Skip to content

Benchmark

Arena ELO Text Factuality - Russian

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

Models measured
130
Scores recorded
146
Sources
1
IQ weight
2.22

Score distribution

1,450.9
Mean
1,456.3
Median
39.2
Std dev
1,407.8
10th percentile
1,497.3
90th percentile
1,300.5
Min
1,300.51,534.6
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 2.22 for chat models, measured over 130 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101DeepSeek V3.2Thinking· LMArena data1,434.2
102MiniMax M3· LMArena data1,433.7
103Gemini 2.5 Flash· LMArena data1,433.7
104Qwen 3.8 27B· LMArena data1,433.4
105Grok 4.1· LMArena data1,431.7
106Mistral Large 3· LMArena data1,431.7
107GPT-5.3 Chat· LMArena data1,430.3
108Mistral Medium 3.12508· LMArena data1,430.3
109NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,429.5
110GLM 4.7· LMArena data1,429.4
111MiMo V2 Omni· LMArena data1,429.1
112Grok 4.3· LMArena data1,428.8
113Qwen3 235B A22B Instruct 25072507· LMArena data1,428.3
114Mistral Large 4· LMArena data1,425.6
115Beam 1.0 501B A23B· LMArena data1,425.5
116MiMo V2.5· LMArena data1,422.2
117Inkling Small· LMArena data1,420.3
118Nemotron 3 UltraNVFP4· LMArena data1,420
119Qwen3.5 122B-A10B· LMArena data1,419.9
120DeepSeek V3.2 Exp· LMArena data1,419.6
121Claude Haiku 5.5High· LMArena data1,417.1
122MiniMax M2.7· LMArena data1,414.9
123Claude Haiku 4.520251001· LMArena data1,414.4
124Mistral Medium 3.5· LMArena data1,414.2
125Step 3.5 Flash· LMArena data1,413
126Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,412.2
127LongCat-Flash-Chat Exp2602· LMArena data1,412
128Qwen3.5 27B· LMArena data1,411.9
129MiniMax-M2.1 Preview· LMArena data1,411.3
130GPT 5.4 NanoHigh· LMArena data1,409.4
131MiMo V2 FlashNon-Thinking· LMArena data1,407.8
132Kimi K2 Thinking· LMArena data1,407.7
133Qwen3.5 Flash· LMArena data1,404.6
134nova-experimental-chat11-10· LMArena data1,401.1
135Gemini 2.5 Flash Preview09-2025· LMArena data1,400.4
136Grok 4.1 FastReasoning· LMArena data1,399.3
137Qwen3.5 35B A3B· LMArena data1,398.7
138Solar Pro 4· LMArena data1,396.7
139MiniMax M2.5· LMArena data1,384.8
140Nova 2 Lite· LMArena data1,374.2
141Trinity Large Thinking· LMArena data1,372.6
142GLM 4.7 Flash· LMArena data1,364.1
143Trinity Large Preview· LMArena data1,358.3
144Nemotron 3 Nano 30B A3BBF16· LMArena data1,334.8
145Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,318.2
146Olmo 3.1 32B Instruct· LMArena data1,300.5

Showing 101–146 of 146 results.

Data credits: LMArena, CC BY 4.0 (licence)