LLM2014 Code 2025-11 - C++ — leaderboard
Metric: Score. Source: raw.githubusercontent.com. 26 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro | 10 |
| 2 | Claude Opus 4.5 | 9.92 |
| 3 | GPT-5 Mini (High) | 9.8 |
| 4 | Qwen 3 Max | 7.52 |
| 5 | Claude Sonnet 4.5 | 7.17 |
| 6 | Claude Sonnet 4.5 (Thinking) | 7.17 |
| 7 | Gemini 2.5 Pro | 7.15 |
| 8 | MiniMax-M2 | 5.82 |
| 9 | DeepSeek V3.2 | 5.67 |
| 10 | Ling-1T | 5.67 |
| 11 | Kimi K2 0905 | 5.5 |
| 12 | Claude Haiku 4.5 | 5.43 |
| 13 | GLM-4.6 (Thinking) | 5.1 |
| 14 | Kimi K2 (Thinking) | 4.15 |
| 15 | DeepSeek V3.2 (Thinking) | 4.03 |
Interactive version: theaggregate.ai/benchmark?slug=llm2014-code-2025-11-c-plus-plus · How the rankings work · Data refreshed daily, snapshot 2026-07-22.