Inference
EN
LiveBench

LiveBench Coding

Mean score over writing a solution to a fresh competition problem and completing one whose body was removed. Not in LiveBench 2.0.

ModelsModels with a result.66
Top resultBest result on this benchmark.91.4%Claude Sonnet 5.5
Top-3 spreadPoints from first to third.5.0 pts
UpdatedDate the source changed the results.25 Jun 2026

Result and cost

65 of 66 results

Results

66 results
#ModelResultThe score from the source.CostUS dollars to run one task.
01Claude Sonnet 5.5max effort91.4%$0.154
02Claude Opus 5.5max effort89.3%$0.303
03Claude Fable 5.1max effort86.4%$0.401
04Claude Fable 5max effort86.0%$0.212
05GPT-5.6 Solmax effort83.9%$0.107
06GPT-5.2-Codex83.6%$0.029
07GPT-5.6 Lunamax effort82.9%$0.052
08Smaug Agentic82.5%$0.058
09GPT-5.5xhigh effort82.1%$0.154
09Claude Opus 4.7xhigh effort82.1%$0.029
11Claude Opus 4.8max effort81.8%$0.123
11GPT-6 Solmax effort81.8%$0.089
13Claude Opus 5max effort81.4%$0.033
13Kimi K381.4%$0.05
15Muse Spark 1.3xhigh effort81.1%$0.059
16Muse Wondermax effort80.7%$0.119
16Claude Sonnet 5xhigh effort80.7%$0.035
18GPT-6 Astramax effort80.4%$0.296
18GPT-6.1 Solmax effort80.4%$0.058
20DeepSeek V4.1 Flash 1017max effort80.0%$0.013
21GLM-5.279.7%$0.051
21Claude Opus 4.5 Thinking 64Khigh effort79.7%$0.174
23Claude Sonnet 4.6 Thinking Automedium effort79.3%$0.0059
24GLM-5.379.0%$0.17
24GPT-6 Lunamax effort79.0%$0.0052
24GLM-5.3-Flash79.0%$0.0033
27Gemini 3.7 Flashhigh effort78.9%$0.051
28Kimi K2.6 Thinking78.6%$0.028
29GPT-5.6 Terramax effort78.2%$0.169
29Gemini 3.5 Flashhigh effort78.2%$0.067
29Qwen3.6 Plus78.2%$0.017
29Claude Opus 4.6 Thinking Autohigh effort78.2%$0.03
33Claude Haiku 5.5max effort77.9%$0.018
33Gemini 3.6 Flashhigh effort77.9%$0.076
35Muse Spark 1.2xhigh effort77.5%$0.051
35GPT-5.4xhigh effort77.5%$0.267
37Grok 4.7xhigh effort77.2%$0.302
37DeepSeek V4 Pro 081377.2%$0.028
37Muse Spark 1.1xhigh effort77.2%$0.024
37Mistral Large 4high effort77.2%$0.031
41Smaug Flash77.1%$0.0062
42Grok 4.676.8%$0.021
43Gemini 3.1 Pro Previewhigh effort76.5%$0.077
44GPT-5.2high effort76.1%$0.029
44Gemini 3.5 Flash-Litehigh effort76.1%$0.01
46Ox Alpha Max75.8%$0
47Qwen3.8-27B75.7%$0.019
48Smaug Mini75.4%$0.01
49DeepSeek V4 Flash 073175.0%$0.0048
50Qwen3.7 Max74.2%$0.027
51Kimi K2.7 Code74.0%$0.014
52Qwen3.8 Max72.9%$0.113
53Qwen3.8-Flash-Next72.6%$0.028
54Gemini 3.8 Flashhigh effort72.5%$0.185
55Qwen3.6-27B71.8%$0.02
56GPT-5.4 minixhigh effort71.6%$0.222
57Inklingxhigh effort71.0%$0.053
58GPT-5.4 nanoxhigh effort70.8%$0.015
59DeepSeek V4 Pro 042370.0%$0.0062
60Grok 4.369.9%$0.011
61DeepSeek V4 Flash 042369.2%$0.0013
62Grok 4.568.6%$0.021
63DeepSeek V4 Flash Vision Exp68.2%$0.035
63MiniMax M368.2%$0.0063
65Grok Build 0.165.4%$0.00084
66Nemotron 3.5 Lightning 30B A3B45.8%$0.0035