Compare · ModelsLive · 2 picked · head to head

Phi 4 vs o4 Mini

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

o4 Mini wins 4 of 4 shared benchmarks. Leads in knowledge · math.

Category leads
knowledge·o4 Minimath·o4 Mini
Hype vs Reality
Phi 4
#126 by perf·no signal
QUIET
o4 Mini
#81 by perf·#13 by attention
DESERVED
Best value
21.8x better value than o4 Mini
Phi 4
421.5 pts/$
$0.10/M
o4 Mini
19.3 pts/$
$2.75/M
Vendor risk
Microsoft logo
Microsoft
$3.00T·Big Tech
Low risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
Phi 4o4 Mini
GPQA diamond
o4 Mini leads by +31.4
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Phi 4
41.4
o4 Mini
72.8
Lech Mazur Writing
o4 Mini leads by +12.4
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
Phi 4
62.6
o4 Mini
75.0
MATH level 5
o4 Mini leads by +32.9
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Phi 4
64.9
o4 Mini
97.8
OTIS Mock AIME 2024-2025
o4 Mini leads by +68.0
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Phi 4
13.7
o4 Mini
81.7
Full benchmark table
BenchmarkPhi 4o4 Mini
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
41.472.8
Lech Mazur Writing
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
62.675.0
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
64.997.8
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
13.781.7
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Microsoft logoPhi 4$0.07$0.1416K tokens (~8 books)$0.84
OpenAI logoo4 Mini$1.10$4.40200K tokens (~100 books)$19.25