o3

Benchmark	Category	Top Score	Info	Self Reported	Source
Ai2 SciArena	-	1172	-	No	Source
Aider-Polyglot	code	0.81	High Reasoning Effort	No	Source
AIME 2024	math	0.92	-	Yes	Source
AIME 2025	math	0.98	-	Yes	Source
ARC-AGI-1	-	0.53	Medium Reasoning Effort	No	Source
ARC-AGI-2	-	0.03	Medium Reasoning Effort	No	Source
BrowseComp Long Context 128k	-	0.88	High Reasoning Effort	Yes	Source
Codeforces	-	2517	-	Yes	Source
Confabulations	-	14.38	High Reasoning Effort	No	Source
Elimation Game	-	4.38	Medium Reasoning Effort	No	Source
EQ-Bench 3	-	1500	-	No	Source
FActScore hallucination rate	hallucinations	0.23	High Reasoning Effort	Yes	Source
GPQA Diamond	general-knowledge	0.83	-	Yes	Source
Graphwalks bfs <128k	-	0.77	High Reasoning Effort	Yes	Source
Graphwalks parents <128k	-	0.73	High Reasoning Effort	Yes	Source
Humanity's Last Exam	-	0.20	-	Yes	Source
LisanBench	-	1036	-	No	Source
LiveBench	-	0.74	High Reasoning Effort	No	Source
LMArena Text	-	1449	-	No	Source
LMArena WebDev	-	1190	16th June 2025	No	Source
LongFact-Concepts hallucination rate	hallucinations	0.05	High Reasoning Effort	Yes	Source
LongFact-Objects hallucination rate	hallucinations	0.07	High Reasoning Effort	Yes	Source
NYT Connections	-	0.80	High Reasoning Effort	No	Source
OpenAI-MRCR: 2 needle 128k	-	0.55	High Reasoning Effort	Yes	Source
SimpleBench	-	0.53	High Reasoning Effort	No	Source
Thematic Generalisation	-	1.83	Medium Reasoning Effort	No	Source
VideoMME	-	0.85	High Reasoning Effort	Yes	Source

Use the selector to switch benchmarks and see how this model stacks up against its closest competitors.

Compare this model with the leading peers for the selected benchmark.

Benchmark

0.81

Rank #4/34

34 models

Showing 11 models around the selected model (out of 34 total).

Preparing your page