Skip to content

Benchmark

Arena ELO Text Factuality - Industry Software and It Services

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

Models measured
162
Scores recorded
182
Sources
1
IQ weight
2.15

Score distribution

1,476.5
Mean
1,480.3
Median
36.5
Std dev
1,425.2
10th percentile
1,517.7
90th percentile
1,338.8
Min
1,338.81,546.5
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 162 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 data1,546.5
2Gemini 4 NeonHigh· LMArena data1,544.7
3Claude Opus 5.5High· LMArena data1,544
4Claude Opus 4.6· LMArena data1,533.2
5Claude Opus 4.6High· LMArena data1,533.1
6Muse WonderMax· LMArena data1,532.9
7Gemini 4 ArgonHigh· LMArena data1,531.5
8Claude Fable 5.1Max· LMArena data1,531.4
9MiMo V2.6 Pro· LMArena data1,531.3
10Claude Opus 5Max· LMArena data1,526.7
11Kimi K3.1 ProMax· LMArena data1,526.2
12Gemini 4 HydrogenHigh· LMArena data1,524.1
13GPT 5.5High· LMArena data1,522.2
14Claude Fable 5High· LMArena data1,520.2
15Claude Opus 4.7High· LMArena data1,519.7
16GPT 5.4High· LMArena data1,519.5
17Muse Spark 1.3Max· LMArena data1,518.8
18Claude Opus 5High· LMArena data1,518.5
19GPT-5.6 SolxHigh· LMArena data1,517.7
20GPT-6.1 SolMax· LMArena data1,516.9
21GPT 5.5· LMArena data1,516.5
22Qwen3.7 Max Preview· LMArena data1,515.7
23GPT-6 AstraMax· LMArena data1,515.5
24Muse Spark 1.2xHigh· LMArena data1,515.2
25Claude Opus 4.7· LMArena data1,513.6
26Claude Sonnet 5.5xHigh· LMArena data1,512.2
27Kimi K3Max· LMArena data1,511.4
28GPT 5.4· LMArena data1,511.2
29GPT-5.6 TerraxHigh· LMArena data1,511.2
30GPT-6 LunaMax· LMArena data1,510.3
31Qwen3.8 Max· LMArena data1,510.3
32Gemini 3.5 FlashHigh· LMArena data1,509.6
33DeepSeek V4.1 Flash 0910Max· LMArena data1,509.5
34Gemini 3.7 FlashHigh· LMArena data1,509.5
35MiMo V2.5 Pro· LMArena data1,509.4
36Claude Opus 4.8High· LMArena data1,509.3
37Claude Fable 5.2Max· LMArena data1,508.1
38Gemini 3.6 FlashHigh· LMArena data1,507.4
39Gemini 3 Pro Preview· LMArena data1,507
40GLM 5.3Max· LMArena data1,507
41Claude Sonnet 4.6· LMArena data1,507
42Qwen3.5-Max-Preview· LMArena data1,506.5
43Claude Opus 4.520251101· LMArena data1,504.4
44GLM 5.3 Flash· LMArena data1,504.2
45Claude Opus 4.8· LMArena data1,503.8
46Claude Opus 4.5High, 32K, 20251101· LMArena data1,503.5
47Gemini 3.8 FlashHigh· LMArena data1,503.2
48Muse Spark 1.1· LMArena data1,503
49GPT-6.1 TerraMax· LMArena data1,502.9
50Grok 4.5· LMArena data1,500.5

Showing 1–50 of 182 results.

Data credits: LMArena, CC BY 4.0 (licence)