Compare · ModelsLive · 2 picked · head to head
DeepSeek V4 Flash 0731 vs Qwen2.5 72B Instruct
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4 Flash 0731 wins on 5/5 benchmarks
DeepSeek V4 Flash 0731 wins 5 of 5 shared benchmarks. Leads in general · knowledge · math.
Category leads
general·DeepSeek V4 Flash 0731knowledge·DeepSeek V4 Flash 0731math·DeepSeek V4 Flash 0731coding·DeepSeek V4 Flash 0731
Hype vs Reality
Attention vs performance
DeepSeek V4 Flash 0731
#76 by perf·#6 by attention
Qwen2.5 72B Instruct
#128 by perf·#2 by attention
Best value
Qwen2.5 72B Instruct
1.5x better value than DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731
85.5 pts/$
$0.65/M
Qwen2.5 72B Instruct
129.5 pts/$
$0.38/M
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 V4 Flash 0731Qwen2.5 72B Instruct
Dtbench
DeepSeek V4 Flash 0731 leads by +46.7
DeepSeek V4 Flash 0731
84.9
Qwen2.5 72B Instruct
38.2
GPQA diamond
DeepSeek V4 Flash 0731 leads by +55.8
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
DeepSeek V4 Flash 0731
88.0
Qwen2.5 72B Instruct
32.2
Lmca
DeepSeek V4 Flash 0731 leads by +33.3
DeepSeek V4 Flash 0731
49.1
Qwen2.5 72B Instruct
15.8
OTIS Mock AIME 2024-2025
DeepSeek V4 Flash 0731 leads by +86.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4 Flash 0731
94.4
Qwen2.5 72B Instruct
8.0
WeirdML
DeepSeek V4 Flash 0731 leads by +47.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
DeepSeek V4 Flash 0731
63.0
Qwen2.5 72B Instruct
16.0
Full benchmark table
| Benchmark | DeepSeek V4 Flash 0731 | Qwen2.5 72B Instruct |
|---|---|---|
Dtbench | 84.9 | 38.2 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 88.0 | 32.2 |
Lmca | 49.1 | 15.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.4 | 8.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 63.0 | 16.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.02 | $1.28 | 1.0M tokens (~524 books) | $3.31 | |
| $0.36 | $0.40 | 33K tokens (~16 books) | $3.70 |