DeepSeek V4.1 Flash 1017vs.Qwen 3.8 Max 0902
Which one is better?
DeepSeek V4.1 Flash 1017 is clearly ahead in the overall index and is cheaper too: Qwen 3.8 Max 0902 costs 11 times (input) and 8.3 times (output) as much per token.
64
DeepSeek V4.1 Flash 1017
Rank 14 to 22
50
Qwen 3.8 Max 0902
Rank 23 to 31
178
DeepSeek V4.1 Flash 1017
fast
41
Qwen 3.8 Max 0902
slow
$0.26
DeepSeek V4.1 Flash 1017
cheap
$2.48
Qwen 3.8 Max 0902
fairly expensive
DeepSeek V4.1 Flash 1017
- Subscription
No DeepSeek subscription includes this model. Through other providers from ≈ €6.36 a month (Token Plan Individual Lite, with limited credits). 7 plans in Germany.
- Via API
$0.15 input, $0.60 output per 1M tokens according to the provider; the price index has listed it at $0.30 and $1 since Oct 26, 2026.
Qwen 3.8 Max 0902
- Subscription
No Alibaba subscription includes this model. Through other providers from ≈ €1.06 a month (Command Code Go, with limited credits). 5 plans in Germany.
- Via API
$1.65 input, $4.951 output per 1M tokens, unchanged since Aug 24, 2026.
Overall index with data through Oct 29, 2026 · Prices from Oct 29, 2026 · Speed: measured by Artificial Analysis · Subscriptions as of Oct 24, 2026 · Subscription prices incl. VAT
Where is the difference?
Values from 0 to 100 per task area. We only name a winner when the gap is large enough and there are enough tests.
DeepSeek V4.1 Flash 1017 ahead: 3Qwen 3.8 Max 0902 ahead: 1level: 2too little data: 4of 10 areas
AreaDeepSeek V4.1 Flash 1017Qwen 3.8 Max 09020 to 100, higher is betterResult
Areas in the overall index
CodingDeepSeek V4.1 Flash 1017 aheadDeepSeek V4.1 Flash 1017: 72Qwen 3.8 Max 0902: 51
ReasoninglevelDeepSeek V4.1 Flash 1017: 45Qwen 3.8 Max 0902: 50
Mathematicsonly Qwen 3.8 Max 0902 has a scoreDeepSeek V4.1 Flash 1017: not enough dataQwen 3.8 Max 0902: 42
KnowledgeQwen 3.8 Max 0902 aheadDeepSeek V4.1 Flash 1017: 33Qwen 3.8 Max 0902: 39
AgentsDeepSeek V4.1 Flash 1017 aheadDeepSeek V4.1 Flash 1017: 75Qwen 3.8 Max 0902: 46
Generalonly Qwen 3.8 Max 0902 has a scoreDeepSeek V4.1 Flash 1017: not enough dataQwen 3.8 Max 0902: 54
Multimodaltoo little dataDeepSeek V4.1 Flash 1017: 55Qwen 3.8 Max 0902: 56
Specialist fields
FinanceDeepSeek V4.1 Flash 1017 aheadDeepSeek V4.1 Flash 1017: 69Qwen 3.8 Max 0902: 45
LegallevelDeepSeek V4.1 Flash 1017: 76Qwen 3.8 Max 0902: 76
Healthonly Qwen 3.8 Max 0902 has a scoreDeepSeek V4.1 Flash 1017: not enough dataQwen 3.8 Max 0902: 31
Show 3 more areas that do not count toward the overall index
AreaDeepSeek V4.1 Flash 1017Qwen 3.8 Max 09020 to 100, higher is betterResult
Cybersecurityonly Qwen 3.8 Max 0902 has a scoreDeepSeek V4.1 Flash 1017: not enough dataQwen 3.8 Max 0902: 4
Productivityonly Qwen 3.8 Max 0902 has a scoreDeepSeek V4.1 Flash 1017: not enough dataQwen 3.8 Max 0902: 62
Educationonly Qwen 3.8 Max 0902 has a scoreDeepSeek V4.1 Flash 1017: not enough dataQwen 3.8 Max 0902: 22
See for yourself: same task, one attempt
The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.
Pelican on a bicycle
A community classic for free-form SVG drawing.
DeepSeek V4.1 Flash 1017
Not tested yet
Qwen 3.8 Max 0902
The response reached the token limit. No complete recording is available.
Reasoning (requested): high
Current attempt
- Run date
- Oct 5, 2026
- API provider
- openrouter
- Requested API model
- qwen/qwen3.8-max-0902
- API model reported in response
- qwen/qwen3.8-max-0902
- Reasoning setting
- high
- Pinned endpoint
- Alibaba | qwen/qwen3.8-max-20260902
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Failed
- Response time
- 189.9 s
Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.
