DeepSeek V4 Pro (0813) vs Qwen3.5-397B-A17B.
Verdict by category, tale of the tape, shared benchmarks only, and cost at three workloads — all from the tracked data.
Verdict by category
| Category | DeepSeek V4 Pro (0813) | Qwen3.5-397B-A17B | Winner |
|---|---|---|---|
| League Score | 63.2 | 60.7 | DeepSeek V4 Pro (0813) |
| Coding (SWE-bench %) | 73.6 | 76.2 | Qwen3.5-397B-A17B |
| Reasoning (GPQA %) | 90.1 | 88.4 | DeepSeek V4 Pro (0813) |
| Context (tokens) | 1000000 | 262144 | DeepSeek V4 Pro (0813) |
| Speed (tok/s) | 99.4 | — | — |
Tale of the tape
| Spec | DeepSeek V4 Pro (0813) | Qwen3.5-397B-A17B |
|---|---|---|
| Maker | DeepSeek | Alibaba Qwen |
| Released | Apr 24, 2026 | Feb 16, 2026 |
| League Score | 63 | 61 |
| Context | 1,000,000 tokens | 262,144 tokens |
| Max output | 384,000 | — |
| $/1M input | $1.32 | — |
| $/1M output | $3.96 | — |
| Weights | Open | Open |
| Speed | 99.4 t/s | — |
Head-to-head benchmarks (shared only)
| Benchmark | DeepSeek V4 Pro (0813) | Qwen3.5-397B-A17B |
|---|---|---|
| SWE-bench Verified | 73.6 | 76.2 |
| GPQA Diamond | 90.1 | 88.4 |
Cost at three workloads
| Workload | DeepSeek V4 Pro (0813) | Qwen3.5-397B-A17B |
|---|---|---|
| Light — 1M in / 250K out | $2.31 | — |
| Standard — 10M in / 2.5M out | $23.10 | — |
| Long-context — 50M in / 5M out | $85.80 | — |
The pick
Pick DeepSeek V4 Pro (0813) if you want the higher overall League Score; you need the bigger context window.
Pick Qwen3.5-397B-A17B if coding is the priority.
All figures from the model database — sources and dates on each model page. Cost your own workload or compare a different pair.
Frequently asked questions
Which is better overall, DeepSeek V4 Pro (0813) or Qwen3.5-397B-A17B?
DeepSeek V4 Pro (0813) leads on overall League Score, 63 to 61 — a gap of 2 points on a composite of sourced benchmarks. That is overall form, not every category: check the per-category verdicts before choosing.
Which is cheaper, DeepSeek V4 Pro (0813) or Qwen3.5-397B-A17B?
Only DeepSeek V4 Pro (0813) has published API pricing in our database ($1.98 blended per 1M tokens); Qwen3.5-397B-A17B has no tracked API price, so a like-for-like cost verdict is not possible.
Which has the bigger context window, DeepSeek V4 Pro (0813) or Qwen3.5-397B-A17B?
DeepSeek V4 Pro (0813), with 1M of context against 262.1K for Qwen3.5-397B-A17B.
Which is better for coding, DeepSeek V4 Pro (0813) or Qwen3.5-397B-A17B?
Qwen3.5-397B-A17B scores higher on SWE-bench Verified, 76.2% vs 73.6% of real GitHub issues resolved.
Which is better at reasoning, DeepSeek V4 Pro (0813) or Qwen3.5-397B-A17B?
DeepSeek V4 Pro (0813) leads on GPQA Diamond, 90.1% vs 88.4% on graduate-level science questions.
Are DeepSeek V4 Pro (0813) and Qwen3.5-397B-A17B open source?
DeepSeek V4 Pro (0813) is open weights — it can be downloaded and self-hosted; Qwen3.5-397B-A17B is open weights — it can be downloaded and self-hosted.