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
151nova-experimental-chat11-10· LMArena data1,394.4
152Qwen 3 235B A22BNon-Thinking· LMArena data1,393.6
153Gemini 2.5 Flash Preview09-2025· LMArena data1,393.4
154Claude Opus 4Thinking 16K, 20250514· LMArena data1,391.9
155Muse Glimmer· LMArena data1,391.4
156Kimi K2 Thinking· LMArena data1,390.4
157nova-experimental-chat26-01-10· LMArena data1,390.2
158GPT-6 LunaMax· LMArena data1,389.9
159Qwen3.5 27B· LMArena data1,388.9
160MiMo V2 FlashNon-Thinking· LMArena data1,388
161Grok 4 FastReasoning· LMArena data1,387.7
162Grok 4.1 FastReasoning· LMArena data1,387.6
163LongCat-Flash-Chat Exp2602· LMArena data1,387.5
164MiniMax-M2.1 Preview· LMArena data1,387.3
165Step 3.5 Flash· LMArena data1,386.1
166Kimi K2 Preview0905· LMArena data1,384.2
167Hunyuan T120250711· LMArena data1,382.3
168Grok 4 FastNon-Reasoning· LMArena data1,382.3
169MiniMax M2.7· LMArena data1,382.2
170Claude Opus 420250514· LMArena data1,380.8
171Claude Haiku 4.520251001· LMArena data1,380.5
172Qwen3.5 Flash· LMArena data1,379.8
173Claude Haiku 5.5High· LMArena data1,378.9
174Inkling 2 Small· LMArena data1,377.2
175Qwen3.5 35B A3B· LMArena data1,376.7
176GPT 4.12025-04-14· LMArena data1,376.4
177MiMo V2 FlashThinking· LMArena data1,373.9
178Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,373.3
179DeepSeek V30324· LMArena data1,372.9
180GLM 4.5 Air· LMArena data1,372.4
181nova-experimental-chat10-20· LMArena data1,370.7
182NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,370.3
183Qwen3 30B A3B Instruct2507· LMArena data1,369.3
184Qwen3 VL 235Bthinking· LMArena data1,368.8
185Hunyuan TurboS20250416· LMArena data1,367
186Qwen3 Coder· LMArena data1,366.4
187Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,363.2
188GPT 5.4 NanoHigh· LMArena data1,362.7
189GPT-5 miniHigh· LMArena data1,361.9
190Kimi K2 Preview0711· LMArena data1,361.8
191MiniMax M2.5· LMArena data1,359.9
192Mistral Medium 32505· LMArena data1,359
193o12024-12-17· LMArena data1,355.7
194Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,355.1
195DeepSeek R1· LMArena data1,354.3
196Qwen2.5-Max· LMArena data1,353
197Grok 3 Minibeta· LMArena data1,352.9
198Claude Sonnet 420250514· LMArena data1,352.2
199Gemini 2.0 Flash001· LMArena data1,351.8
200Solar Pro 4· LMArena data1,351.5

Showing 151–200 of 387 results.

Data credits: LMArena, CC BY 4.0 (licence)