Compare Models

Select up to 4 models to compare benchmarks, pricing, and capabilities side by side.

o3-mini

OpenAI

DeepSeek-R1

DeepSeek

Llama 3.2 90B Vision

Meta

Add Model

MMLU

o3-mini

86.9

DeepSeek-R1

90.8

Llama 3.2 90B Vision

86.0

HumanEval

o3-mini

92.9

DeepSeek-R1

92.8

Llama 3.2 90B Vision

84.0

GSM8K

o3-mini

97.9

DeepSeek-R1

97.3

Llama 3.2 90B Vision

92.0

GPQA

o3-mini

77.0

DeepSeek-R1

71.5

Llama 3.2 90B Vision

48.0

MGSM

o3-mini

89.5

DeepSeek-R1

92.8

Llama 3.2 90B Vision

0.0

ARC-Challenge

o3-mini

96.0

DeepSeek-R1

97.2

Llama 3.2 90B Vision

0.0

HellaSwag

o3-mini

92.5

DeepSeek-R1

93.8

Llama 3.2 90B Vision

88.0

MATH

o3-mini

97.0

DeepSeek-R1

97.3

Llama 3.2 90B Vision

0.0

SWE-bench

o3-mini

49.3

DeepSeek-R1

49.2

Llama 3.2 90B Vision

0.0

MMMLU

o3-mini

83.5

DeepSeek-R1

87.5

Llama 3.2 90B Vision

0.0

Model	Input	Output	Blended*
o3-mini	$1.10	$4.40	$2.75
DeepSeek-R1	$0.55	$2.19	$1.37
Llama 3.2 90B Vision	$0.35	$0.40	$0.38

*Blended = average of input and output price

Spec	o3-mini	DeepSeek-R1	Llama 3.2 90B Vision
Context Window	200K	128K	128K
Max Output	100K	8K	4K
TTFT	800ms	900ms	400ms
Speed	75 tok/s	60 tok/s	55 tok/s
Parameters	N/A	685B (37B active)	90B
Architecture	Transformer + CoT	Transformer (MoE) + CoT	Transformer
Open Source	No	Yes	Yes
Tier	mid	mid	mid

Quick Verdict

Best Performance

DeepSeek-R1

Best Value

Llama 3.2 90B Vision

Fastest

o3-mini