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
151Trinity Large Thinking· LMArena data1,230.6
152Grok 4.1Thinking· LMArena data1,225.6
153Devstral 2 123b Instruct 2512· LMArena data1,217.6
154Granite 4.1 8B· LMArena data1,206.1
155Mercury 2· LMArena data1,199.3
156Grok Code Fast 1· LMArena data1,172.7
157Grok 4 FastReasoning· LMArena data1,166.6
158Devstral Medium2507· LMArena data1,078

Showing 151–158 of 158 results.

Data credits: LMArena, CC BY 4.0 (licence)