Skip to content

Benchmark

Arena ELO Text Factuality - Industry Life and Physical and Social Science

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

Models measured
138
Scores recorded
156
Sources
1
IQ weight
2.35

Score distribution

1,466.8
Mean
1,468.6
Median
33.7
Std dev
1,433.2
10th percentile
1,506.4
90th percentile
1,348.5
Min
1,348.51,551.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.35 for chat models, measured over 138 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51ERNIE 5.1· LMArena data1,483
52Muse Spark 1.1· LMArena data1,483
53DeepSeek V4 Pro· LMArena data1,481.5
54DeepSeek V4 ProHigh, 20260813· LMArena data1,480
55ERNIE-5.0-Preview1203· LMArena data1,479.9
56Step 5 Preview· LMArena data1,479.5
57Claude Sonnet 5High· LMArena data1,478
58GPT 5.1High· LMArena data1,477.9
59Inkling FP4· LMArena data1,477.3
60Kimi K2.6· LMArena data1,476.7
61Hy3 (Deep Infra)· LMArena data1,476.4
62Grok 4.20Reasoning, 0309, beta· LMArena data1,476.2
63GPT-6 LunaMax· LMArena data1,475.3
64Qwen3.7 Plus· LMArena data1,475.2
65GPT-5.6 LunaxHigh· LMArena data1,475
66GLM 5· LMArena data1,474.6
67MiMo V2.6 Flash· LMArena data1,474.3
68MiMo V2 Pro· LMArena data1,474.1
69Claude Opus 4.520251101· LMArena data1,473.6
70Qwen3.5 397B A17B· LMArena data1,473.1
71Gemini 3 FlashMinimal· LMArena data1,472.7
72DeepSeek-V4-Pro PreviewHigh· LMArena data1,472.3
73GPT-6.1 TerraMax· LMArena data1,471.6
74Grok 4.20 Multi-Agent0309, beta· LMArena data1,471
75GPT 5.1· LMArena data1,470.3
76Claude Opus 4.5High, 32K, 20251101· LMArena data1,470
77Qwen 3.8 27B· LMArena data1,469.3
78Gemini 3.5 Flash Lite· LMArena data1,468.6
79GLM 4.6· LMArena data1,466.3
80Kimi K2.5Thinking· LMArena data1,465.4
81Nemotron 3 UltraNVFP4· LMArena data1,465.3
82Claude Sonnet 4.520250929· LMArena data1,464.9
83Grok 4.6High· LMArena data1,464.6
84Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,463.8
85ERNIE 5.00110· LMArena data1,463.8
86GLM 4.7· LMArena data1,463
87DeepSeek V3.2· LMArena data1,462.8
88Gemini 2.5 Flash Preview09-2025· LMArena data1,462.4
89Qwen3 235B A22B Instruct 25072507· LMArena data1,462.1
90DeepSeek V4 Flash· LMArena data1,460.9
91MiMo V2.5· LMArena data1,460.7
92NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,460.6
93ChatGPT-4o Latest20250326· LMArena data1,460.6
94GPT-5.4 miniHigh· LMArena data1,460.3
95nova-experimental-chat11-10· LMArena data1,460.3
96Mistral Large 3· LMArena data1,460.1
97GPT 5.2High· LMArena data1,460
98GPT-5.2 Chat20260210· LMArena data1,459.6
99Grok 4.20 Beta 1· LMArena data1,459.5
100GPT 5.2· LMArena data1,458.9

Showing 51–100 of 156 results.

Data credits: LMArena, CC BY 4.0 (licence)