Skip to content

Benchmark

Arena ELO - Industry Software and It Services

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

Models measured
366
Scores recorded
423
Sources
1
IQ weight
1.29

Score distribution

1,322.6
Mean
1,374.8
Median
161.3
Std dev
1,081.5
10th percentile
1,486.1
90th percentile
719.3
Min
719.31,552.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.29 for chat models, measured over 366 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151DeepSeek V3.1· LMArena data1,427.2
152DeepSeek V3.1Thinking· LMArena data1,427.1
153DeepSeek V3.1 TerminusThinking· LMArena data1,425.3
154Gemini 2.5 Flash· LMArena data1,425.2
155Qwen3 VL 235Bthinking· LMArena data1,425.1
156GPT-6 LunaMax· LMArena data1,422.4
157nova-experimental-chat10-20· LMArena data1,422.2
158Hunyuan Vision 1.5 Thinking· LMArena data1,421.4
159MiMo V2 FlashThinking· LMArena data1,421.3
160Grok 4.7xHigh· LMArena data1,420.1
161GPT 5High· LMArena data1,420.1
162Grok 4.1 FastReasoning· LMArena data1,418
163Qwen3 30B A3B Instruct2507· LMArena data1,416.6
164Grok 4 FastReasoning· LMArena data1,416.5
165Qwen3.5 Flash· LMArena data1,416.4
166MiniMax-M2.1 Preview· LMArena data1,415.6
167Grok 4.3· LMArena data1,415.4
168Qwen3.5 35B A3B· LMArena data1,415.1
169OpenAI o32025-04-16· LMArena data1,414.5
170Muse Glimmer· LMArena data1,413.8
171Gemini 3.1 Flash Lite· LMArena data1,413
172GPT-4.5 Preview2025-02-27· LMArena data1,412
173Grok 40709· LMArena data1,410.9
174DeepSeek V3.1 Terminus· LMArena data1,409.8
175Nemotron 3 Super 120B A12B· LMArena data1,409.1
176Qwen 3 235B A22BNon-Thinking· LMArena data1,408.8
177Claude Opus 4Thinking 16K, 20250514· LMArena data1,408.7
178Gemini 2.5 Flash Preview09-2025· LMArena data1,408.7
179Hunyuan T120250711· LMArena data1,408.5
180GPT-5.3 Chat· LMArena data1,407.8
181GPT-5 Chat· LMArena data1,407.4
182GPT 5.4 NanoHigh· LMArena data1,402
183Granite 4.2 30B· LMArena data1,402
184GLM 4.5 Air· LMArena data1,401.2
185Ling Flash 2.0· LMArena data1,399.8
186Nova 2 Lite· LMArena data1,394.2
187GPT-5 miniHigh· LMArena data1,394.1
188Kimi K2 Preview0905· LMArena data1,393.7
189Qwen3 Next 80B A3Bthinking· LMArena data1,393.5
190Qwen3 Coder· LMArena data1,392.9
191GLM 4.6v· LMArena data1,391.7
192GPT 4.12025-04-14· LMArena data1,391.2
193Hunyuan TurboS20250416· LMArena data1,391.2
194GLM 4.7 Flash· LMArena data1,388.5
195GPT OSS 120B· LMArena data1,387.4
196Mercury 2· LMArena data1,386.4
197Qwen 3 235B A22B· LMArena data1,386
198Mistral Medium 32505· LMArena data1,385.2
199Kimi K2 Preview0711· LMArena data1,384.3
200Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,384.2

Showing 151–200 of 423 results.

Data credits: LMArena, CC BY 4.0 (licence)