Compare · ModelsLive · 2 picked · head to head
Qwen2.5 32B Instruct vs Qwen2-72B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen2.5 32B Instruct wins on 5/8 benchmarks
Qwen2.5 32B Instruct wins 5 of 8 shared benchmarks. Leads in general · language · math.
Category leads
knowledge·Qwen2-72Bgeneral·Qwen2.5 32B Instructlanguage·Qwen2.5 32B Instructmath·Qwen2.5 32B Instructreasoning·Qwen2-72B
Hype vs Reality
Attention vs performance
Qwen2.5 32B Instruct
#222 by perf·#2 by attention
Qwen2-72B
#203 by perf·#2 by attention
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
8 benchmarks · 2 models
Qwen2.5 32B InstructQwen2-72B
GPQA diamond
Qwen2.5 32B Instruct leads by +7.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Qwen2.5 32B Instruct
28.1
Qwen2-72B
21.0
BBH (HuggingFace)
Qwen2.5 32B Instruct leads by +4.6
Qwen2.5 32B Instruct
56.5
Qwen2-72B
51.9
GPQA
Qwen2-72B leads by +7.5
Qwen2.5 32B Instruct
11.7
Qwen2-72B
19.2
IFEval
Qwen2.5 32B Instruct leads by +45.2
Qwen2.5 32B Instruct
83.5
Qwen2-72B
38.2
MATH Level 5
Qwen2.5 32B Instruct leads by +31.4
Qwen2.5 32B Instruct
62.5
Qwen2-72B
31.1
MMLU-PRO
Qwen2-72B leads by +0.7
Qwen2.5 32B Instruct
51.9
Qwen2-72B
52.6
MUSR
Qwen2-72B leads by +6.2
Qwen2.5 32B Instruct
13.5
Qwen2-72B
19.7
MATH level 5
Qwen2.5 32B Instruct leads by +17.0
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Qwen2.5 32B Instruct
56.1
Qwen2-72B
39.1
Full benchmark table
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 28.1 | 21.0 |
BBH (HuggingFace) | 56.5 | 51.9 |
GPQA | 11.7 | 19.2 |
IFEval | 83.5 | 38.2 |
MATH Level 5 | 62.5 | 31.1 |
MMLU-PRO | 51.9 | 52.6 |
MUSR | 13.5 | 19.7 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 56.1 | 39.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| — | — | — | — |