Skip to content

Benchmark

Arena ELO - Industry Mathematical

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

Models measured
348
Scores recorded
402
Sources
1
IQ weight
1.25

Score distribution

1,321.4
Mean
1,367.7
Median
154.1
Std dev
1,094.5
10th percentile
1,481.4
90th percentile
833.6
Min
833.61,566.4
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.25 for chat models, measured over 348 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-6 SolMax· LMArena data1,412.6
152Qwen3 30B A3B Instruct2507· LMArena data1,412.2
153Mistral Medium 3.12508· LMArena data1,412.1
154ERNIE-5.0-Preview1203· LMArena data1,411.4
155Qwen3.5 35B A3B· LMArena data1,411.4
156MiMo V2 FlashNon-Thinking· LMArena data1,410.9
157GLM 4.7· LMArena data1,410.9
158GPT-4.5 Preview2025-02-27· LMArena data1,410.6
159GPT 5.4 NanoHigh· LMArena data1,408.8
160GPT-5.5 Instant· LMArena data1,407.9
161Grok 4.1· LMArena data1,407.4
162ChatGPT-4o Latest20250326· LMArena data1,406.4
163Grok 3 Preview02-24· LMArena data1,406.3
164Nemotron 3 Super 120B A12B· LMArena data1,405.4
165NVIDIA Nemotron 3.5 Super VL 120BNVFP4· LMArena data1,405.3
166GPT 5High· LMArena data1,404.4
167Grok 4 FastReasoning· LMArena data1,402.9
168Grok 4.1 FastReasoning· LMArena data1,402.6
169Qwen 3 235B A22BNon-Thinking· LMArena data1,401.2
170Kimi K2 Preview0905· LMArena data1,400.1
171o3 MiniHigh· LMArena data1,398.7
172Llama 3.3 Nemotron Super 49B v1.5· LMArena data1,397.9
173GPT-5 Chat· LMArena data1,397
174Grok 4.3· LMArena data1,396.2
175GLM 4.5 Air· LMArena data1,395.8
176Qwen 3 235B A22B· LMArena data1,395.8
177Hunyuan T120250711· LMArena data1,392.3
178Claude Opus 4Thinking 16K, 20250514· LMArena data1,391.8
179Qwen3 Next 80B A3Bthinking· LMArena data1,391.4
180o12024-12-17· LMArena data1,389.8
181DeepSeek R1· LMArena data1,389.5
182MiMo V2 FlashThinking· LMArena data1,389.1
183GPT OSS 120B· LMArena data1,387
184GPT-5.3 Chat· LMArena data1,385.3
185GPT-5 miniHigh· LMArena data1,381.2
186O1 Preview· LMArena data1,380.3
187Muse Glimmer· LMArena data1,380.2
188o3 Mini· LMArena data1,379.2
189MiniMax M2.5· LMArena data1,378.9
190Claude Sonnet 4Thinking 32K, 20250514· LMArena data1,378.7
191o4 Mini2025-04-16· LMArena data1,378.5
192Gemini 2.5 Flash-Lite PreviewNon-Thinking, 09-2025· LMArena data1,377.3
193Claude Opus 420250514· LMArena data1,377.1
194Step3· LMArena data1,376.8
195Nemotron 3 Nano 30B A3BBF16· LMArena data1,373.9
196MiniMax M2· LMArena data1,373.3
197Grok 3 MiniHigh· LMArena data1,369.2
198GLM 4.7 Flash· LMArena data1,368.6
199Nova 2 Lite· LMArena data1,368.2
200Ling Flash 2.0· LMArena data1,367.7

Showing 151–200 of 402 results.

Data credits: LMArena, CC BY 4.0 (licence)