Benchmarks · coding
LiveCodeBench
LiveCodeBench: competitive programming problems; pass rate.
57 models · 71 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
GLM 4.7
All results
71 rows| # | Model | Effort | LiveCodeBench |
|---|---|---|---|
| 1 | GLM 4.7 | 89.4% | |
| 2 | GPT-5.2 | medium | 89.4% |
| 3 | GPT-5.2 | xhigh | 88.9% |
| 4 | gpt-oss-120b | high | 87.8% |
| 5 | GPT-5.1 | high | 86.8% |
| 6 | o4 mini | high | 85.9% |
| 7 | GPT-5.1 Codex | high | 84.9% |
| 8 | GPT-5 | high | 84.6% |
| 9 | GPT-5 Codex | high | 84.0% |
| 10 | GPT-5 Mini | high | 83.8% |
| 11 | GPT-5.1 Codex Mini | high | 83.6% |
| 12 | MiniMax M2 | 82.6% | |
| 13 | Grok 4 | 81.9% | |
| 14 | MiniMax M2.1 | 81.0% | |
| 15 | o3 | 80.8% | |
| 16 | Gemini 2.5 Pro | 80.1% | |
| 17 | GPT-5 Nano | high | 78.9% |
| 18 | gpt-oss-20b | high | 77.7% |
| 19 | Qwen 3 Max | none | 76.7% |
| 20 | GPT-5 Nano | medium | 76.3% |
| 21 | GPT-5 | low | 76.3% |
| 22 | Opus 4.5 | none | 73.8% |
| 23 | GLM 4.5 | 73.8% | |
| 24 | o3 mini | high | 73.4% |
| 25 | o3 mini | 71.7% | |
| 26 | gpt-oss-120b | low | 70.7% |
| 27 | GPT-5 | medium | 70.3% |
| 28 | GPT-5 Mini | medium | 69.2% |
| 29 | GLM 4.5 Air | 68.4% | |
| 30 | o1 | 67.9% |