DeepSeek V4.1 Flash 1017 vs Qwen3.8 Max Preview
DeepSeek V4.1 Flash 1017 leads Qwen3.8 Max Preview by 4.0 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. DeepSeek V4.1 Flash 1017 wins 4 and Qwen3.8 Max Preview wins 2 of 9 shared benchmarks. Qwen3.8 Max Preview is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | DeepSeek V4.1 Flash 1017 | Qwen3.8 Max Preview |
|---|---|---|
| Agentic coding | 63 | 58 |
| Long-horizon autonomy | 66 | 63 |
| Knowledge-work agents | 49 | 46 |
| Computer use | 45 | 41 |
| Security & context learning | 54 | 52 |
Shared benchmarks
| Benchmark | DeepSeek V4.1 Flash 1017 | Qwen3.8 Max Preview |
|---|---|---|
| APEX-Agentsindex | 69.8% | 63.3% |
| Chess Puzzles | 46.0% | 46.0% |
| CritPt | 24.0% | 20.0% |
| FrontierMath Tier 4 | 46.3% | 46.3% |
| FrontierMath Tiers 1-3 | 71.2% | 74.7% |
| GPQA Diamond | 93.2% | 92.7% |
| OTIS Mock AIME | 99.4% | 99.4% |
| SciCode | 55.9% | 53.2% |
| SimpleQA Verified | 42.5% | 45.8% |
Specs and price
| DeepSeek V4.1 Flash 1017 | Qwen3.8 Max Preview | |
|---|---|---|
| Agent Index | 57.6 (#17) | 53.6 (#30) |
| Agent $/M | $0.050 | Free |
| Input / output $/M | $0.15 / $0.60 | Free / Free |
| Context | 1M | 1M |
| Released | Oct 17, 2026 | Jul 19, 2026 |
| Weights | Open | Closed |
| API hosts | 51 | 1 |
Don’t pick one. Route.
Shogo can run DeepSeek V4.1 Flash 1017 and Qwen3.8 Max Preview side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo