Skip to content

Benchmark

Arena ELO - French

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

Models measured
262
Scores recorded
303
Sources
1
IQ weight
1.87

Score distribution

1,360.8
Mean
1,408.4
Median
127.5
Std dev
1,158.9
10th percentile
1,487.2
90th percentile
945.6
Min
945.61,562.9
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.87 for chat models, measured over 262 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151GPT-5 Chat· LMArena data1,408.4
152GPT 5High· LMArena data1,408.2
153Kimi K2.5Instant· LMArena data1,404
154MiniMax-M2.1 Preview· LMArena data1,403.5
155GPT-6 LunaMax· LMArena data1,403
156DeepSeek V3.1Thinking· LMArena data1,401.5
157GPT-6 SolMax· LMArena data1,400
158Nemotron 3 Super 120B A12B· LMArena data1,399.6
159GLM 4.5 Air· LMArena data1,398.6
160Qwen3 Coder· LMArena data1,398.2
161Qwen2.5-Max· LMArena data1,397.2
162GPT-5.3 Chat· LMArena data1,397.2
163GPT 5.4 NanoHigh· LMArena data1,396.4
164Nemotron 3 Nano 30B A3BBF16· LMArena data1,396.3
165Gemini 2.0 Flash001· LMArena data1,392
166Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,391.1
167Hunyuan TurboS20250416· LMArena data1,390.6
168Gemini 2.5 Flash-Lite PreviewThinking, 06-17· LMArena data1,386.8
169GPT-5 miniHigh· LMArena data1,386.2
170DeepSeek V30324· LMArena data1,385.1
171GPT 4.12025-04-14· LMArena data1,381.4
172Kimi K2 Preview0905· LMArena data1,380.6
173Nova 2 Lite· LMArena data1,380.2
174Nemotron 3.5 Lightning 30B A3BNVFP4· LMArena data1,378.1
175Trinity Large Preview· LMArena data1,375.2
176Kimi K2 Preview0711· LMArena data1,373.6
177Claude Opus 4Thinking 16K, 20250514· LMArena data1,372.5
178MiniMax M1· LMArena data1,370.9
179Mistral Medium 32505· LMArena data1,369.4
180Qwen 3 235B A22BNon-Thinking· LMArena data1,368.7
181Trinity Large Thinking· LMArena data1,368.7
182GPT OSS 120B· LMArena data1,368.5
183Gemma 3 27B IT· LMArena data1,367.5
184DeepSeek R1· LMArena data1,366.5
185MiniMax M2.5· LMArena data1,364.1
186Claude Sonnet 420250514· LMArena data1,362.9
187o4 Mini2025-04-16· LMArena data1,362.7
188Claude Opus 420250514· LMArena data1,359.5
189Qwen 3 235B A22B· LMArena data1,358.7
190GPT-4.1 mini2025-04-14· LMArena data1,357.6
191Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,355.2
192Grok 3 Minibeta· LMArena data1,355.2
193Qwen3 Next 80B A3Bthinking· LMArena data1,352.6
194Qwen3 30B A3B· LMArena data1,350.2
195Command A03-2025· LMArena data1,349.5
196Gemini 2.0 Flash-Lite Preview02-05· LMArena data1,347.2
197Grok 3 MiniHigh· LMArena data1,345.8
198O1 Preview· LMArena data1,344.4
199o12024-12-17· LMArena data1,344.1
200DeepSeek V3· LMArena data1,343

Showing 151–200 of 303 results.

Data credits: LMArena, CC BY 4.0 (licence)