Skip to content

Benchmark

Arena ELO - Industry Life and Physical and Social Science

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

Models measured
364
Scores recorded
421
Sources
1
IQ weight
1.24

Score distribution

1,316.4
Mean
1,364.4
Median
158.9
Std dev
1,071.5
10th percentile
1,475.1
90th percentile
800.9
Min
800.91,549.3
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.24 for chat models, measured over 364 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
151Kimi K2 Thinking· LMArena data1,418.9
152GPT-5.4 miniHigh· LMArena data1,417.3
153Claude Opus 4.120250805· LMArena data1,416.5
154MiniMax M2.7· LMArena data1,415.7
155GPT-5 Chat· LMArena data1,415.7
156MiniMax-M2.1 Preview· LMArena data1,415.5
157Claude Haiku 5.5High· LMArena data1,415
158Step 3.5 Flash· LMArena data1,414.7
159Qwen3.5 Flash· LMArena data1,414.6
160GPT-6.2 AstraMax· LMArena data1,414.6
161Qwen3.5 35B A3B· LMArena data1,412.9
162Qwen3 Max2025-09-23· LMArena data1,412.6
163Grok 4.7xHigh· LMArena data1,412
164Qwen3 VL 235Bthinking· LMArena data1,411.6
165Inkling 2 Small· LMArena data1,408.8
166Grok 4 FastNon-Reasoning· LMArena data1,408.4
167Hunyuan Vision 1.5 Thinking· LMArena data1,407.7
168GLM 4.5 Air· LMArena data1,407.5
169nova-experimental-chat10-09· LMArena data1,406.3
170Claude Haiku 4.520251001· LMArena data1,405.7
171Qwen 3 235B A22BNon-Thinking· LMArena data1,405.6
172nova-experimental-chat26-01-10· LMArena data1,403.5
173GPT 5High· LMArena data1,403.2
174Solar Pro 4· LMArena data1,402.3
175Hunyuan TurboS20250416· LMArena data1,400.5
176MiMo V2 FlashThinking· LMArena data1,399.7
177Grok 4.3· LMArena data1,399.5
178Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,395.6
179Qwen3 30B A3B Instruct2507· LMArena data1,393
180GLM 4.6v· LMArena data1,389.5
181Muse Glimmer· LMArena data1,388.5
182GPT-6 SolMax· LMArena data1,387.9
183Nemotron 3 Super 120B A12B· LMArena data1,387.3
184GPT-6 LunaMax· LMArena data1,386.8
185Kimi K2 Preview0905· LMArena data1,386.2
186GPT-5.3 Chat· LMArena data1,385.5
187Qwen3 Next 80B A3Bthinking· LMArena data1,384.6
188Granite 4.2 30B· LMArena data1,383.4
189Gemma 3 27B IT· LMArena data1,383.1
190Nova 2 Lite· LMArena data1,382.8
191GPT 4.12025-04-14· LMArena data1,382.1
192Grok 3 MiniHigh· LMArena data1,381.9
193DeepSeek V30324· LMArena data1,381.6
194GPT OSS 120B· LMArena data1,381.5
195Qwen2.5-Max· LMArena data1,381.2
196Mistral Medium 32505· LMArena data1,380.7
197Ling Flash 2.0· LMArena data1,380.5
198DeepSeek R1· LMArena data1,375.2
199Grok 3 Minibeta· LMArena data1,374.3
200GPT 5.4 NanoHigh· LMArena data1,374.2

Showing 151–200 of 421 results.

Data credits: LMArena, CC BY 4.0 (licence)