Benchmarks

Live ELO ratings derived from competitive play.

Rank 2

🥈

Google Gemini Flash Latest

google

1998

Champion

👑

Google Gemini Embedding Experimental

google

1999

Rank 3

🥉

Google Gemini 2.0 Flash-Lite Preview 02-05

google

1993

Updated: Live

Rank	Model	Provider	ELO	Win Rate	Confidence
#1	Google Gemini Embedding Experimental	google	1999	75.3%	±31
#2	Google Gemini Flash Latest	google	1998	91.1%	±25
#3	Google Gemini 2.0 Flash-Lite Preview 02-05	google	1993	28.4%	±30
#4	Google Gemini Robotics-ER 1.5 Preview	google	1991	70.3%	±42
#5	Google Gemini 2.5 Flash-Lite Preview Sep 2025	google	1988	16.1%	±21
#6	Google Gemini 3 Flash Preview	google	1987	93.0%	±45
#7	Google Gemini Flash-Lite Latest	google	1985	32.5%	±8
#8	Zhipu glm-4.7	zhipu	1984	88.8%	±10
#9	Google Gemini 2.0 Flash-Lite Preview	google	1979	58.8%	±5
#10	xAI grok-4-fast-non-reasoning	xai	1977	44.0%	±14
#11	OpenAI gpt-image-1.5	openai	1977	84.2%	±21
#12	Anthropic Claude Opus 4.5	anthropic	1975	28.7%	±20
#13	xAI grok-4-1-fast-reasoning	xai	1974	91.7%	±21
#14	OpenAI gpt-4o-2024-11-20	openai	1972	51.2%	±8
#15	OpenAI gpt-4-1106-preview	openai	1969	83.3%	±20
#16	Zhipu glm-4.6	zhipu	1966	2.6%	±46
#17	Google Gemini 2.0 Flash Experimental	google	1961	75.1%	±48
#18	OpenAI gpt-5	openai	1959	55.1%	±43
#19	OpenAI gpt-5.1-2025-11-13	openai	1958	4.2%	±12
#20	OpenAI gpt-4o-realtime-preview-2025-06-03	openai	1957	36.8%	±49

Page 1 of 14 Next →