GPTCrunch

Compare Models

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

Anthropic logoClaude Haiku 3.5

Anthropic

Mistral AI logoMistral Small

Mistral AI

DeepSeek logoDeepSeek-R1-Distill-Llama-8B

DeepSeek

Add Model
MMLU
Claude Haiku 3.5
85.2
Mistral Small
81.2
DeepSeek-R1-Distill-Llama-8B
73.0
HumanEval
Claude Haiku 3.5
88.1
Mistral Small
84.8
DeepSeek-R1-Distill-Llama-8B
74.0
GSM8K
Claude Haiku 3.5
91.6
Mistral Small
88.4
DeepSeek-R1-Distill-Llama-8B
87.0
GPQA
Claude Haiku 3.5
41.6
Mistral Small
37.5
DeepSeek-R1-Distill-Llama-8B
44.0
MGSM
Claude Haiku 3.5
88.5
Mistral Small
80.1
DeepSeek-R1-Distill-Llama-8B
0.0
ARC-Challenge
Claude Haiku 3.5
93.5
Mistral Small
89.5
DeepSeek-R1-Distill-Llama-8B
0.0
HellaSwag
Claude Haiku 3.5
89.5
Mistral Small
84.0
DeepSeek-R1-Distill-Llama-8B
78.0
MATH
Claude Haiku 3.5
69.2
Mistral Small
61.0
DeepSeek-R1-Distill-Llama-8B
80.0
SWE-bench
Claude Haiku 3.5
40.6
Mistral Small
18.5
DeepSeek-R1-Distill-Llama-8B
0.0
MMMLU
Claude Haiku 3.5
81.7
Mistral Small
73.2
DeepSeek-R1-Distill-Llama-8B
0.0
ModelInputOutputBlended*
Claude Haiku 3.5
$0.80$4.00$2.40
Mistral Small
$0.10$0.30$0.20
DeepSeek-R1-Distill-Llama-8B
$0.07$0.14$0.11

*Blended = average of input and output price

Spec
Claude Haiku 3.5
Mistral Small
DeepSeek-R1-Distill-Llama-8B
Context Window200K32K128K
Max Output8K4KN/A
TTFT150ms140msN/A
Speed160 tok/s170 tok/sN/A
ParametersN/A24B8B
ArchitectureTransformerTransformerDense Transformer
Open SourceNoNoYes
Tierbudgetbudgetbudget

Quick Verdict

Best Performance

Claude Haiku 3.5

Best Value

DeepSeek-R1-Distill-Llama-8B

Fastest

Mistral Small