Benchmark
LiveCodeBench
Coding benchmarks compare models on programming tasks. Scores are percentages. Higher is better.
- Models measured
- 81
- Scores recorded
- 98
- Sources
- 3
- IQ weight
- 1.24
Score distribution
- 61.3%
- Mean
- 65.7%
- Median
- 22.1%
- Std dev
- 29.7%
- 10th percentile
- 84.7%
- 90th percentile
- 1.9%
- Min
This benchmark has a weight of 1.24 for chat models, measured over 78 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model | Score |
|---|---|---|
| 51 | Mistral Smalllatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.6% |
| 52 | QwQ 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 63.4% |
| 53 | Qwen3 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.6% |
| 54 | Claude Opus 4overall· LiveCodeBench Leaderboard data | 62.4% |
| 55 | MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. | 62.3% |
| 56 | Ministral 8Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 61.6% |
| 57 | Claude Sonnet 4overall· LiveCodeBench Leaderboard data | 59.4% |
| 58 | DeepSeek R1 Distill Llama 70b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.5% |
| 59 | DeepSeek R1 Distill Qwen 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.2% |
| 60 | DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 56.4% |
| 61 | Qwen2.5 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 55.5% |
| 62 | DeepSeek V4 FlashDeepSeek V4 official model card · Non-Think· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.2% |
| 63 | Ministral 3Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54.8% |
| 64 | Phi-4-reasoning· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.8% |
| 65 | Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.7% |
| 66 | DeepSeek R1 Distill Qwen 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.1% |
| 67 | Phi 4 Reasoning Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 53.1% |
| 68 | Magistral Small 25092506· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 51.3% |
| 69 | Magistral Medium· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.3% |
| 70 | DeepSeek R1 Zero· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50% |
| 71 | QwQ 32B Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50% |
| 72 | DeepSeek V3overall· LiveCodeBench Leaderboard data | 49.6% |
| 73 | Claude 3.5 Sonnetoverall· LiveCodeBench Leaderboard data | 48.7% |
| 74 | LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 48% |
| 75 | Llama 4 Maverick· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 43.4% |
| 76 | DeepSeek R1 Distill Llama 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 39.6% |
| 77 | GPT 4ooverall· LiveCodeBench Leaderboard data | 38.3% |
| 78 | DeepSeek R1 Distill Qwen 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 37.6% |
| 79 | DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 37.6% |
| 80 | GPT-4 Turbooverall· LiveCodeBench Leaderboard data | 37.3% |
| 81 | GPT-4o minioverall· LiveCodeBench Leaderboard data | 35.5% |
| 82 | Gemini 2.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 35.1% |
| 83 | Mistral Largelatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34.4% |
| 84 | Gemini 2.5 Flash-Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 33.7% |
| 85 | Llama 4 Scout· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 32.8% |
| 86 | Llama 4 Scout2024-10-01–2025-02-01 · pass@1· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 32.8% |
| 87 | Qwen 2.5 Coder 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.4% |
| 88 | Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 29.7% |
| 89 | Qwen2.5 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 28.7% |
| 90 | Qwen2 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 26.6% |
| 91 | Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 24.6% |
| 92 | Claude 3 Haikuoverall· LiveCodeBench Leaderboard data | 22.5% |
| 93 | Qwen2.5 Coder 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 18.2% |
| 94 | DeepSeek R1 Distill Qwen 1.5B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 16.9% |
| 95 | Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 13.2% |
| 96 | Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 13.2% |
| 97 | Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 12.6% |
| 98 | Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 1.9% |
Showing 51–98 of 98 results.
Data credits: Data by LLM Stats · BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.