BenchmarksCoding
LiveCodeBench Pro
A live competitive-programming benchmark that rates LLMs with a Codeforces-style Elo on fresh contest problems.
CodingCodeforces EloHigher is better
| Model | Lab | Score↓ | Source model | Status | Date | |
|---|---|---|---|---|---|---|
| Gemini 3 Deep Think | Google DeepMind | 3298 | Gemini 3 Deep Think | Official | May 31, 2026 | Details |
| Gemini 3.1 Pro Preview | Google DeepMind | 2887 | Gemini 3.1 Pro Preview | Official | May 31, 2026 | Details |
| Gemini 3 Pro | Google DeepMind | 2439 | Gemini 3 Pro Preview | Official | May 31, 2026 | Details |
| GPT-5.2 | OpenAI | 2393 | GPT-5.2-high (2025-12-11) | Official | May 31, 2026 | Details |
| Gemini 3 Flash | Google DeepMind | 2316 | Gemini 3 Flash Preview | Official | May 31, 2026 | Details |
| GPT-5.1 | OpenAI | 2269 | GPT-5.1-high (2025-11-13) | Official | May 31, 2026 | Details |
| GPT-5 high | OpenAI | 2176 | GPT-5-high (2025-08-07) | Official | May 31, 2026 | Details |
| o4-mini (high) | OpenAI | 2092 | o4-mini-high (2025-04-16) | Official | May 31, 2026 | Details |
| Gemini 2.5 Pro | Google DeepMind | 1769 | Gemini 2.5 Pro | Official | May 31, 2026 | Details |
| Qwen3 235B A22B Instruct 2507 | Alibaba / Qwen | 1673 | Qwen3-235B-A22B-Thinking-2507 | Official | May 31, 2026 | Details |
| Claude Sonnet 4.5 | Anthropic | 1412 | Claude 4.5 Sonnet Thinking | Official | May 31, 2026 | Details |
| GPT-OSS-120B | OpenAI | 1299 | GPT OSS 120B | Official | May 31, 2026 | Details |
| DeepSeek R1 | DeepSeek | 1284 | DeepSeek R1 (2025-05-28) | Official | May 31, 2026 | Details |
| DeepSeek V3 0324 | DeepSeek | 1124 | DeepSeek V3 (2025-03-24) | Official | May 31, 2026 | Details |
Each row reports the model’s Codeforces Elo on LiveCodeBench Pro. Click a row for the full run context.