Skip to content

Benchmark

Arena ELO Text Factuality - Creative Writing

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

Models measured
142
Scores recorded
160
Sources
1
IQ weight
2.07

Score distribution

1,418.6
Mean
1,420.8
Median
43.1
Std dev
1,361.3
10th percentile
1,468.6
90th percentile
1,295.9
Min
1,295.91,508.7
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.07 for chat models, measured over 142 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51Claude Sonnet 4.6· LMArena data1,441.3
52Muse Spark 1.2xHigh· LMArena data1,440.6
53Qwen3.7 Plus· LMArena data1,439.6
54DeepSeek-V4-Pro PreviewHigh· LMArena data1,439.4
55GPT 5.4· LMArena data1,438.7
56DeepSeek V4.1 Flash 0910Max· LMArena data1,438.6
57Grok 4.20Reasoning, 0309, beta· LMArena data1,438.6
58GLM 5.3 Flash· LMArena data1,438
59Kimi K2.6· LMArena data1,437.5
60Gemini 3 FlashMinimal· LMArena data1,436.7
61GPT 5.1High· LMArena data1,436.4
62Claude Opus 4.120250805· LMArena data1,436.4
63GPT-6.1 SolMax· LMArena data1,436.2
64Grok 4.6High· LMArena data1,436.1
65DeepSeek V4 ProHigh, 20260813· LMArena data1,435.5
66ERNIE-5.0-Preview1203· LMArena data1,435.5
67GPT-6 AstraMax· LMArena data1,434.8
68Muse Spark 1.1· LMArena data1,434.8
69Claude Sonnet 4.5High, 32K, 20250929· LMArena data1,434.6
70ERNIE 5.00110· LMArena data1,433.8
71GPT-5.6 TerraxHigh· LMArena data1,428.4
72Kimi K2.5Thinking· LMArena data1,427.7
73Gemini 3.5 Flash Lite· LMArena data1,427.3
74GPT-5.5 Instant· LMArena data1,425.6
75Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,424.9
76Step 5 Preview· LMArena data1,424.6
77MiMo V2 Pro· LMArena data1,423.7
78Claude Sonnet 5High· LMArena data1,422.4
79Grok 4.1Thinking· LMArena data1,421.1
80GPT-6.2 SolMax· LMArena data1,420.8
81GPT-6.1 TerraMax· LMArena data1,420.2
82GPT 5.1· LMArena data1,419.3
83GPT-6 LunaMax· LMArena data1,417.8
84ChatGPT-4o Latest20250326· LMArena data1,416.7
85Qwen3.5 397B A17B· LMArena data1,416.2
86DeepSeek V4 Flash· LMArena data1,416.1
87GPT-5.6 LunaxHigh· LMArena data1,416.1
88MiMo V2.6 Flash· LMArena data1,415.9
89Grok 4.1· LMArena data1,415.7
90Hy3 (Deep Infra)· LMArena data1,415
91GLM 4.6· LMArena data1,414.7
92DeepSeek V3.2· LMArena data1,413.6
93Gemini 3.1 Flash Lite· LMArena data1,412.8
94GLM 4.7· LMArena data1,412.4
95Gemini 2.5 Flash· LMArena data1,411.6
96DeepSeek V3.2 Exp· LMArena data1,411.3
97DeepSeek-V4-Flash PreviewHigh· LMArena data1,409.8
98Qwen3.6 Plus· LMArena data1,409.6
99Inkling FP4· LMArena data1,409.6
100GPT-5.2 Chat20260210· LMArena data1,409.3

Showing 51–100 of 160 results.

Data credits: LMArena, CC BY 4.0 (licence)