Compare · ModelsLive · 2 picked · head to head
GPT-5.4 Mini vs GPT-4o-mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5.4 Mini wins on 4/4 benchmarks
GPT-5.4 Mini wins 4 of 4 shared benchmarks. Leads in reasoning · knowledge · math.
Category leads
reasoning·GPT-5.4 Miniknowledge·GPT-5.4 Minimath·GPT-5.4 Minicoding·GPT-5.4 Mini
Hype vs Reality
Attention vs performance
GPT-5.4 Mini
#182 by perf·no signal
GPT-4o-mini
#175 by perf·no signal
Best value
GPT-4o-mini
7.2x better value than GPT-5.4 Mini
GPT-5.4 Mini
14.6 pts/$
$2.63/M
GPT-4o-mini
105.6 pts/$
$0.38/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
4 benchmarks · 2 models
GPT-5.4 MiniGPT-4o-mini
ARC-AGI-2
GPT-5.4 Mini leads by +18.9
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-5.4 Mini
18.9
GPT-4o-mini
0.0
GPQA diamond
GPT-5.4 Mini leads by +61.1
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
GPT-4o-mini
17.0
OTIS Mock AIME 2024-2025
GPT-5.4 Mini leads by +80.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5.4 Mini
87.2
GPT-4o-mini
6.8
WeirdML
GPT-5.4 Mini leads by +48.5
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5.4 Mini
60.3
GPT-4o-mini
11.8
Full benchmark table
| Benchmark | GPT-5.4 Mini | GPT-4o-mini |
|---|---|---|
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 18.9 | 0.0 |
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 | 17.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 87.2 | 6.8 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 60.3 | 11.8 |
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 | |
| $0.15 | $0.60 | 128K tokens (~64 books) | $2.62 |
People also compared