DeepSeek V4.1 Flash 1017 vs Qwen4 Max
Full profiles: DeepSeek V4.1 Flash 1017 (DeepSeek) and Qwen4 Max (Alibaba): every benchmark, price and rank.
Updated · Data from 15 sources
As of 19 Nov 2026, there are not enough shared benchmarks for a verdict, and DeepSeek V4.1 Flash is 4.3× cheaper at $0.525 vs $2.25 per 1M tokens blended. Choose DeepSeek V4.1 Flash for coding (62 vs 55) and fast first answers (44.5 s vs 139.2 s), where it also streams 3×+ faster; choose Qwen4 Max for knowledge (59 vs 48) and reasoning (59 vs 55).
Key facts (as of 19 Nov 2026)
- DeepSeek V4.1 Flash costs $0.525 per 1M tokens blended (list price, 19 Nov 2026).
- Qwen4 Max costs $2.25 per 1M tokens blended (list price, 19 Nov 2026).
- DeepSeek V4.1 Flash streams 3×+ faster than Qwen4 Max (Artificial Analysis, 7-day median, 19 Nov 2026).
- Of the 13 benchmarks both models have, Qwen4 Max leads 11 (BenchLeader, 19 Nov 2026).
Which to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | DeepSeek V4.1 Flash 1017 | 62 vs 55 category score; FrontierCode 2.0 (AA) 28.5% vs 26.4% | Medium |
| Reasoning | Qwen4 Max | 59 vs 55 category score; HLE-Diamond (AA) 44.9% vs 25.3% | Medium |
| Knowledge | Qwen4 Max | 59 vs 48 category score; AA-Omniscience v1.1 27.7 vs 0.9 | High |
| Lowest cost | DeepSeek V4.1 Flash 1017 | $0.525 vs $2.25 per 1M blended; agentic coding session $0.023 vs $0.108 | – |
| Fastest first answer | DeepSeek V4.1 Flash 1017 | 44.5 s (DeepSeek V4.1 Flash 1017 (max)) vs 139.2 s (Qwen4 Max) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Not enough shared benchmarks for a verdict.
- DeepSeek V4.1 Flash 1017 (max) is stronger in coding.
- Qwen4 Max is stronger in knowledge, reasoning.
- DeepSeek V4.1 Flash 1017 (max) is 4.3× cheaper ($0.525 vs $2.25 per 1M blended).
- DeepSeek V4.1 Flash 1017 (max) streams 2.8× faster (165 vs 59 tokens per second).
At a glance
| Spec | DeepSeek V4.1 Flash 1017 | Qwen4 Max |
|---|---|---|
| Developer | DeepSeek | Alibaba |
| Released | 17 Oct 2026 | 16 Nov 2026 |
| Context window (tokens) | 1,048,576 | 991,808 |
| Compared at | DeepSeek V4.1 Flash 1017 (max) | Qwen4 Max |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $0.300 / $1.20 / $0.0060 | $1.50 / $4.50 / $0.071 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | DeepSeek V4.1 Flash 1017 (max) | Qwen4 Max | Leader |
|---|---|---|---|
| Reasoning | 55.0 | 58.5 | Qwen4 Max |
| Coding | 61.7 | 55.1 | DeepSeek V4.1 Flash 1017 |
| Agents & tools | 54.6 | – | not comparable |
| Maths | 60.5 | – | not comparable |
| Knowledge | 47.5 | 59.0 | Qwen4 Max |
| Multimodal | 62.7 | – | not comparable |
| Long context | 66.0 | – | not comparable |
| Composite | 53.5 | – | not comparable |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 13 benchmarks both have, DeepSeek V4.1 Flash 1017 leads 2, Qwen4 Max leads 11. Every overall index that rates both puts Qwen4 Max ahead.
