BlogLLM Benchmark Scores as Published, Side by Side
DeepSeek-V4.1-Flash-1017 vs Qwen3.8-Max: Benchmark Scores Side by Side
Every test both DeepSeek-V4.1-Flash-1017 by DeepSeek and Qwen3.8-Max by Alibaba have a published number for: 12 tests in 5 areas. Each number is as printed, with the page it comes from and the setup it was run under; nothing is ranked or rescored, and two numbers under different setups are two results, not one comparison.
Models DeepSeek-V4.1-Flash-1017, Qwen3.8-MaxData version 2026103001, as of 2026-10-30
Model
What each developer prints on its own model page; a dash means it prints none.
| Fact | DeepSeek-V4.1-Flash-1017 | Qwen3.8-Max |
|---|---|---|
| Released | 2026-10-17 | 2026-08-03 |
| Context window | 1M | 1M |
| Max output | - | 131K |
| Input | Text, image | Text, image, video |
| Output | Text | Text |
| Weights | Open (MIT) | Closed |
Knowledge Work
| Test | DeepSeek-V4.1-Flash-1017 | Qwen3.8-Max |
|---|---|---|
| AutomationBench | 60.5%DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18; printed on 2 more pagesDataset revision: v1.0.6 (printed in the label) | 27.3%Alibaba, Qwen3.8-Max comparison, checked 2026-10-14; printed on 1 more page |
Agentic Coding
| Test | DeepSeek-V4.1-Flash-1017 | Qwen3.8-Max |
|---|---|---|
| DeepSWE v1.1 | 77%DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18; printed on 2 more pagesHarness: Mini-SWE-V2 | 56.6%Alibaba, Qwen3.8-Max comparison, checked 2026-10-14; printed on 2 more pages |
| Terminal-Bench 4.0 | 42.3%DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18; printed on 2 more pagesHarness: Claude Code | 17%Mistral AI, Mistral Large 4 (preview), checked 2026-10-15 |
| NL2Repo-Bench | 68.2DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18; printed on 1 more page | 55.9Alibaba, Qwen3.8-Max comparison, checked 2026-10-14; printed on 1 more page |
| ProgramBench Almost@1 | 29.1%DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18; printed on 1 more page | 10.5%Z.ai, GLM-5.3 model card, checked 2026-10-15 |
Science and Math
| Test | DeepSeek-V4.1-Flash-1017 | Qwen3.8-Max |
|---|---|---|
| GPQA Diamond | 92.6%Alibaba, Qwen3.8-Max comparison, checked 2026-10-14 | |
| FrontierMath Tier 4 (v2) | ||
| FrontierMath Tier 1-3 (v2) |
General Knowledge and Reasoning
| Test | DeepSeek-V4.1-Flash-1017 | Qwen3.8-Max |
|---|---|---|
| Humanity's Last Exam (no tools) | 42.6%DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18; printed on 2 more pages 44%DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18Dataset revision: text-only subset of HLE (dagger on the card) | 43.6%Alibaba, Qwen3.8-Max comparison, checked 2026-10-14 |
| Humanity's Last Exam (with tools) | 56.2%Alibaba, Qwen3.8-Max comparison, checked 2026-10-14; printed on 1 more pageTools: enabled; exact tools in source | |
| SimpleQA Verified |
Tool Use and Workflows
| Test | DeepSeek-V4.1-Flash-1017 | Qwen3.8-Max |
|---|---|---|
| Agents' Last Exam (pass rate) | 35.4%DeepSeek, DeepSeek-V4.1-Flash-1017 model card, checked 2026-10-18; printed on 1 more page | 27%Alibaba, Qwen3.8-Max comparison, checked 2026-10-14; printed on 1 more page |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked; a dash means the developer lists that price in another unit or not at all. Cost per task is measured by Vals AI.
| Price | DeepSeek-V4.1-Flash-1017 | Qwen3.8-Max |
|---|---|---|
| Input | $0.3DeepSeek, DeepSeek API pricing, checked 2026-10-18 | $1.65Alibaba, Alibaba Model Studio pricing, checked 2026-10-15 |
| Cached input | $0.006DeepSeek, DeepSeek API pricing, checked 2026-10-18 | - |
| Output | $1.2DeepSeek, DeepSeek API pricing, checked 2026-10-18 | $4.951Alibaba, Alibaba Model Studio pricing, checked 2026-10-15 |
| Input, off-peak hours | $0.15DeepSeek, DeepSeek API pricing, checked 2026-10-18 | - |
| Cached input, off-peak hours | $0.003DeepSeek, DeepSeek API pricing, checked 2026-10-18 | - |
| Output, off-peak hours | $0.6DeepSeek, DeepSeek API pricing, checked 2026-10-18 | - |
| Cost per taskVals AI, USD, lower is better |
DeepSeek-V4.1-Flash-1017 has 38 more and Qwen3.8-Max has 33 more: tests only one of them has a number for, listed on its model page.
More side by side
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. A pair has a page when both models are their developers' flagships and both have a number for at least 10 of the same tests. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.