Skip to content

Benchmark

Arena ELO Text Factuality - Industry Business and Management and Financial Operations

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

Models measured
146
Scores recorded
165
Sources
1
IQ weight
2.32

Score distribution

1,444.9
Mean
1,448.8
Median
35.8
Std dev
1,391.7
10th percentile
1,485.5
90th percentile
1,297.2
Min
1,297.21,509.6
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.32 for chat models, measured over 146 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51GLM 5.1· LMArena data1,464.3
52Qwen3.7 Max Preview· LMArena data1,463.6
53GLM 5.2Max· LMArena data1,462
54Gemini 3 Flash· LMArena data1,462
55Kimi K2.6· LMArena data1,461.5
56MiMo V2.6 Flash· LMArena data1,461
57GPT-6 LunaMax· LMArena data1,460.8
58GPT-5.4 miniHigh· LMArena data1,460
59Claude Sonnet 4.520250929· LMArena data1,459.5
60DeepSeek V4 Pro· LMArena data1,458.6
61Inkling FP4· LMArena data1,458.6
62Beam 1.0 501B A23B· LMArena data1,458.5
63GLM 5· LMArena data1,458
64ChatGPT-4o Latest20250326· LMArena data1,457.9
65Step 5 Preview· LMArena data1,457.5
66GPT-6.1 TerraMax· LMArena data1,457.3
67DeepSeek V4 ProHigh, 20260813· LMArena data1,457.3
68Claude Opus 4.5High, 32K, 20251101· LMArena data1,457.2
69Claude Sonnet 5High· LMArena data1,456.2
70GPT 5.1· LMArena data1,456
71Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,455.6
72Gemini 2.5 Pro· LMArena data1,455.4
73MiMo V2 Pro· LMArena data1,454.7
74Qwen3 Max Preview· LMArena data1,454.4
75Qwen3.5 397B A17B· LMArena data1,453.8
76GPT-5.2 Chat20260210· LMArena data1,453.1
77GPT 5.2· LMArena data1,452.1
78Grok 4.20Reasoning, 0309, beta· LMArena data1,452.1
79GPT-5 Chat· LMArena data1,450.4
80MiMo V2.5· LMArena data1,450.3
81GPT 5.2High· LMArena data1,449.5
82Grok 4.6High· LMArena data1,449.2
83Gemini 3 FlashMinimal· LMArena data1,448.8
84Hy3 (Deep Infra)· LMArena data1,447.9
85Qwen3.6 Plus· LMArena data1,447.5
86Grok 4.20 Multi-Agent0309, beta· LMArena data1,446.7
87Qwen3.7 Plus· LMArena data1,446.3
88Qwen 3.8 27B· LMArena data1,446.1
89GLM 4.7· LMArena data1,445.6
90Grok 4.20 Beta 1· LMArena data1,444.2
91MiMo V2 Omni· LMArena data1,444.1
92ERNIE 5.00110· LMArena data1,443.9
93Mistral Medium 3.5· LMArena data1,443.7
94DeepSeek V4 Flash· LMArena data1,443.1
95NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,443.1
96MiniMax M3· LMArena data1,442.8
97Kimi K2.5Thinking· LMArena data1,442.1
98GPT-5.5 Instant· LMArena data1,441.3
99DeepSeek V3.2 Exp· LMArena data1,440.6
100Gemini 3.5 Flash Lite· LMArena data1,440.5

Showing 51–100 of 165 results.

Data credits: LMArena, CC BY 4.0 (licence)