Code Generation on LiveCode Bench V6
86.19LiveCode BenchV6GLM-5
Evaluation Results
| Method | Links | |
|---|---|---|
| GLM-5Precision=FP82026.05 | 86.19 | |
| Step-3.5-Flash2026.05 | 83.9 | |
| GLM-4-72026.05 | 83.81 | |
| GPT-5-2025-08-07Setting=high2026.05 | 83.24 | |
| Gemini-3-Pro-Preview2026.05 | 82.86 | |
| DeepSeek-V3.2-Speciale2026.05 | 80.86 | |
| GPT-5-mini-2025-08-07Setting=high2026.05 | 80.76 | |
| Kimi-K2.52026.05 | 80.57 | |
| gpt-oss-120bSetting=high2026.05 | 78.38 | |
| GLM-4.62026.05 | 78.19 | |
| Kimi-K2Mode=Thinking2026.05 | 77.14 | |
| o3-mini-2025-04-16Setting=high2026.05 | 76 | |
| DeepSeek-V3.22026.05 | 75.43 | |
| MiniMax-M22026.05 | 74 | |
| GPT-5-nano-2025-08-07Setting=high2026.05 | 74 | |
| MiniMax-M2.52026.05 | 73.62 | |
| o3-2025-04-162026.05 | 72.67 | |
| Mimo-V2-Flash2026.05 | 71.81 | |
| TeleChatMode=Thinking2026.05 | 71.71 | |
| Gemini-2.5-Pro2026.05 | 71.33 | |
| o4-mini-2025-04-16Setting=high2026.05 | 71.05 | |
| Qwen3Parameters=235B, Active Parameters=A22B, Mode=Thinking, Version=25072026.05 | 70.57 | |
| gpt-oss-20bSetting=high2026.05 | 68.38 | |
| Seed-OSS-36BType=Instruct2026.05 | 67.33 | |
| Qwen3-NextParameters=80B, Active Parameters=A3B, Mode=Thinking2026.05 | 66.29 | |
| GLM-4.52026.05 | 65.05 | |
| JTMode=Think2026.05 | 64.86 | |
| doubao-seed-1.6Mode=thinking, Version=2506152026.05 | 61.81 | |
| DeepSeek-R1-05282026.05 | 60.95 | |
| Qwen3Parameters=235B, Active Parameters=A22B, Mode=Thinking2026.05 | 60 | |
| Qwen3Parameters=30B, Active Parameters=A3B, Mode=Thinking, Version=25072026.05 | 59.43 | |
| GLM-4.5-Air2026.05 | 58.38 | |
| Finix-P1-32BMode=Thinking2026.05 | 54.86 | |
| Qwen3-NextParameters=80B, Active Parameters=A3B, Type=Instruct2026.05 | 54.76 | |
| MiniCPM-Sala2026.05 | 54.67 | |
| QwQ-32B2026.05 | 52.76 | |
| Qwen3-4BMode=Thinking, Version=25072026.05 | 51.62 | |
| GLM-Z1-32B-04142026.05 | 50.19 | |
| LongCat-Flash-Chat2026.05 | 48.19 | |
| Claude Sonnet 4Mode=Thinking2026.05 | 47.52 | |
| ERNIE-4.5Parameters=21B, Active Parameters=A3B, Mode=Thinking2026.05 | 47.05 | |
| Kimi-K2Type=Instruct2026.05 | 46.76 | |
| DeepSeek-Chat-V3-03242026.05 | 46 | |
| Hunyuan-A13BType=Instruct2026.05 | 43.9 | |
| Qwen3Parameters=235B, Active Parameters=A22B, Type=Instruct, Version=25072026.05 | 42.95 | |
| ERNIE-4.5Parameters=300B, Active Parameters=A47B, Type=PT2026.05 | 41.05 | |
| Qwen3Parameters=30B, Active Parameters=A3B, Type=Instruct, Version=25072026.05 | 38.67 | |
| GPT-4.1-202504142026.05 | 37.24 | |
| Qwen3-4BType=Instruct, Version=25072026.05 | 33.52 | |
| Llama4-MaverickParameters=17B, Experts=128E, Type=Instruct2026.05 | 33.24 | |
| GLM-4-32B-04142026.05 | 32.57 | |
| Gemma-3-27B-it2026.05 | 30.76 |