Skip to content

Benchmark

Arena ELO Webdev - Webdev

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

Models measured
139
Scores recorded
159
Sources
1
IQ weight
1.96

Score distribution

1,484.4
Mean
1,484.4
Median
157.2
Std dev
1,263.4
10th percentile
1,683
90th percentile
1,072
Min
1,0721,823.6
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.96 for chat models, measured over 139 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Claude Fable 5.2xHigh· LMArena data1,823.6
2Claude Opus 5.5Max· LMArena data1,819
3Claude Sonnet 5.5xHigh· LMArena data1,772
4Gemini 4 CarbonHigh· LMArena data1,768.7
5GPT-6.2 AstraMax· LMArena data1,766.2
6Gemini 4 NeonHigh· LMArena data1,764.9
7GPT-6 AstraMax· LMArena data1,764
8GPT-6.2 SolMax· LMArena data1,754
9Qwen4 MaxxHigh· LMArena data1,750.9
10GPT-6.1 SolMax· LMArena data1,743.4
11Claude Fable 5.1Max· LMArena data1,741.9
12Muse Wonder FullMax· LMArena data1,722.6
13Claude Sonnet 5.5High· LMArena data1,715.5
14Gemini 4 HydrogenHigh· LMArena data1,700.6
15Claude Opus 5Max· LMArena data1,691.6
16GPT-6.1 TerraMax· LMArena data1,685.4
17Kimi K3.1 ProMax· LMArena data1,683
18Gemini 4 ArgonHigh· LMArena data1,682.4
19GPT-6 SolMax· LMArena data1,674.4
20Qwen3.8 Max0902· LMArena data1,673.6
21Qwen3.8 Max· LMArena data1,670.4
22Kimi K3Max· LMArena data1,659.2
23DeepSeek V4.1 Flash 1017Max· LMArena data1,658
24Claude Opus 5High· LMArena data1,656.5
25Muse Spark 1.3Max· LMArena data1,653
26Hy 4· LMArena data1,650.5
27Muse WonderMax· LMArena data1,647
28Inkling 2 Small· LMArena data1,642.7
29Grok 4.7xHigh· LMArena data1,638.9
30MiMo V2.6 Flash· LMArena data1,637.5
31Hy4 preview· LMArena data1,631.4
32Claude Fable 5High· LMArena data1,625.9
33Qwen 3.8 Flash Next· LMArena data1,625.7
34GLM 5.3Max· LMArena data1,622.7
35MiMo V2.6 Pro· LMArena data1,622.1
36DeepSeek V4.1 Flash 0910Max· LMArena data1,621.3
37Muse Spark 1.3xHigh· LMArena data1,620.8
38Grok 4.6High· LMArena data1,618
39GPT-5.6 SolxHigh, Codex Harness· LMArena data1,615.4
40GLM 5.3 Flash· LMArena data1,610.5
41U2 Flash· LMArena data1,609.4
42Muse EmberMax· LMArena data1,608.3
43GLM 5.2Max· LMArena data1,607.5
44Claude Haiku 5.5High· LMArena data1,595.4
45Qwen 3.8 27B· LMArena data1,589.5
46Gemini 3.7 FlashHigh· LMArena data1,588.7
47Gemini 3.8 FlashHigh· LMArena data1,584.2
48DeepSeek V4 FlashHigh· LMArena data1,582.1
49MiniMax M3.1 Flash· LMArena data1,581.4
50DeepSeek V4 ProHigh, 20260813· LMArena data1,580.7

Showing 1–50 of 159 results.

Data credits: LMArena, CC BY 4.0 (licence)