| Overall index | DeepSeek V4.1 Flash 1017 (max) | Qwen4 Max | Leader |
|---|---|---|---|
| AA Intelligence Index v5.0.1 | 32.6 | 42.9 | Qwen4 Max |
| Vals Index | 61.3 | 63.2† | Qwen4 Max |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | DeepSeek V4.1 Flash 1017 (max) | Qwen4 Max |
|---|---|---|
| Blended price per 1M tokens | $0.525 | $2.25 |
| Input / output per 1M | $0.300 / $1.20 | $1.50 / $4.50 |
| Cached input per 1M | $0.0060 | $0.071 |
| Price per task: chat reply | $0.0005 | $0.0020 |
| Price per task: summarize a 30-page report | $0.0043 | $0.021 |
| Price per task: code edit | $0.0036 | $0.016 |
| Price per task: agentic coding session | $0.023 | $0.108 |
| Price per task: structured extraction | $0.0008 | $0.0039 |
| Agentic coding session, input mostly cached | $0.0096 | $0.044 |
| Cost per benchmark task (AA Index) | $0.602 | $3.27 |
| Output tokens per task (AA Index) | 139k | 105k |
| Of which reasoning | 91k | 69k |
| Time per task (AA Index) | 14 min | 30 min |
| Output speed | 165 tok/s | 59 tok/s |
| Time to first answer | 44.5 s | 139.2 s |
| Time to a complete answer, last measured 13 Nov 2026 | 91.2 s | – |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $0.602 on DeepSeek V4.1 Flash 1017 (max) and $3.27 on Qwen4 Max, and DeepSeek V4.1 Flash 1017 (max) wrote 1.3× as many output tokens for the same work, which a per-token price hides.
Each model is compared at its best-ranked reasoning-effort setting. DeepSeek V4.1 Flash 1017 (max) scores 56.8 and takes 44 s to its first answer token; DeepSeek V4.1 Flash 1017 (high) scores 50.9 in 18 s, DeepSeek V4.1 Flash 1017 (no reasoning) scores 44.9 in 1 s. Qwen4 Max and takes 139 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
96 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | DeepSeek V4.1 Flash 1017 (max) | Qwen4 Max |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 56.8 | – |
| Agents & tools score | BenchLeader | 54.6 | – |
| Coding score | BenchLeader | 61.7 | 55.1 |
| Composite score | BenchLeader | 53.5 | – |
| Knowledge score | BenchLeader | 47.5 | 59.0 |
| Long context score | BenchLeader | 66.0 | – |
| Maths score | BenchLeader | 60.5 | – |
| Multimodal score | BenchLeader | 62.7 | – |
| Reasoning score | BenchLeader | 55.0 | 58.5 |
| Blended price $/M | BenchLeader | $0.525 | $2.25 |
| Output speed | BenchLeader | 165 tok/s | 59 tok/s |
| Time to first answer | BenchLeader | 44.5 s | 139.2 s |
| Context window | BenchLeader | 1,048,576 tokens | 991,808 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 93.2% | – |
| LiveBench 2.0 Reasoning | LiveBench | 89.1% | 92.2%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 43.3% | – |
| HLE-Diamond (AA) | Artificial Analysis | 25.3% | 44.9% |
| ARC-AGI-1 | ARC Prize | 93.5% | – |
| ARC-AGI-2 | ARC Prize | 78.1% | – |
| ARC-AGI-3 | ARC Prize | 5.8% | – |
| CritPt | Artificial Analysis | 24.0% | – |
| CritPt v2 hard subset (AA) | Artificial Analysis | 25.0% | 43.0% |
| HLE-Diamond (Scale) | Scale AI SEAL | 20.5%† | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 46.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 49.0% | – |
| Coding | |||
| SciCode | SciCode | 55.9% | – |
| Arena WebDev | Arena (LMArena) | 1659 | 1750† |
| LiveBench 2.0 Coding | LiveBench | 80.4% | 69.8%† |
| Code Migration | Vals AI | 44.2% | – |
| Code Migration v1.1 | Vals AI | 67.5% | – |
| Vibe Code Bench v1.1 | Vals AI | 87.7% | 86.7%† |
| Vibe Code Bench 1-100 v1.1 | Vals AI | 26.1% | – |
| CursorBench | Cursor | 47.7% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1622 | – |
| WeirdML v3 | WeirdML | 9.1%† | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 33.8% | 48.5% |
| GameBench 2 Overall | DuelLab GameBench 2 | 61.4† | – |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 69.9 | – |
Show all 96 benchmarks
| Metric | Publisher | DeepSeek V4.1 Flash 1017 (max) | Qwen4 Max |
|---|---|---|---|
| Coding | |||
| Design Arena Website | Design Arena | 1292† | – |
