Compare · ModelsLive · 2 picked · head to head
GPT-5.4 Mini vs Claude 3.5 Haiku
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.4 Mini wins on 5/5 benchmarks
GPT-5.4 Mini wins 5 of 5 shared benchmarks. Leads in math · knowledge · coding.
Category leads
math·GPT-5.4 Miniknowledge·GPT-5.4 Minicoding·GPT-5.4 Mini
Hype vs Reality
Attention vs performance
GPT-5.4 Mini
#182 by perf·no signal
Claude 3.5 Haiku
#187 by perf·no signal
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Anthropic
$380.0B·Tier 1
Head to head
5 benchmarks · 2 models
GPT-5.4 MiniClaude 3.5 Haiku
FrontierMath-2025-02-28-Private
GPT-5.4 Mini leads by +27.9
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
GPT-5.4 Mini
28.3
Claude 3.5 Haiku
0.3
GPQA diamond
GPT-5.4 Mini leads by +60.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5.4 Mini
78.1
Claude 3.5 Haiku
17.5
OTIS Mock AIME 2024-2025
GPT-5.4 Mini leads by +83.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5.4 Mini
87.2
Claude 3.5 Haiku
4.2
SimpleQA Verified
GPT-5.4 Mini leads by +21.9
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5.4 Mini
28.6
Claude 3.5 Haiku
6.7
WeirdML
GPT-5.4 Mini leads by +29.6
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5.4 Mini
60.3
Claude 3.5 Haiku
30.7
Full benchmark table
| Benchmark | GPT-5.4 Mini | Claude 3.5 Haiku |
|---|---|---|
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 28.3 | 0.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 78.1 | 17.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 87.2 | 4.2 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 28.6 | 6.7 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 60.3 | 30.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.75 | $4.50 | 400K tokens (~200 books) | $16.88 | |
| — | — | — | — |
People also compared