Compare · ModelsLive · 2 picked · head to head
o3 Mini vs Llama 3.2 90B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
o3 Mini wins on 3/3 benchmarks
o3 Mini wins 3 of 3 shared benchmarks. Leads in knowledge · math.
Category leads
knowledge·o3 Minimath·o3 Mini
Hype vs Reality
Attention vs performance
o3 Mini
#151 by perf·no signal
Llama 3.2 90B
#164 by perf·no signal
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Meta AI
$1.50T·Tier 1
Head to head
3 benchmarks · 2 models
o3 MiniLlama 3.2 90B
GPQA diamond
o3 Mini leads by +48.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
o3 Mini
69.4
Llama 3.2 90B
21.4
MATH level 5
o3 Mini leads by +57.0
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
o3 Mini
96.5
Llama 3.2 90B
39.4
OTIS Mock AIME 2024-2025
o3 Mini leads by +74.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
o3 Mini
76.9
Llama 3.2 90B
2.5
Full benchmark table
| Benchmark | o3 Mini | Llama 3.2 90B |
|---|---|---|
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 69.4 | 21.4 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 96.5 | 39.4 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 76.9 | 2.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.10 | $4.40 | 200K tokens (~100 books) | $19.25 | |
| — | — | — | — |