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
1Fugu UltraFugu official headline evaluation· Reported by Sakana AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.93.2%
2DeepSeek V4 FlashDeepSeek V4 official model card · Think Max· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.6%
3Qwen3.7 MaxQwen3.7-Max release · recommended reasoning-effort=xhigh system prompt· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.91.6%
4Qwen3.7 PlusQwen3.7-Plus release · recommended reasoning-effort=xhigh system prompt· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.89.6%
5DeepSeek V3.2 SpecialeSpeciale high-compute reasoning · temperature 1.0 · 128K context · pass@1-CoT· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.7%
6DeepSeek V4 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.4%
7DeepSeek V4 FlashDeepSeek V4 official model card · Think High· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.88.4%
8Beam 1.0 501B A23B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim88.3%
9Solar Pro 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim87.8%
10o4 Minioverall, high· LiveCodeBench Leaderboard data87.3%
11OpenAI o3overall, high· LiveCodeBench Leaderboard data84.7%
12o4 Minioverall, medium· LiveCodeBench Leaderboard data84.5%
13DeepSeek R1overall· LiveCodeBench Leaderboard data84.4%
14Gemini 2.5 Prooverall· LiveCodeBench Leaderboard data84.3%
15DeepSeek Reasoner· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.3%
16DeepSeek V3.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim83.3%
17DeepSeek V3.2Thinking mode · temperature 1.0 · 128K context · pass@1-CoT· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.3%
18MiMo V2 Flashtechnical report Table 7 · student after MOPD · benchmark version unspecified· Reported by Xiaomi MiMo· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.83.2%
19MiniMax M2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.83%
20LongCat-Flash-Thinking· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim82.8%
21Nemotron 3 Super 120B A12B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.2%
22Nemotron 3 Super 120B A12BNeMo Evaluator / mostly NeMo Skills · v5 · 2024-07↔2024-12· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.81.2%
23Grok 3 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80.4%
24Qwen 3 235B A22Boverall· LiveCodeBench Leaderboard data80.4%
25Grok 4 Fast· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim80%
26Grok 3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79.4%
27Grok 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim79%
28Grok 3 Minioverall, high· LiveCodeBench Leaderboard data78.1%
29MiniMax M2.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim78%
30o3 Minioverall, high· LiveCodeBench Leaderboard data77.7%
31o4 Minioverall, low· LiveCodeBench Leaderboard data77.4%
32Gemini 2.5 Flashoverall· LiveCodeBench Leaderboard data76.2%
33o3 Minioverall, Med· LiveCodeBench Leaderboard data75.4%
34DeepSeek V3.2 Exp· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim74.1%
35DeepSeek R1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim73.3%
36GLM 4.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim72.9%
37Gemini 3.1 Flash LiteGemini 3.1 Flash-Lite Model Card · high thinking · default sampling · single attempt/pass@1 · 175 problems · 2025-01-01 through 2025-05-01· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.72%
38Nemotron Nano 9b V2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71.1%
39Nova 2 Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim71%
40GLM 4.5 Air· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.7%
41Qwen 3 235B A22B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim70.7%
42o3 Minioverall, low· LiveCodeBench Leaderboard data70.6%
43Claude Opus 4overall, thinking· LiveCodeBench Leaderboard data70.4%
44Gemini 2.5 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim69%
45Claude Sonnet 4overall, thinking· LiveCodeBench Leaderboard data68.5%
46Mercury 2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim67%
47Llama 3.1 Nemotron Ultra 253B v1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim66.3%
48Qwen3 32B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim65.7%
49MiniMax M1 80K· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it.65%
50Ministral 14Blatest· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim64.6%

Showing 1–50 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.