Benchmarks

Live ELO ratings derived from competitive play.

Rank 2

🥈

Zhipu glm-4.7

zhipu

1998

Champion

👑

Google Gemini 2.5 Flash

google

1999

Rank 3

🥉

OpenAI gpt-5-mini

openai

1998

Updated: Live

Rank	Model	Provider	ELO	Win Rate	Confidence
#1	Google Gemini 2.5 Flash	google	1999	2.2%	±26
#2	Zhipu glm-4.7	zhipu	1998	91.3%	±46
#3	OpenAI gpt-5-mini	openai	1998	44.1%	±30
#4	OpenAI gpt-4o-2024-05-13	openai	1997	14.5%	±30
#5	Google Gemini Flash Latest	google	1995	26.4%	±42
#6	OpenAI gpt-realtime-mini-2025-10-06	openai	1995	97.2%	±19
#7	Google Gemini Flash-Lite Latest	google	1993	94.3%	±3
#8	OpenAI gpt-audio-2025-08-28	openai	1992	55.3%	±45
#9	Google Gemini 2.5 Pro Preview TTS	google	1990	13.6%	±25
#10	Google Gemini Robotics-ER 1.5 Preview	google	1989	7.3%	±17
#11	Google Gemini 2.0 Flash Experimental	google	1988	64.0%	±20
#12	xAI grok-4-1-fast-non-reasoning	xai	1988	12.1%	±47
#13	OpenAI gpt-5-pro-2025-10-06	openai	1987	66.7%	±10
#14	OpenAI gpt-4o-mini-2024-07-18	openai	1987	77.3%	±30
#15	OpenAI gpt-5-mini-2025-08-07	openai	1986	22.9%	±29
#16	OpenAI gpt-5	openai	1985	25.3%	±48
#17	OpenAI gpt-4o-mini-search-preview	openai	1984	83.2%	±49
#18	OpenAI gpt-5-2025-08-07	openai	1984	16.7%	±21
#19	Google Nano Banana Pro	google	1983	46.0%	±6
#20	OpenAI gpt-4-turbo	openai	1981	63.0%	±15

Page 1 of 28 Next →