Compare · ModelsLive · 2 picked · head to head
DeepSeek V4 Flash 0731 vs Qwen3.5 397B A17B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4 Flash 0731 wins on 7/7 benchmarks
DeepSeek V4 Flash 0731 wins 7 of 7 shared benchmarks. Leads in knowledge · general · math.
Category leads
knowledge·DeepSeek V4 Flash 0731general·DeepSeek V4 Flash 0731math·DeepSeek V4 Flash 0731
Hype vs Reality
Attention vs performance
DeepSeek V4 Flash 0731
#76 by perf·#6 by attention
Qwen3.5 397B A17B
#48 by perf·#2 by attention
Best value
DeepSeek V4 Flash 0731
2.9x better value than Qwen3.5 397B A17B
DeepSeek V4 Flash 0731
85.5 pts/$
$0.65/M
Qwen3.5 397B A17B
29.6 pts/$
$2.02/M
Vendor risk
Mixed exposure
One or more vendors flagged
DeepSeek
$3.4B·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
7 benchmarks · 2 models
DeepSeek V4 Flash 0731Qwen3.5 397B A17B
Chess Puzzles
DeepSeek V4 Flash 0731 leads by +21.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
DeepSeek V4 Flash 0731
29.5
Qwen3.5 397B A17B
8.5
Dtbench
DeepSeek V4 Flash 0731 leads by +5.8
DeepSeek V4 Flash 0731
84.9
Qwen3.5 397B A17B
79.1
FrontierMath-Tiers-1-3-v2-Private
DeepSeek V4 Flash 0731 leads by +26.3
DeepSeek V4 Flash 0731
57.5
Qwen3.5 397B A17B
31.2
GPQA diamond
DeepSeek V4 Flash 0731 leads by +6.2
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
Qwen3.5 397B A17B
81.8
Lmca
DeepSeek V4 Flash 0731 leads by +4.5
DeepSeek V4 Flash 0731
49.1
Qwen3.5 397B A17B
44.6
Mystery Game Puzzles
DeepSeek V4 Flash 0731 leads by +17.6
DeepSeek V4 Flash 0731
27.3
Qwen3.5 397B A17B
9.7
OTIS Mock AIME 2024-2025
DeepSeek V4 Flash 0731 leads by +5.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
DeepSeek V4 Flash 0731
94.4
Qwen3.5 397B A17B
88.9
Full benchmark table
| Benchmark | DeepSeek V4 Flash 0731 | Qwen3.5 397B A17B |
|---|---|---|
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 29.5 | 8.5 |
Dtbench | 84.9 | 79.1 |
FrontierMath-Tiers-1-3-v2-Private | 57.5 | 31.2 |
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 | 81.8 |
Lmca | 49.1 | 44.6 |
Mystery Game Puzzles | 27.3 | 9.7 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 94.4 | 88.9 |
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 | |
| $0.55 | $3.50 | 262K tokens (~131 books) | $12.88 |