Compare · ModelsLive · 2 picked · head to head
DeepSeek R1 Distill Qwen 14B vs Qwen2-72B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek R1 Distill Qwen 14B wins on 5/8 benchmarks
DeepSeek R1 Distill Qwen 14B wins 5 of 8 shared benchmarks. Leads in language · math · reasoning.
Category leads
knowledge·Qwen2-72Bgeneral·Qwen2-72Blanguage·DeepSeek R1 Distill Qwen 14Bmath·DeepSeek R1 Distill Qwen 14Breasoning·DeepSeek R1 Distill Qwen 14B
Hype vs Reality
Attention vs performance
DeepSeek R1 Distill Qwen 14B
#107 by perf·no signal
Qwen2-72B
#203 by perf·#2 by attention
Best value
Pricing unknown
DeepSeek R1 Distill Qwen 14B
n/a
no price
Qwen2-72B
n/a
no price
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
8 benchmarks · 2 models
DeepSeek R1 Distill Qwen 14BQwen2-72B
GPQA diamond
DeepSeek R1 Distill Qwen 14B leads by +5.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek R1 Distill Qwen 14B
26.3
Qwen2-72B
21.0
BBH (HuggingFace)
Qwen2-72B leads by +11.2
DeepSeek R1 Distill Qwen 14B
40.7
Qwen2-72B
51.9
GPQA
Qwen2-72B leads by +0.9
DeepSeek R1 Distill Qwen 14B
18.3
Qwen2-72B
19.2
IFEval
DeepSeek R1 Distill Qwen 14B leads by +5.6
DeepSeek R1 Distill Qwen 14B
43.8
Qwen2-72B
38.2
MATH Level 5
DeepSeek R1 Distill Qwen 14B leads by +25.9
DeepSeek R1 Distill Qwen 14B
57.0
Qwen2-72B
31.1
MMLU-PRO
Qwen2-72B leads by +11.8
DeepSeek R1 Distill Qwen 14B
40.7
Qwen2-72B
52.6
MUSR
DeepSeek R1 Distill Qwen 14B leads by +9.0
DeepSeek R1 Distill Qwen 14B
28.7
Qwen2-72B
19.7
MATH level 5
DeepSeek R1 Distill Qwen 14B leads by +48.1
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
DeepSeek R1 Distill Qwen 14B
87.1
Qwen2-72B
39.1
Full benchmark table
| Benchmark | DeepSeek R1 Distill Qwen 14B | 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. | 26.3 | 21.0 |
BBH (HuggingFace) | 40.7 | 51.9 |
GPQA | 18.3 | 19.2 |
IFEval | 43.8 | 38.2 |
MATH Level 5 | 57.0 | 31.1 |
MMLU-PRO | 40.7 | 52.6 |
MUSR | 28.7 | 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. | 87.1 | 39.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| — | — | — | — | |
| — | — | — | — |