| FrontierCode 1.1 (AA) | Artificial Analysis | 43.7% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 28.5% | 26.4% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 38.5% | – |
| APEX-Agents | Mercor | 69.8% | – |
| Arena Agent | Arena (LMArena) | 0.8 | 7.3† |
| LiveBench Long Agentic | LiveBench | 38.8% | 46.6%† |
| LiveBench Browser | LiveBench | 67.2% | 80.7%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 62.3% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1746 | 1809 |
| Analyst Agent (AA) | Artificial Analysis | – | 46.3% |
| APEX-Agents (AA) | Artificial Analysis | – | 59.1% |
| Finance Agent v2 | Vals AI | 57.0% | – |
| Finance Agent v2.1 | Vals AI | 62.9% | 66.7%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 14.2% | 21.3%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 9.2% | – |
| Legal Research Bench | Vals AI | 45.2% | 41.4%† |
| Robo-bench | Vals AI | 4.2% | – |
| Tax Agent Bench | Vals AI | 44.4% | 40.4%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 31.8% | 48.5%† |
| Arena Agent Task Completion | Arena (LMArena) | 2.2 | 8.8† |
| AutomationBench | Artificial Analysis | 66.6% | 72.6% |
| GDP.pdf (AA) | Artificial Analysis | 17.2% | 26.2% |
| Harvey LAB-AA v1.1 | Harvey | – | 9.4% |
| EnterpriseOps-Gym | Artificial Analysis | – | 48.5% |
| AA-Briefcase v1.1 | Artificial Analysis | 1570 | 1686 |
| GDPx | GDPx by SemiAnalysis | 5.4% | – |
| Design Arena Agentic | Design Arena | 1284† | 1356 |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 12.9% | 23.3% |
| CWE-Bench (AA) | Artificial Analysis | 69.2% | – |
| DeepSec-Bench (AA) | Artificial Analysis | 24.9% | – |
| CyberGym end-to-end (AA) | Artificial Analysis | 76.3% | – |
| MKA (AA) | Artificial Analysis | 38.5% | – |
| FACTS Search | 89.9%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 71.2% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 46.3% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 99.4% | – |
| ArXivMath | MathArena | 42.5% | – |
| BrokenArXiv | MathArena | 48.7% | – |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 42.5% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 79.5% | 83.4%† |
| LiveBench Research | LiveBench | 78.6% | 84.7%† |
| AA-Omniscience v1.1 | Artificial Analysis | 0.9 | 27.7 |
| PRBench Finance | Scale AI SEAL | 47.1%† | – |
| PRBench Legal | Scale AI SEAL | 47.3%† | – |
| Excel Modeling Benchmark | Vals AI | 61.8% | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 69.2% | 70.8%† |
| Access to Justice Benchmark | Vals AI | 73.1% | – |
| DrugDiscoveryBench | Scale AI SEAL | 60.6%† | – |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 39.6% | 43.7% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 35.9% | 71.6% |
| FACTS Parametric | 52.8%† | – | |
| Instruction following | |||
| MultiChallenge | Scale AI SEAL | 74.9%† | – |
| Multimodal | |||
| LiveBench Design | LiveBench | 79.8% | 79.1%† |
| MMMU-Pro | Artificial Analysis | 80.6% | – |
| Humanity's Sixth Sense | Scale AI SEAL | 30.1% | – |
| VIALS-AA | Handshake AI | 40.4% | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 82.7% | – |
| MLCR | Artificial Analysis | 26.7% | 19.4% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 159.4† | – |
| LiveBench 2.0 | LiveBench | 70.3% | 73.1%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 32.6 | 42.9 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 45.1 | – |
| AA Progress Index v1 | Artificial Analysis | 323.7 | – |
| Vals Index | Vals AI | 61.3 | 63.2† |
| Vals Finance Index | Vals AI | 60.9% | 62.0%† |
| Vals Router Index | Vals AI | 61.3%† | – |
| Vals Legal Index | Vals AI | 71.9% | 70.7%† |
| AA Cyber Index | Artificial Analysis | 56.8 | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 27.2%† | – |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 44.4 | – |
Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- DeepSeek V4.1 Flash 1017 (max): 1 score revision.
