Skip to content

Benchmark

Arena ELO Webdev - Webdev Html

Coding benchmarks compare models on programming tasks. Higher scores are better.

Models measured
138
Scores recorded
158
Sources
1
IQ weight
2.06

Score distribution

1,488.6
Mean
1,488.1
Median
154.2
Std dev
1,286.1
10th percentile
1,683
90th percentile
1,078
Min
1,0781,854.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.06 for chat models, measured over 138 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-6.2 AstraMax· LMArena data1,854.3
2GPT-6.2 SolMax· LMArena data1,840.5
3Gemini 4 NeonHigh· LMArena data1,802.8
4GPT-6.1 SolMax· LMArena data1,796.8
5GPT-6 AstraMax· LMArena data1,793.8
6Claude Fable 5.2xHigh· LMArena data1,781
7Gemini 4 CarbonHigh· LMArena data1,770.5
8Claude Opus 5.5Max· LMArena data1,761.7
9Claude Sonnet 5.5xHigh· LMArena data1,758.3
10Qwen4 MaxxHigh· LMArena data1,751.9
11GPT-6.1 TerraMax· LMArena data1,734.3
12Gemini 4 HydrogenHigh· LMArena data1,718.5
13Muse Wonder FullMax· LMArena data1,715.2
14Claude Sonnet 5.5High· LMArena data1,709
15Claude Fable 5.1Max· LMArena data1,686.4
16GPT-6 SolMax· LMArena data1,684
17DeepSeek V4.1 Flash 1017Max· LMArena data1,683
18Claude Opus 5Max· LMArena data1,680.6
19Kimi K3.1 ProMax· LMArena data1,679.2
20Gemini 4 ArgonHigh· LMArena data1,677.5
21Hy 4· LMArena data1,659.1
22Qwen3.8 Max0902· LMArena data1,652.7
23Muse WonderMax· LMArena data1,652.3
24Muse Spark 1.3Max· LMArena data1,651.5
25Claude Fable 5High· LMArena data1,650.7
26Claude Opus 5High· LMArena data1,649.5
27Kimi K3Max· LMArena data1,640.5
28MiMo V2.6 Flash· LMArena data1,637.9
29Grok 4.7xHigh· LMArena data1,630.4
30Inkling 2 Small· LMArena data1,628.9
31Qwen3.8 Max· LMArena data1,625.8
32Hy4 preview· LMArena data1,624.2
33Muse EmberMax· LMArena data1,623.7
34MiMo V2.6 Pro· LMArena data1,622.1
35DeepSeek V4.1 Flash 0910Max· LMArena data1,619.6
36U2 Flash· LMArena data1,618.8
37Muse Spark 1.3xHigh· LMArena data1,616.1
38GPT-5.6 SolxHigh, Codex Harness· LMArena data1,612.6
39Gemini 3.8 FlashHigh· LMArena data1,609.5
40GLM 5.3Max· LMArena data1,599.3
41Grok 4.6High· LMArena data1,598.1
42Gemini 3.7 FlashHigh· LMArena data1,594.5
43Qwen 3.8 Flash Next· LMArena data1,593.1
44GPT-6 LunaMax· LMArena data1,592.9
45GLM 5.3 Flash· LMArena data1,579.1
46Qwen 3.8 27B· LMArena data1,570.6
47Claude Haiku 5.5High· LMArena data1,568.5
48GLM 5.2Max· LMArena data1,567.2
49Grok 4.5· LMArena data1,565.9
50DeepSeek V4 ProHigh, 20260813· LMArena data1,561.8

Showing 1–50 of 158 results.

Data credits: LMArena, CC BY 4.0 (licence)