All Comparisons

Claude Haiku 4.5 vs GPT-4.1

Claude Haiku 4.5
Anthropic 🇺🇸
59.3
#125—
medium
$1.00/M in · $5.00/M out
200K context
GPT-4.1
OpenAI 🇺🇸
32.8
#238—
high
$2.00/M in · $8.00/M out
1.0M context
Most Affordable
Claude Haiku 4.5
$1.00/M input
Largest Context
GPT-4.1
1.0M tokens
Best Benchmark Score
Claude Haiku 4.5
59.3/100

Model Specifications

SpecClaude Haiku 4.5GPT-4.1
ProviderAnthropicOpenAI
Release DateOct 2025Apr 2025
Knowledge Cutoff2025-02-012024-06-01
ParametersUndisclosedUndisclosed
Context Window200K1.0M
Max Output——
Open SourceNoNo
Licenseproprietaryproprietary
Tokenizer——
Modality——
Reasoning ModelNoNo
ModeratedNoNo

Pricing Comparison

Price (per 1M tokens)Claude Haiku 4.5GPT-4.1
Input$1.00$2.00
Output$5.00$8.00

API Provider Pricing

Capabilities

FeatureClaude Haiku 4.5GPT-4.1
Text Input
Image Input (Vision)
Audio Input
Video Input
File Input
Image Output
Audio Output
Tool Use
Structured Output (JSON)
Streaming
Reasoning Tokens
Web Search
Temperature Control
Top-P Sampling
Stop Sequences
Seed (Reproducibility)
Log Probabilities

Category Comparison

Benchmark-by-Benchmark

general

BenchmarkClaude Haiku 4.5GPT-4.1
MMMLU
83
87.3

coding

BenchmarkClaude Haiku 4.5GPT-4.1
SWE-bench Verified
73.3
54.6
TerminalBench
41
—

math

BenchmarkClaude Haiku 4.5GPT-4.1
AIME 2025
80.7
46.4

reasoning

BenchmarkClaude Haiku 4.5GPT-4.1
GPQA Diamond
73
66.3
Humanity's Last Exam—
5.4

agent

BenchmarkClaude Haiku 4.5GPT-4.1
OSWorld
50.7
—
TAU-Bench Retail—
68

multimodal

BenchmarkClaude Haiku 4.5GPT-4.1
MMMU—
74.8
CharXiv Reasoning—
56.7

Category Winners

coding
Claude Haiku 4.5
70.3
math
Claude Haiku 4.5
53.2
reasoning
Claude Haiku 4.5
61.0
general
GPT-4.1
66.0
multimodal
GPT-4.1
40.2
agent
Claude Haiku 4.5
58.5

Compare More Models

Claude Haiku 4.5 vs GPT-4o
GPT-4.1 vs GPT-4o mini
Gemini 2.5 Flash vs GPT-4.1
Gemini 2.0 Flash vs GPT-4.1
DeepSeek V3 vs GPT-4.1
GPT-4.1 vs Llama 4 Scout
Codestral vs GPT-4.1
Command R+ vs GPT-4.1

Frequently Asked Questions