Compare · ModelsLive · 2 picked · head to head

Llama 3.2 90B vs Qwen2.5-Max

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

Winner summary

Qwen2.5-Max wins 3 of 3 shared benchmarks. Leads in knowledge · math.

Category leads
knowledge·Qwen2.5-Maxmath·Qwen2.5-Max
Hype vs Reality
Llama 3.2 90B
#164 by perf·no signal
QUIET
Qwen2.5-Max
#141 by perf·no signal
QUIET
Best value
Llama 3.2 90B
no price
Qwen2.5-Max
no price
Vendor risk
Meta logo
Meta AI
$1.50T·Tier 1
Low risk
Alibaba Qwen logo
Alibaba (Qwen)
$293.0B·Tier 1
Low risk
Head to head
Llama 3.2 90BQwen2.5-Max
GPQA diamond
Qwen2.5-Max leads by +20.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Llama 3.2 90B
21.4
Qwen2.5-Max
41.5
MATH level 5
Qwen2.5-Max leads by +27.7
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Llama 3.2 90B
39.4
Qwen2.5-Max
67.2
OTIS Mock AIME 2024-2025
Qwen2.5-Max leads by +13.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Llama 3.2 90B
2.5
Qwen2.5-Max
16.0
Full benchmark table
BenchmarkLlama 3.2 90BQwen2.5-Max
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
21.441.5
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
39.467.2
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
2.516.0
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Meta logoLlama 3.2 90B
Alibaba Qwen logoQwen2.5-Max