Skip to content

Benchmark

Arena ELO - French

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

Models measured
262
Scores recorded
303
Sources
1
IQ weight
1.87

Score distribution

1,360.8
Mean
1,408.4
Median
127.5
Std dev
1,158.9
10th percentile
1,487.2
90th percentile
945.6
Min
945.61,562.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.87 for chat models, measured over 262 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 NeonHigh· LMArena data1,562.9
2Gemini 4 ArgonHigh· LMArena data1,550.5
3Claude Fable 5.2Max· LMArena data1,523.5
4Claude Fable 5.1Max· LMArena data1,521.5
5Claude Opus 5High· LMArena data1,521.4
6Muse WonderMax· LMArena data1,514.8
7Claude Opus 4.6High· LMArena data1,511.5
8Claude Fable 5High· LMArena data1,509.5
9Claude Opus 5.5High· LMArena data1,506
10Qwen3.8 Max· LMArena data1,505.8
11Gemini 4 HydrogenHigh· LMArena data1,504.6
12Muse Spark 1.3Max· LMArena data1,504.3
13Claude Opus 4.7High· LMArena data1,503.3
14Muse Spark 1.2xHigh· LMArena data1,502.1
15Gemini 3.6 FlashHigh· LMArena data1,501.8
16GLM 5.3Max· LMArena data1,499.6
17Gemini 3.8 FlashHigh· LMArena data1,498.8
18Claude Opus 4.6· LMArena data1,498.4
19Claude Opus 5Max· LMArena data1,497.5
20Claude Opus 4.7· LMArena data1,496.8
21GPT 5.4High· LMArena data1,494
22Muse Spark· LMArena data1,494
23Muse Spark 1.1· LMArena data1,493.1
24Gemini 3 Pro Preview· LMArena data1,492.8
25Gemini 3.7 FlashHigh· LMArena data1,492
26Gemini 3.5 FlashHigh· LMArena data1,490.8
27Claude Sonnet 5.5xHigh· LMArena data1,489.6
28Kimi K3.1 ProMax· LMArena data1,488.9
29ERNIE 5.1· LMArena data1,488.3
30MiMo V2.5 Pro· LMArena data1,487.7
31GLM 5.3 Flash· LMArena data1,487.2
32Gemini 3.1 Pro Preview· LMArena data1,486.5
33Qwen3.5-Max-Preview· LMArena data1,485.2
34Kimi K3Max· LMArena data1,484.8
35GPT 5.5· LMArena data1,484.4
36GPT 5.5High· LMArena data1,482.9
37Claude Opus 4.8High· LMArena data1,480.5
38Gemini 3 Flash· LMArena data1,477.5
39GLM 5.2Max· LMArena data1,476.4
40Claude Opus 4.8· LMArena data1,476.1
41Grok 4.20Reasoning, 0309, beta· LMArena data1,475.4
42GPT-5.6 SolxHigh· LMArena data1,474.4
43Gemini 2.5 Pro· LMArena data1,474
44Nemotron 3 UltraNVFP4· LMArena data1,473.6
45MiMo V2.6 Flash· LMArena data1,472.9
46Gemini 3.5 FlashMedium· LMArena data1,472.8
47Doubao Seed 2.0 Pro· LMArena data1,471.4
48GPT 5.4· LMArena data1,471.4
49Qwen3.7 Plus· LMArena data1,471.1
50Kimi K2.6· LMArena data1,470.9

Showing 1–50 of 303 results.

Data credits: LMArena, CC BY 4.0 (licence)