Compare · ModelsLive · 2 picked · head to head
Qwen2-72B vs Qwen2.5 32B Instruct
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen2.5 32B Instruct wins on 3/6 benchmarks
Qwen2.5 32B Instruct wins 3 of 6 shared benchmarks. Leads in general · language · math.
Category leads
general·Qwen2.5 32B Instructknowledge·Qwen2-72Blanguage·Qwen2.5 32B Instructmath·Qwen2.5 32B Instructreasoning·Qwen2-72B
Hype vs Reality
Attention vs performance
Qwen2-72B
#137 by perf·no signal
Qwen2.5 32B Instruct
#125 by perf·no signal
Vendor risk
Who is behind the model
Alibaba (Qwen)
$293.0B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
6 benchmarks · 2 models
Qwen2-72BQwen2.5 32B Instruct
BBH (HuggingFace)
Qwen2.5 32B Instruct leads by +4.6
Qwen2-72B
51.9
Qwen2.5 32B Instruct
56.5
GPQA
Qwen2-72B leads by +7.5
Qwen2-72B
19.2
Qwen2.5 32B Instruct
11.7
IFEval
Qwen2.5 32B Instruct leads by +45.2
Qwen2-72B
38.2
Qwen2.5 32B Instruct
83.5
MATH Level 5
Qwen2.5 32B Instruct leads by +31.4
Qwen2-72B
31.1
Qwen2.5 32B Instruct
62.5
MMLU-PRO
Qwen2-72B leads by +0.7
Qwen2-72B
52.6
Qwen2.5 32B Instruct
51.9
MUSR
Qwen2-72B leads by +6.2
Qwen2-72B
19.7
Qwen2.5 32B Instruct
13.5
Full benchmark table
| Benchmark | Qwen2-72B | Qwen2.5 32B Instruct |
|---|---|---|
BBH (HuggingFace) | 51.9 | 56.5 |
GPQA | 19.2 | 11.7 |
IFEval | 38.2 | 83.5 |
MATH Level 5 | 31.1 | 62.5 |
MMLU-PRO | 52.6 | 51.9 |
MUSR | 19.7 | 13.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Qwen2-72B | — | — | — | — |
| Qwen2.5 32B Instruct | — | — | — | — |