Skip to content

Benchmark

Arena ELO Vision - Homework

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
104
Scores recorded
119
Sources
1
IQ weight
2.12

Score distribution

1,265.7
Mean
1,276
Median
57.7
Std dev
1,171.2
10th percentile
1,332.9
90th percentile
1,117.1
Min
1,117.11,362.8
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.12 for chat models, measured over 104 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 Opus 5.5High· LMArena data1,362.8
2Claude Fable 5High· LMArena data1,361.3
3Claude Fable 5.2Max· LMArena data1,354.4
4Gemini 3.8 FlashHigh· LMArena data1,352.4
5GPT-6.1 SolMax· LMArena data1,340.3
6Claude Fable 5.1Max· LMArena data1,338.8
7Claude Opus 4.7High· LMArena data1,337.6
8Claude Opus 5High· LMArena data1,336.1
9Claude Opus 4.6High· LMArena data1,336
10GPT 5.4High· LMArena data1,335.8
11Claude Opus 4.8High· LMArena data1,335.7
12Claude Opus 4.7· LMArena data1,334.8
13Qwen3.8 Max· LMArena data1,332.9
14GPT 5.5High· LMArena data1,331.6
15GPT-6 AstraMax· LMArena data1,331.3
16Claude Opus 4.8· LMArena data1,328.3
17Gemini 3.5 FlashMedium· LMArena data1,327.4
18Claude Opus 4.6· LMArena data1,326.9
19GPT 5.5· LMArena data1,326.3
20Gemini 3.7 FlashHigh· LMArena data1,325.8
21GLM 5.3 Flash· LMArena data1,324.9
22Claude Sonnet 5.5xHigh· LMArena data1,324
23Gemini 3.5 FlashHigh· LMArena data1,323
24Gemini 3.6 FlashHigh· LMArena data1,317.4
25Gemini 3.1 Pro Preview· LMArena data1,317.3
26Gemini 3 Pro Preview· LMArena data1,314.2
27Gemini 3 Flash· LMArena data1,313
28Claude Sonnet 4.6· LMArena data1,311.1
29Claude Sonnet 5High· LMArena data1,310.2
30Kimi K2.6· LMArena data1,310.2
31Gemma 4 31B IT· LMArena data1,310
32GPT 5.4· LMArena data1,309.5
33GPT-5.6 SolxHigh· LMArena data1,308.3
34GPT-6.1 TerraMax· LMArena data1,307.9
35GPT-5.6 TerraxHigh· LMArena data1,307.7
36Muse Spark 1.3Max· LMArena data1,306.5
37DeepSeek V4.1 Flash 0910Max· LMArena data1,306
38Muse Spark 1.3xHigh· LMArena data1,304
39Grok 4.5· LMArena data1,301.4
40Muse Spark· LMArena data1,298.2
41Gemini 3 FlashMinimal· LMArena data1,298.2
42Qwen3.7 Plus· LMArena data1,296
43Kimi K2.5Thinking· LMArena data1,295.5
44Qwen3.5 397B A17B· LMArena data1,292.4
45Gemma 4 26B A4B· LMArena data1,292.2
46GPT-6 SolMax· LMArena data1,289.9
47Gemini 3.5 Flash Lite· LMArena data1,288.7
48Qwen 3.8 27B· LMArena data1,288.4
49Grok 4.7xHigh· LMArena data1,285.9
50GPT-5.2 Chat20260210· LMArena data1,285.5

Showing 1–50 of 119 results.

Data credits: LMArena, CC BY 4.0 (licence)