Anthropic
Claude Haiku 4.5
VS
OpenAI
GPT-5.4 mini
Decision Recommendation
👑 GPT-5.4 mini strictly dominates Claude Haiku 4.5 across all metrics. It is cheaper, faster, and smarter. There is no major reason to choose Claude Haiku 4.5 over it.
Model Specs
Claude Haiku 4.5
Benchmarks & Scores
Coding (swe-bench-pro)
39.5%Reasoning (gpqa-diamond)
73%Cost & Performance
Cost (per 1M tokens)
$2.00Input: $1.00 | Output: $5.00Speed
98.5 tpsContext Window
200k tokensModel Specs
GPT-5.4 mini
Benchmarks & Scores
Coding (swe-bench-pro)Winner (+14.9%)
54.4%Reasoning (gpqa-diamond)Winner (+14.5%)
87.5%Cost & Performance
Cost (per 1M tokens)1.2x cheaper
$1.69Input: $0.75 | Output: $4.50Speed2.0x faster
201 tpsContext WindowLarger
400k tokensWant to customize weights or add more models?
Open our interactive dashboard where you can adjust your priority levels for speed, budget, or accuracy slider-bars and watch model rankings calculate dynamically.
Customize in Interactive Dashboard