Skip to content

Benchmark

Arena ELO - Coding

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

Models measured
361
Scores recorded
418
Sources
1
IQ weight
1.28

Score distribution

1,325
Mean
1,374.5
Median
162.1
Std dev
1,081.6
10th percentile
1,488
90th percentile
682.8
Min
682.81,564.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.28 for chat models, measured over 361 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1Gemini 4 CarbonHigh· LMArena data1,564.3
2Gemini 4 NeonHigh· LMArena data1,555.3
3Claude Opus 5.5High· LMArena data1,543.5
4Gemini 4 ArgonHigh· LMArena data1,539.2
5MiMo V2.6 Pro· LMArena data1,534.1
6Claude Opus 4.6· LMArena data1,533.9
7Claude Opus 5Max· LMArena data1,531.9
8Claude Opus 4.6High· LMArena data1,530.8
9Claude Opus 5High· LMArena data1,530.7
10Claude Fable 5.1Max· LMArena data1,526.6
11Muse WonderMax· LMArena data1,523.2
12Claude Opus 4.7High· LMArena data1,519
13Claude Fable 5High· LMArena data1,518.5
14Claude Opus 4.7· LMArena data1,515.2
15Gemini 4 HydrogenHigh· LMArena data1,512
16Muse Spark 1.3Max· LMArena data1,510.1
17Gemini 3.8 FlashHigh· LMArena data1,509.2
18GLM 5.3 Flash· LMArena data1,509
19Kimi K3Max· LMArena data1,505.2
20Muse Spark 1.2xHigh· LMArena data1,503.8
21Claude Sonnet 4.6· LMArena data1,503.4
22Qwen3.8 Max· LMArena data1,503.3
23DeepSeek V4.1 Flash 0910Max· LMArena data1,503.3
24Claude Opus 4.5High, 32K, 20251101· LMArena data1,503.1
25Gemini 3.7 FlashHigh· LMArena data1,500.6
26GLM 5.3Max· LMArena data1,500.6
27MiMo V2.5 Pro· LMArena data1,500.5
28Claude Sonnet 5.5xHigh· LMArena data1,500.4
29Claude Opus 4.520251101· LMArena data1,498.6
30Muse Spark 1.1· LMArena data1,497.9
31GPT 5.4High· LMArena data1,496.8
32Qwen3.7 Max Preview· LMArena data1,496.8
33MiMo V2.6 Flash· LMArena data1,495.5
34GPT-5.6 SolxHigh· LMArena data1,495.2
35GPT-6 AstraMax· LMArena data1,494
36GPT 5.5High· LMArena data1,493.3
37Gemini 3.5 FlashHigh· LMArena data1,493
38Gemini 3.6 FlashHigh· LMArena data1,491.4
39Claude Opus 4.8High· LMArena data1,490.9
40GPT-6.1 SolMax· LMArena data1,490.3
41Kimi K2.6· LMArena data1,488.9
42Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,488.1
43GLM 5.2Max· LMArena data1,488
44Gemini 3.5 FlashMedium· LMArena data1,487.8
45ERNIE 5.1· LMArena data1,487.6
46Qwen3.5-Max-Preview· LMArena data1,487.3
47Claude Fable 5.2Max· LMArena data1,486.7
48Claude Opus 4.8· LMArena data1,486.2
49GPT-5.6 TerraxHigh· LMArena data1,485.3
50GLM 5.1· LMArena data1,485.2

Showing 1–50 of 418 results.

Data credits: LMArena, CC BY 4.0 (licence)