- DeepSeek V4.1 Flash 1017 (max): 1 score revision.
- DeepSeek V4.1 Flash 1017 (max): BenchLeader Index 58.0 → 57.1.
- DeepSeek V4.1 Flash 1017 (max): 1 new result (Robo-bench); 1 score revision.
- DeepSeek V4.1 Flash 1017 (max): 1 score revision.
- DeepSeek V4.1 Flash 1017 (max): 8 new results (LiveBench 2.0, LiveBench Long Agentic, LiveBench 2.0 Reasoning…).
- DeepSeek V4.1 Flash 1017 (max): BenchLeader Index 58.5 → 58.0.
- DeepSeek V4.1 Flash 1017 (max): 1 new result (Terminal-Bench); 1 score revision.
- DeepSeek V4.1 Flash 1017 (max): BenchLeader Index 59.0 → 58.5.
- DeepSeek V4.1 Flash 1017 (max): 1 score revision.
Related comparisons
- DeepSeek V4.1 Flash 1017 vs Claude Fable 5.2
- DeepSeek V4.1 Flash 1017 vs Gemini 4 Carbon
- DeepSeek V4.1 Flash 1017 vs Claude Opus 5.5
- DeepSeek V4.1 Flash 1017 vs GPT-6 Astra
- Qwen4 Max vs Qwen3.8 Max
- Qwen4 Max vs Inkling 2 Small
- DeepSeek V4 Flash vs Qwen4 Max
- DeepSeek V4.1 Flash 1017 vs Qwen3.8-Flash-Next
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
DeepSeek V4.1 Flash 1017 vs Qwen4 Max: questions
- DeepSeek V4.1 Flash 1017 vs Qwen4 Max: which is cheaper, and will that change?
- DeepSeek V4.1 Flash 1017 is cheaper today: $0.525 against $2.25 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is DeepSeek V4.1 Flash 1017 or Qwen4 Max better for coding?
- DeepSeek V4.1 Flash 1017 scores higher in coding (62 vs 55 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 28.5% for DeepSeek V4.1 Flash 1017 against 26.4% for Qwen4 Max.
- Which is faster, DeepSeek V4.1 Flash 1017 or Qwen4 Max?
- DeepSeek V4.1 Flash 1017 streams 3×+ faster (165 vs 59 output tokens per second, Artificial Analysis 7-day median).
- Is DeepSeek V4.1 Flash the same as DeepSeek V4.1 Flash 1017?
- DeepSeek V4.1 Flash 1017 is the checkpoint compared here (BenchLeader Index 56.8); people searching for DeepSeek V4.1 Flash land on this page because it replaced that earlier build.
- Which is better for long documents?
- DeepSeek V4.1 Flash 1017 accepts more context: 1,048,576 against 991,808 tokens for Qwen4 Max.
More questions (3)
- Which has lower latency?
- DeepSeek V4.1 Flash 1017 answers first: 44.5 s against 139.2 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on DeepSeek V4.1 Flash 1017 vs Qwen4 Max?
- Across the 13 benchmarks both have, DeepSeek V4.1 Flash 1017 leads 2, Qwen4 Max leads 11. Every overall index that rates both puts Qwen4 Max ahead.
- When was Qwen4 Max released?
- Qwen4 Max was released on 16 Nov 2026.