⌕Is ___ SOTA?
benchmarks / lmarena-text-math

LMArena Text (style-controlled, math)

Arena score. Status display_only. Contamination risk low. Maintainer LMArena. Source.

Display only.This benchmark cannot decide a crown under methodology v1.0.
ModelScoreDateKind
O11412.3228774754292025-07-28snapshot
O1 Preview1379.24832559045512025-06-11snapshot
O1 Mini1294.97059020823462025-04-16snapshot
Claude 3.5 Sonnet1273.89372012219842025-03-11snapshot
Gemini 1.5 Pro 0021263.61007129105382025-02-27snapshot
DeepSeek V31243.82369221197022025-01-22snapshot
Llama 3.1 405B Instruct Bf161244.78447033292025-02-11snapshot
Llama 3.1 405B Instruct Fp81244.03480106165082025-02-05snapshot
Athene V2 Chat1242.75746446199222025-02-03snapshot
Qwen2 5 Plus 11271243.90364537578672025-01-24snapshot
YI Lightning1242.18395563619222025-01-28snapshot
Step 2 16k Exp 2024121244.5127901483972025-02-11snapshot
DeepSeek R11412.44735095667332025-08-01snapshot
Qwen2 51288.81867069567082025-03-25snapshot
Gemini 2.0 Flash 0011292.3040954681822025-04-09snapshot
O3 Mini1385.33285562196672025-06-18snapshot
Gemini 2.0 Flash Lite Preview 02.051250.92890108018882025-02-17snapshot
Qwen Plus 01251255.78767399424992025-02-21snapshot
O3 Mini1400.8535294002012025-07-01snapshot
Claude 3.7 Sonnet1292.76004564325132025-04-16snapshot
GPT-4.5 Preview1415.46853497635062025-08-04snapshot
Grok 3 Preview 02.241359.45721750755552025-05-22snapshot
Claude 3.7 Sonnet 20250219 Thinking1381.48107927550152025-06-18snapshot
ChatGPT 4O Latest1378.0384357868312025-06-11snapshot
Qwq 32B1292.8517595099622025-04-08snapshot
DeepSeek V3 03241294.74598839087682025-04-16snapshot
O31453.1193942454332026-02-06snapshot
O4 Mini1430.1533345046482025-09-18snapshot
Qwen3 235B A22b1411.84098863620652025-07-28snapshot
Qwen3 32B1404.7474075736772025-07-07snapshot