Skip to content

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
1.9%93.2%
The band covers the middle 80% of scores. The line marks the median.

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

#ModelScore
51Mistral Smalllatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.6%
52QwQ 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim63.4%
53Qwen3 30B A3B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim62.6%
54Claude Opus 4overall· LiveCodeBench Leaderboard data62.4%
55MiniMax M1 40K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.62.3%
56Ministral 8Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim61.6%
57Claude Sonnet 4overall· LiveCodeBench Leaderboard data59.4%
58DeepSeek R1 Distill Llama 70b· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.5%
59DeepSeek R1 Distill Qwen 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim57.2%
60DeepSeek V3.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim56.4%
61Qwen2.5 72B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim55.5%
62DeepSeek 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%
63Ministral 3Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim54.8%
64Phi-4-reasoning· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.8%
65Kimi K2 Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.7%
66DeepSeek R1 Distill Qwen 14B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.1%
67Phi 4 Reasoning Plus· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim53.1%
68Magistral Small 25092506· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim51.3%
69Magistral Medium· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50.3%
70DeepSeek R1 Zero· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50%
71QwQ 32B Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim50%
72DeepSeek V3overall· LiveCodeBench Leaderboard data49.6%
73Claude 3.5 Sonnetoverall· LiveCodeBench Leaderboard data48.7%
74LongCat Flash Chat· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim48%
75Llama 4 Maverick· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim43.4%
76DeepSeek R1 Distill Llama 8B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim39.6%
77GPT 4ooverall· LiveCodeBench Leaderboard data38.3%
78DeepSeek R1 Distill Qwen 7B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim37.6%
79DeepSeek V3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim37.6%
80GPT-4 Turbooverall· LiveCodeBench Leaderboard data37.3%
81GPT-4o minioverall· LiveCodeBench Leaderboard data35.5%
82Gemini 2.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim35.1%
83Mistral Largelatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim34.4%
84Gemini 2.5 Flash-Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim33.7%
85Llama 4 Scout· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim32.8%
86Llama 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%
87Qwen 2.5 Coder 32B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim31.4%
88Gemma 3 27B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim29.7%
89Qwen2.5 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim28.7%
90Qwen2 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim26.6%
91Gemma 3 12B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim24.6%
92Claude 3 Haikuoverall· LiveCodeBench Leaderboard data22.5%
93Qwen2.5 Coder 7B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim18.2%
94DeepSeek R1 Distill Qwen 1.5B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim16.9%
95Gemma 3n E2b It· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim13.2%
96Gemma 3n E4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim13.2%
97Gemma 3 4B IT· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim12.6%
98Gemma 3 1b it· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim1.9%

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.