Compare · ModelsLive · 2 picked · head to head
DeepSeek V4 Flash vs Qwen3.5 397B A17B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
DeepSeek V4 Flash wins on 3/6 benchmarks
DeepSeek V4 Flash wins 3 of 6 shared benchmarks. Leads in speed.
Category leads
speed·DeepSeek V4 Flasharena·Qwen3.5 397B A17Bgeneral·Qwen3.5 397B A17B
Hype vs Reality
Attention vs performance
DeepSeek V4 Flash
#39 by perf·#6 by attention
Qwen3.5 397B A17B
#48 by perf·#2 by attention
Best value
DeepSeek V4 Flash
3.2x better value than Qwen3.5 397B A17B
DeepSeek V4 Flash
94.4 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
6 benchmarks · 2 models
DeepSeek V4 FlashQwen3.5 397B A17B
Artificial Analysis · Agentic Index
DeepSeek V4 Flash leads by +11.2
Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?"
DeepSeek V4 Flash
31.1
Qwen3.5 397B A17B
19.9
Artificial Analysis · Coding Index
DeepSeek V4 Flash leads by +8.0
Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads.
DeepSeek V4 Flash
56.2
Qwen3.5 397B A17B
48.2
Artificial Analysis · Quality Index
DeepSeek V4 Flash leads by +18.8
DeepSeek V4 Flash
40.3
Qwen3.5 397B A17B
21.4
Chatbot Arena Elo · Overall
Qwen3.5 397B A17B leads by +5.8
DeepSeek V4 Flash
1436.0
Qwen3.5 397B A17B
1441.8
Dtbench
Qwen3.5 397B A17B leads by +1.8
DeepSeek V4 Flash
77.3
Qwen3.5 397B A17B
79.1
Lmca
Qwen3.5 397B A17B leads by +2.4
DeepSeek V4 Flash
42.2
Qwen3.5 397B A17B
44.6
Full benchmark table
| Benchmark | DeepSeek V4 Flash | Qwen3.5 397B A17B |
|---|---|---|
Artificial Analysis · Agentic Index Artificial Analysis Agentic Index · a composite score measuring how well a model performs in agentic workflows · multi-step tool use, planning, error recovery, and autonomous task completion. Aggregates results from multiple agentic benchmarks including SWE-bench, tool-use tests, and planning evaluations. The canonical single-number metric for "how good is this model as an agent?" | 31.1 | 19.9 |
Artificial Analysis · Coding Index Artificial Analysis Coding Index · a composite score that aggregates performance across multiple coding benchmarks into a single index. Tracks code generation quality, debugging ability, multi-language competence, and real-world software engineering tasks. Used by Artificial Analysis to rank model coding capability in a normalized, comparable format. Useful for developers choosing between models for coding-heavy workloads. | 56.2 | 48.2 |
Artificial Analysis · Quality Index | 40.3 | 21.4 |
Chatbot Arena Elo · Overall | 1436.0 | 1441.8 |
Dtbench | 77.3 | 79.1 |
Lmca | 42.2 | 44.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.03 | $1.28 | 1.0M tokens (~524 books) | $3.39 | |
| $0.55 | $3.50 | 262K tokens (~131 books) | $12.88 |
People also compared
DeepSeek V3.2 Speciale vs DeepSeek V4 FlashDeepSeek-V2 (MoE-236B, May 2024) vs DeepSeek V4 FlashQwen3 30B A3B Thinking 2507 vs Qwen3.5 397B A17BDeepSeek V4 Flash vs PaLM 2-MDeepSeek V4 Flash vs Qwen3 Next 80B A3B ThinkingDeepSeek V4 Flash vs Qwen3.7 MaxDeepSeek V4 Flash vs o3 ProDeepSeek V4 Flash vs Qwen-14B