LLM2014 Code 2025-11 - Golang: leaderboard
LLM2014 monthly coding benchmark for 2025-11, measuring Golang code-generation problem-solving on the source score scale.
Metric: Score. Source: raw.githubusercontent.com. Saturation forecast: Estimated already saturated. 26 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Mini (High) | 9.2 | #186 (GPT-5 Mini) |
| 2 | Claude Opus 4.5 | 9.1 | #83 |
| 3 | Gemini 2.5 Pro | 8.87 | #152 |
| 4 | Gemini 3 Pro | 7.93 | #80 |
| 5 | Claude Sonnet 4.5 | 7.85 | #142 |
| 6 | DeepSeek V3.2 (Thinking) | 7.25 | #205 (DeepSeek V3.2) |
| 7 | Claude Sonnet 4.5 (Thinking) | 7.18 | #142 (Claude Sonnet 4.5) |
| 8 | Qwen 3 Coder 480B A35B | 6.37 | #279 |
| 9 | Kimi K2 (Thinking) | 5.95 | #243 (Kimi K2) |
| 10 | GLM-4.6 (Thinking) | 5.7 | #252 (GLM-4.6) |
| 11 | Kimi K2 0905 | 5.67 | #288 |
| 12 | DeepSeek V3.2 | 5.62 | #205 |
| 13 | Claude Haiku 4.5 | 5.03 | #280 |
| 14 | Seed-1.6 (Thinking) | 4.45 | #265 (Seed-1.6) |
| 15 | Ling-1T | 3.67 | #348 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=llm2014-code-2025-11-golang · How It Works · Data refreshed daily, snapshot 2026-10-20.