Skip to content

Benchmark

Arena ELO Text Factuality - Industry Entertainment and Sports and Media

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

Models measured
150
Scores recorded
169
Sources
1
IQ weight
2.16

Score distribution

1,414.5
Mean
1,418.2
Median
43.7
Std dev
1,351.5
10th percentile
1,463.3
90th percentile
1,269.3
Min
1,269.31,504.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.16 for chat models, measured over 150 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 data1,504.5
2Gemini 4 ArgonHigh· LMArena data1,496.4
3Claude Opus 5.5High· LMArena data1,492.8
4Claude Fable 5.1Max· LMArena data1,490
5Gemini 4 NeonHigh· LMArena data1,486.2
6Claude Fable 5.2Max· LMArena data1,483.8
7Claude Opus 4.6High· LMArena data1,482.9
8Gemini 4 HydrogenHigh· LMArena data1,481.9
9Muse WonderMax· LMArena data1,478.6
10Claude Fable 5High· LMArena data1,475.1
11Claude Opus 4.6· LMArena data1,470
12Claude Opus 5Max· LMArena data1,469.3
13Gemini 3.7 FlashHigh· LMArena data1,466
14Qwen3.8 Max· LMArena data1,465.8
15Claude Opus 4.7High· LMArena data1,465.1
16Muse Spark 1.3Max· LMArena data1,463.9
17Kimi K3.1 ProMax· LMArena data1,463.8
18Qwen3.5-Max-Preview· LMArena data1,463.3
19Gemini 3 Pro Preview· LMArena data1,463.2
20Claude Opus 5High· LMArena data1,463.2
21Gemini 3.5 FlashHigh· LMArena data1,463.1
22Claude Opus 4.7· LMArena data1,462.7
23Gemini 3.8 FlashHigh· LMArena data1,461.8
24MiMo V2.6 Pro· LMArena data1,460.8
25GPT-5.6 SolxHigh· LMArena data1,459
26Gemini 3.1 Pro Preview· LMArena data1,458.9
27GPT 5.5· LMArena data1,457.3
28GPT 5.5High· LMArena data1,455.7
29Claude Sonnet 5.5xHigh· LMArena data1,455.5
30Gemini 3.6 FlashHigh· LMArena data1,455
31Gemini 3.5 FlashMedium· LMArena data1,453.7
32GPT 5.4High· LMArena data1,453.4
33Muse Spark· LMArena data1,451.8
34Claude Opus 4.8High· LMArena data1,450.3
35Gemini 3 Flash· LMArena data1,450.2
36Muse Spark 1.2xHigh· LMArena data1,450.2
37GLM 5.3Max· LMArena data1,449.6
38Kimi K3Max· LMArena data1,448.9
39DeepSeek V4.1 Flash 0910Max· LMArena data1,448
40GLM 5.2Max· LMArena data1,446.1
41Grok 4.5· LMArena data1,445.2
42Claude Opus 4.8· LMArena data1,445.1
43Claude Opus 4.520251101· LMArena data1,444.5
44GLM 5.1· LMArena data1,442.8
45GPT-6 AstraMax· LMArena data1,442.4
46MiMo V2.5 Pro· LMArena data1,442.1
47Claude Sonnet 4.520250929· LMArena data1,440.6
48GPT 5.4· LMArena data1,440.2
49Claude Sonnet 4.6· LMArena data1,439.6
50Gemini 2.5 Pro· LMArena data1,439.2

Showing 1–50 of 169 results.

Data credits: LMArena, CC BY 4.0 (licence)