Compare · ModelsLive · 2 picked · head to head
DeepSeek V3 vs Qwen2-72B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V3 wins on 5/5 benchmarks
DeepSeek V3 wins 5 of 5 shared benchmarks. Leads in knowledge · math · general.
Category leads
knowledge·DeepSeek V3math·DeepSeek V3general·DeepSeek V3coding·DeepSeek V3
Hype vs Reality
Attention vs performance
DeepSeek V3
#70 by perf·no signal
Qwen2-72B
#203 by perf·#1 by attention
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
5 benchmarks · 2 models
DeepSeek V3Qwen2-72B
GPQA diamond
DeepSeek V3 leads by +21.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V3
42.0
Qwen2-72B
21.0
MATH level 5
DeepSeek V3 leads by +25.8
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
DeepSeek V3
64.8
Qwen2-72B
39.1
Metr Time Horizons
DeepSeek V3 leads by +17.5
DeepSeek V3
47.4
Qwen2-72B
29.9
MMLU
DeepSeek V3 leads by +6.4
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
DeepSeek V3
82.9
Qwen2-72B
76.5
WeirdML
DeepSeek V3 leads by +24.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V3
36.1
Qwen2-72B
11.3
Full benchmark table
| Benchmark | DeepSeek V3 | 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. | 42.0 | 21.0 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 64.8 | 39.1 |
Metr Time Horizons | 47.4 | 29.9 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 82.9 | 76.5 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 36.1 | 11.3 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.26 | $1.03 | 164K tokens (~82 books) | $4.50 | |
| — | — | — | — |
People also compared