Skip to content

Benchmark

Arena ELO Text Factuality - English

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

Models measured
167
Scores recorded
189
Sources
1
IQ weight
2.15

Score distribution

1,448.4
Mean
1,453.2
Median
33.8
Std dev
1,399.6
10th percentile
1,487.4
90th percentile
1,336.9
Min
1,336.91,518.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.15 for chat models, measured over 167 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 data1,518.5
2Claude Opus 5.5High· LMArena data1,516.5
3Gemini 4 NeonHigh· LMArena data1,507.3
4Muse WonderMax· LMArena data1,504.3
5Claude Opus 4.6High· LMArena data1,504.1
6Gemini 4 ArgonHigh· LMArena data1,503.3
7Claude Fable 5.1Max· LMArena data1,501.9
8Claude Opus 4.6· LMArena data1,501
9MiMo V2.6 Pro· LMArena data1,497.3
10Claude Fable 5High· LMArena data1,494.3
11Claude Opus 5Max· LMArena data1,494.2
12Gemini 4 HydrogenHigh· LMArena data1,493.2
13Muse Spark 1.3Max· LMArena data1,490.9
14Kimi K3.1 ProMax· LMArena data1,490.2
15Claude Opus 5High· LMArena data1,488.1
16Claude Opus 4.7High· LMArena data1,488
17Muse Spark 1.2xHigh· LMArena data1,487.7
18GPT 5.4High· LMArena data1,487.6
19GPT 5.5· LMArena data1,487.4
20Qwen3.8 Max· LMArena data1,487.4
21GPT 5.5High· LMArena data1,487.3
22Claude Sonnet 5.5xHigh· LMArena data1,486.1
23Qwen3.5-Max-Preview· LMArena data1,484.6
24Claude Opus 4.7· LMArena data1,483.5
25Claude Fable 5.2Max· LMArena data1,483.1
26Gemini 3.5 FlashHigh· LMArena data1,482.6
27Gemini 3 Pro Preview· LMArena data1,482.4
28Kimi K3Max· LMArena data1,481.2
29MiMo V2.5 Pro· LMArena data1,480.6
30DeepSeek V4.1 Flash 0910Max· LMArena data1,480
31Gemini 3.7 FlashHigh· LMArena data1,479.8
32GLM 5.3Max· LMArena data1,479.7
33GPT-5.6 SolxHigh· LMArena data1,479.5
34Claude Opus 4.8High· LMArena data1,479.3
35Muse Spark· LMArena data1,479.1
36GPT 5.4· LMArena data1,479
37Gemini 3.6 FlashHigh· LMArena data1,478.4
38GPT-6.1 SolMax· LMArena data1,477.9
39Claude Sonnet 4.6· LMArena data1,477.4
40Qwen3.7 Max Preview· LMArena data1,477
41Gemini 3.1 Pro Preview· LMArena data1,476
42GPT-6 AstraMax· LMArena data1,474.8
43Gemini 3.8 FlashHigh· LMArena data1,474.1
44GPT-5.6 TerraxHigh· LMArena data1,473.7
45GLM 5.1· LMArena data1,473
46GLM 5.2Max· LMArena data1,473
47GPT-6 LunaMax· LMArena data1,473
48Claude Opus 4.8· LMArena data1,472.8
49Gemini 3.5 FlashMedium· LMArena data1,472.7
50MiMo V2.6 Flash· LMArena data1,472.4

Showing 1–50 of 189 results.

Data credits: LMArena, CC BY 4.0 (licence)