Compare · ModelsLive · 3 picked · head to head
DeepSeek R1 Distill Qwen 32B vs DeepSeek R1 Distill Qwen 14B vs Qwen2 7B Instruct
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek R1 Distill Qwen 14B wins on 5/11 benchmarks
DeepSeek R1 Distill Qwen 14B wins 5 of 11 shared benchmarks. Leads in general · knowledge · math.
Category leads
general·DeepSeek R1 Distill Qwen 14Bknowledge·DeepSeek R1 Distill Qwen 14Blanguage·DeepSeek R1 Distill Qwen 32Bmath·DeepSeek R1 Distill Qwen 14Breasoning·DeepSeek R1 Distill Qwen 14B
Hype vs Reality
Attention vs performance
DeepSeek R1 Distill Qwen 32B
#125 by perf·no signal
DeepSeek R1 Distill Qwen 14B
#80 by perf·no signal
Qwen2 7B Instruct
#118 by perf·no signal
Best value
Pricing unknown
DeepSeek R1 Distill Qwen 32B
—
no price
DeepSeek R1 Distill Qwen 14B
—
no price
Qwen2 7B Instruct
—
no price
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
DeepSeek
$3.4B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
11 benchmarks · 3 models
DeepSeek R1 Distill Qwen 32BDeepSeek R1 Distill Qwen 14BQwen2 7B Instruct
BBH (HuggingFace)
DeepSeek R1 Distill Qwen 14B leads by +2.9
DeepSeek R1 Distill Qwen 32B
17.1
DeepSeek R1 Distill Qwen 14B
40.7
Qwen2 7B Instruct
37.8
GPQA
DeepSeek R1 Distill Qwen 14B leads by +12.0
DeepSeek R1 Distill Qwen 32B
4.6
DeepSeek R1 Distill Qwen 14B
18.3
Qwen2 7B Instruct
6.4
IFEval
Qwen2 7B Instruct leads by +13.0
DeepSeek R1 Distill Qwen 32B
41.9
DeepSeek R1 Distill Qwen 14B
43.8
Qwen2 7B Instruct
56.8
MATH Level 5
DeepSeek R1 Distill Qwen 14B leads by +29.4
DeepSeek R1 Distill Qwen 32B
17.1
DeepSeek R1 Distill Qwen 14B
57.0
Qwen2 7B Instruct
27.6
MMLU-PRO
DeepSeek R1 Distill Qwen 32B leads by +0.2
DeepSeek R1 Distill Qwen 32B
41.0
DeepSeek R1 Distill Qwen 14B
40.7
Qwen2 7B Instruct
31.6
MUSR
DeepSeek R1 Distill Qwen 14B leads by +12.6
DeepSeek R1 Distill Qwen 32B
16.1
DeepSeek R1 Distill Qwen 14B
28.7
Qwen2 7B Instruct
7.4
JCommonsenseQA
DeepSeek R1 Distill Qwen 32B leads by +1.6
DeepSeek R1 Distill Qwen 32B
95.3
DeepSeek R1 Distill Qwen 14B
93.7
Qwen2 7B Instruct
89.1
JMMLU
DeepSeek R1 Distill Qwen 32B leads by +8.8
DeepSeek R1 Distill Qwen 32B
72.2
DeepSeek R1 Distill Qwen 14B
63.4
Qwen2 7B Instruct
56.5
JNLI
DeepSeek R1 Distill Qwen 32B leads by +3.2
DeepSeek R1 Distill Qwen 32B
85.6
DeepSeek R1 Distill Qwen 14B
82.4
Qwen2 7B Instruct
81.3
JSQuAD
DeepSeek R1 Distill Qwen 14B leads by +0.2
DeepSeek R1 Distill Qwen 32B
89.2
DeepSeek R1 Distill Qwen 14B
89.8
Qwen2 7B Instruct
89.6
LLM-JP · Overall
DeepSeek R1 Distill Qwen 32B leads by +2.5
DeepSeek R1 Distill Qwen 32B
59.3
DeepSeek R1 Distill Qwen 14B
56.8
Qwen2 7B Instruct
51.7
Full benchmark table
| Benchmark | DeepSeek R1 Distill Qwen 32B | DeepSeek R1 Distill Qwen 14B | Qwen2 7B Instruct |
|---|---|---|---|
BBH (HuggingFace) | 17.1 | 40.7 | 37.8 |
GPQA | 4.6 | 18.3 | 6.4 |
IFEval | 41.9 | 43.8 | 56.8 |
MATH Level 5 | 17.1 | 57.0 | 27.6 |
MMLU-PRO | 41.0 | 40.7 | 31.6 |
MUSR | 16.1 | 28.7 | 7.4 |
JCommonsenseQA | 95.3 | 93.7 | 89.1 |
JMMLU | 72.2 | 63.4 | 56.5 |
JNLI | 85.6 | 82.4 | 81.3 |
JSQuAD | 89.2 | 89.8 | 89.6 |
LLM-JP · Overall | 59.3 | 56.8 | 51.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| — | — | — | — | |
| — | — | — | — |