Skip to content

Benchmark

Arena ELO - Russian

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

Models measured
332
Scores recorded
387
Sources
1
IQ weight
1.42

Score distribution

1,322.5
Mean
1,355.7
Median
134.6
Std dev
1,109.2
10th percentile
1,466.9
90th percentile
936.6
Min
936.61,560.5
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.42 for chat models, measured over 332 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101nova-experimental-chat26-02-10· LMArena data1,422
102Claude Opus 4.120250805· LMArena data1,421.2
103Nemotron 3 UltraNVFP4· LMArena data1,421.2
104Gemini 3.1 Flash Lite· LMArena data1,420.4
105Grok 4.6High· LMArena data1,420
106MiniMax M3· LMArena data1,419.1
107GPT-4.5 Preview2025-02-27· LMArena data1,419
108GPT-6.1 TerraMax· LMArena data1,419
109GLM 4.6· LMArena data1,418.5
110GPT-5.4 miniHigh· LMArena data1,417.9
111Qwen3 Max2025-09-23· LMArena data1,417.5
112MiMo V2.6 Flash· LMArena data1,417.4
113Claude Opus 4.1Thinking 16K, 20250805· LMArena data1,416.9
114Grok 3 Preview02-24· LMArena data1,416
115GPT 5.2· LMArena data1,415.3
116Mistral Large 4· LMArena data1,414.9
117Gemini 2.5 Flash· LMArena data1,414.4
118GLM 4.5· LMArena data1,412.7
119Mistral Large 3· LMArena data1,412.1
120Qwen 3.8 27B· LMArena data1,411.8
121GPT 5.2High· LMArena data1,411.6
122Mistral Medium 3.12508· LMArena data1,411.5
123DeepSeek V3.2 ExpThinking· LMArena data1,411.5
124MiMo V2 Omni· LMArena data1,411.3
125Qwen3 235B A22B Instruct 25072507· LMArena data1,411.1
126Qwen3 VL 235B· LMArena data1,409.4
127Grok 40709· LMArena data1,409.2
128GPT-6 SolMax· LMArena data1,407.3
129DeepSeek V3.2Thinking· LMArena data1,407.1
130GPT-5 Chat· LMArena data1,406.5
131OpenAI o32025-04-16· LMArena data1,406.4
132Beam 1.0 501B A23B· LMArena data1,405.4
133DeepSeek V3.1· LMArena data1,404.1
134DeepSeek V3.2 Exp· LMArena data1,404
135Kimi K2.5Instant· LMArena data1,403.9
136Qwen3 Next 80B A3B Instruct· LMArena data1,403.2
137GPT 5High· LMArena data1,401.8
138GPT-6.2 SolMax· LMArena data1,401.2
139Grok 4.7xHigh· LMArena data1,400.7
140DeepSeek V3.1Thinking· LMArena data1,400.5
141Qwen3.5 122B-A10B· LMArena data1,400.4
142Qwen 3 235B A22B2507, thinking· LMArena data1,400.3
143GPT-5.3 Chat· LMArena data1,399.5
144ERNIE-5.0-Preview1022· LMArena data1,399.3
145Grok 4.3· LMArena data1,398.7
146Inkling Small· LMArena data1,397.2
147nova-experimental-chat12-10· LMArena data1,396.7
148Mistral Medium 3.5· LMArena data1,396.6
149LongCat Flash Chat· LMArena data1,395.4
150MiMo V2.5· LMArena data1,395.3

Showing 101–150 of 387 results.

Data credits: LMArena, CC BY 4.0 (licence)