | Claude Sonnet 4 (Thinking) | 4.44 |
| 12 | GPT-OSS-20B (High) | 4.34 |
| 13 | Claude Sonnet 4 | 3.88 |
| 14 | DeepSeek V3.1 | 3.41 |
| 15 | Grok 4 | 2.43 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-code-2025-09-c-plus-plus · How the rankings work · Data refreshed daily, snapshot 2026-07-22.