Skip to content

Benchmark

Arena ELO Webdev - Webdev React

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

Models measured
124
Scores recorded
143
Sources
1
IQ weight
2.03

Score distribution

1,506.4
Mean
1,505
Median
159.1
Std dev
1,312.4
10th percentile
1,713.4
90th percentile
1,142.7
Min
1,142.71,885
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.03 for chat models, measured over 124 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 data1,885
2Claude Opus 5.5Max· LMArena data1,871.3
3Claude Sonnet 5.5xHigh· LMArena data1,819.2
4Gemini 4 CarbonHigh· LMArena data1,792.8
5Claude Fable 5.1Max· LMArena data1,787.2
6Gemini 4 NeonHigh· LMArena data1,786.9
7Qwen4 MaxxHigh· LMArena data1,784.6
8GPT-6 AstraMax· LMArena data1,774.9
9GPT-6.2 AstraMax· LMArena data1,769.7
10GPT-6.2 SolMax· LMArena data1,760.7
11GPT-6.1 SolMax· LMArena data1,749.7
12Claude Sonnet 5.5High· LMArena data1,749.6
13Muse Wonder FullMax· LMArena data1,741.9
14Gemini 4 HydrogenHigh· LMArena data1,722
15Claude Opus 5Max· LMArena data1,713.4
16Gemini 4 ArgonHigh· LMArena data1,700.8
17Kimi K3.1 ProMax· LMArena data1,697.3
18Qwen3.8 Max0902· LMArena data1,696.1
19Qwen3.8 Max· LMArena data1,679.4
20Claude Opus 5High· LMArena data1,678.4
21GPT-6 SolMax· LMArena data1,676.1
22GPT-6.1 TerraMax· LMArena data1,676.1
23Kimi K3Max· LMArena data1,674
24DeepSeek V4.1 Flash 1017Max· LMArena data1,673.3
25Muse Spark 1.3Max· LMArena data1,666.9
26Hy 4· LMArena data1,664.1
27Grok 4.7xHigh· LMArena data1,661.5
28Inkling 2 Small· LMArena data1,655.4
29Muse WonderMax· LMArena data1,655.2
30Qwen 3.8 Flash Next· LMArena data1,654.6
31MiMo V2.6 Flash· LMArena data1,652.6
32Hy4 preview· LMArena data1,652.4
33GLM 5.3Max· LMArena data1,641.3
34MiMo V2.6 Pro· LMArena data1,635.6
35Claude Fable 5High· LMArena data1,632.7
36Grok 4.6High· LMArena data1,631.3
37DeepSeek V4.1 Flash 0910Max· LMArena data1,630.7
38Muse Spark 1.3xHigh· LMArena data1,630.5
39GLM 5.3 Flash· LMArena data1,629.5
40GLM 5.2Max· LMArena data1,620.7
41GPT-5.6 SolxHigh, Codex Harness· LMArena data1,617.9
42Claude Haiku 5.5High· LMArena data1,617.9
43Muse EmberMax· LMArena data1,615.6
44U2 Flash· LMArena data1,615.5
45MiniMax M3.1 Flash· LMArena data1,600.5
46Qwen 3.8 27B· LMArena data1,594.3
47Step 5 PreviewHigh· LMArena data1,588
48DeepSeek V4 ProHigh, 20260813· LMArena data1,585.4
49DeepSeek V4 FlashHigh· LMArena data1,584.6
50Gemini 3.7 FlashHigh· LMArena data1,583.9

Showing 1–50 of 143 results.

Data credits: LMArena, CC BY 4.0 (licence)