Compare · ModelsLive · 2 picked · head to head
Qwen2.5 32B Instruct vs Qwen2.5 72B Instruct
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Qwen2.5 72B Instruct wins on 3/6 benchmarks
Qwen2.5 72B Instruct wins 3 of 6 shared benchmarks. Leads in general · knowledge · language.
Category leads
general·Qwen2.5 72B Instructknowledge·Qwen2.5 72B Instructlanguage·Qwen2.5 72B Instructmath·Qwen2.5 32B Instructreasoning·Qwen2.5 32B Instruct
Hype vs Reality
Attention vs performance
Qwen2.5 32B Instruct
#125 by perf·no signal
Qwen2.5 72B Instruct
#80 by perf·no signal
Best value
Qwen2.5 72B Instruct
Qwen2.5 32B Instruct
—
no price
Qwen2.5 72B Instruct
208.6 pts/$
$0.26/M
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
Qwen2.5 32B InstructQwen2.5 72B Instruct
BBH (HuggingFace)
Qwen2.5 72B Instruct leads by +5.4
Qwen2.5 32B Instruct
56.5
Qwen2.5 72B Instruct
61.9
GPQA
Qwen2.5 72B Instruct leads by +4.9
Qwen2.5 32B Instruct
11.7
Qwen2.5 72B Instruct
16.7
IFEval
Qwen2.5 72B Instruct leads by +2.9
Qwen2.5 32B Instruct
83.5
Qwen2.5 72B Instruct
86.4
MATH Level 5
Qwen2.5 32B Instruct leads by +2.7
Qwen2.5 32B Instruct
62.5
Qwen2.5 72B Instruct
59.8
MMLU-PRO
Qwen2.5 32B Instruct leads by +0.5
Qwen2.5 32B Instruct
51.9
Qwen2.5 72B Instruct
51.4
MUSR
Qwen2.5 32B Instruct leads by +1.8
Qwen2.5 32B Instruct
13.5
Qwen2.5 72B Instruct
11.7
Full benchmark table
| Benchmark | Qwen2.5 32B Instruct | Qwen2.5 72B Instruct |
|---|---|---|
BBH (HuggingFace) | 56.5 | 61.9 |
GPQA | 11.7 | 16.7 |
IFEval | 83.5 | 86.4 |
MATH Level 5 | 62.5 | 59.8 |
MMLU-PRO | 51.9 | 51.4 |
MUSR | 13.5 | 11.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Qwen2.5 32B Instruct | — | — | — | — |
| Qwen2.5 72B Instruct | $0.12 | $0.39 | 33K tokens (~16 books) | $1.88 |