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
51Mistral Large 4· LMArena data1,581.8
52GPT-6 LunaMax· LMArena data1,575.8
53Gemini 3.8 FlashHigh· LMArena data1,575.4
54Claude Opus 4.7High· LMArena data1,559.4
55Claude Opus 4.8High· LMArena data1,555.9
56Grok 4.5· LMArena data1,555.5
57Claude Opus 4.7· LMArena data1,552.4
58Claude Sonnet 5High· LMArena data1,539
59Claude Opus 4.6High· LMArena data1,538.2
60Claude Opus 4.8· LMArena data1,537
61Muse Spark 1.1· LMArena data1,529.9
62Claude Opus 4.6· LMArena data1,527
63Gemini 3.6 FlashHigh· LMArena data1,526.3
64Muse Spark 1.2xHigh· LMArena data1,525
65Muse Spark OpenMax· LMArena data1,522.1
66Seed2.1 Pro Preview· LMArena data1,513.1
67Qwen3.7 Max20260517· LMArena data1,512.5
68GPT-5.6 TerraxHigh, Codex Harness· LMArena data1,511
69Claude Sonnet 4.6· LMArena data1,510.9
70GPT-5.6 LunaxHigh, Codex Harness· LMArena data1,507.5
71Hy3 (Deep Infra)· LMArena data1,506
72GPT 5.5xHigh, Codex Harness· LMArena data1,505
73Kimi K2.6· LMArena data1,503.8
74GLM 5.1· LMArena data1,503.7
75Gemini 3.5 FlashHigh· LMArena data1,494.5
76Spark-X2.6· LMArena data1,491.8
77Gemini 3.5 FlashMedium· LMArena data1,480.2
78MiniMax M3· LMArena data1,478.6
79Claude Opus 4.5High, 32K, 20251101· LMArena data1,476.7
80GPT 5.5High, Codex Harness· LMArena data1,476.5
81Kimi K2.7 Code· LMArena data1,475.2
82Qwen3.6 Max Preview· LMArena data1,472.5
83MiMo V2.5 Pro· LMArena data1,467.6
84Claude Opus 4.520251101· LMArena data1,455.6
85Qwen3.6 Plus· LMArena data1,453.5
86DeepSeek-V4-Pro PreviewHigh· LMArena data1,452.7
87GPT 5.4High, Codex Harness· LMArena data1,450.5
88GPT 5.5Codex Harness· LMArena data1,444.3
89Beam 1.0 501B A23B· LMArena data1,442.9
90DeepSeek V4 Pro· LMArena data1,441.2
91Gemini 3.1 Pro Preview· LMArena data1,437.4
92Kimi K2.5Thinking· LMArena data1,428.2
93Gemini 3 Flash· LMArena data1,427.7
94GPT 5.4Medium, Codex Harness· LMArena data1,426.6
95MiMo V2 Pro· LMArena data1,425.1
96MiMo V2.5· LMArena data1,423.2
97GLM 5· LMArena data1,423.1
98DeepSeek-V4-Flash PreviewHigh· LMArena data1,421.3
99GLM 4.7· LMArena data1,420.5
100Gemini 3.5 Flash Lite· LMArena data1,409

Showing 51–100 of 143 results.

Data credits: LMArena, CC BY 4.0 (licence)