Earlier attempts (3)
- Oct 2, 2026API request failedReasoning setting: high
- Oct 1, 2026API request failedReasoning setting: high
- Sep 7, 2026API request failedReasoning setting: high
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)SVG short test
There is no shared test round for this selection. Results from different rounds are not mixed.
All data side by side
The better value is bold. For the overall index only when the gap is clear.
| Metric | DeepSeek V4.1 Flash 1017 | Qwen 3.8 Max 0902 |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 64 | 50 |
| Rank | Rank 14 to 22 of 95 | Rank 23 to 31 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $0.15 | $1.65 |
| Outputwhat the model writes | $0.60 | $4.951 |
| Speed | ||
| Tokens per second | 178 | 41 |
| Technical | ||
| Context windowhow much text the model reads at once | 1.05 M tokens≈ 1,570 A4 pages | 1 M tokens≈ 1,500 A4 pages |
| Knowledge cutoff | n/a | n/a |
| Released | Oct 17, 2026 | Sep 2, 2026 |
| Availability | Open Source | API-only |
| Open weights | yes | no |
- DeepSeek V4.1 Flash 1017: At peak times (Mon, Tue, Wed, Thu, Fri, 01:00-04:00 UTC; Mon, Tue, Wed, Thu, Fri, 06:00-10:00 UTC) the price is $0.30 input and $1.20 output per 1M tokens. The table shows the off-peak price.
- DeepSeek V4.1 Flash 1017, Time-based API pricing: Off peak: $0.15 input, $0.60 output, and $0.003 cached input. Weekdays UTC 01:00-04:00 and 06:00-10:00: $0.30, $1.20, and $0.006. Chinese public holidays are excluded. Source
Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis
Shared benchmarks
Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.
A: DeepSeek V4.1 Flash 1017B: Qwen 3.8 Max 0902
Code MigrationOverall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 44.2%Qwen 3.8 Max 0902: 24%Vals AIAs of 10/18/2026
EMBOverall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 61.8%Qwen 3.8 Max 0902: 60.1%Vals AIAs of 10/20/2026
EMB v1.1Overall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 69.2%Qwen 3.8 Max 0902: 66%Vals AIAs of 10/26/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 57%Qwen 3.8 Max 0902: 50.6%Vals AIAs of 10/20/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 45.2%Qwen 3.8 Max 0902: 47.6%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevOverall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 1,666Qwen 3.8 Max 0902: 1,676LMArenaAs of 10/27/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 44.4%Qwen 3.8 Max 0902: 32.1%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 31.8%Qwen 3.8 Max 0902: 34.3%Vals AIAs of 10/26/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 87.7%Qwen 3.8 Max 0902: 64.7%Vals AIAs of 10/26/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 35.6%Qwen 3.8 Max 0902: 11.9%Vals AIAs of 10/18/2026
Show 54 more benchmarks
EMBComps · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 49.8%Qwen 3.8 Max 0902: 54.3%Vals AIAs of 10/20/2026
EMB v1.1Comps · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 70.8%Qwen 3.8 Max 0902: 65.7%Vals AIAs of 10/26/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 58.4%Qwen 3.8 Max 0902: 48.4%Vals AIAs of 10/20/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 59.1%Qwen 3.8 Max 0902: 59.1%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevHTML development · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 1,705Qwen 3.8 Max 0902: 1,658LMArenaAs of 10/27/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 23.3%Qwen 3.8 Max 0902: 20%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 6.7%Qwen 3.8 Max 0902: 0%Vals AIAs of 10/26/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 70%Qwen 3.8 Max 0902: 60%Vals AIAs of 10/18/2026
EMBDataroom · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 82.8%Qwen 3.8 Max 0902: 83.5%Vals AIAs of 10/20/2026
EMB v1.1Dataroom · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 86.5%Qwen 3.8 Max 0902: 84.3%Vals AIAs of 10/26/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 45.2%Qwen 3.8 Max 0902: 38.2%Vals AIAs of 10/20/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 91.3%Qwen 3.8 Max 0902: 90.5%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevReact development · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 1,672Qwen 3.8 Max 0902: 1,692LMArenaAs of 10/27/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 73.2%Qwen 3.8 Max 0902: 62.6%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 25%Qwen 3.8 Max 0902: 50%Vals AIAs of 10/26/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 3.992 / 5Qwen 3.8 Max 0902: 4.255 / 5Vals AIAs of 10/18/2026
EMBDCF · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 53%Qwen 3.8 Max 0902: 49.1%Vals AIAs of 10/20/2026
EMB v1.1DCF · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 59.7%Qwen 3.8 Max 0902: 54.2%Vals AIAs of 10/26/2026
Finance Agent (v2)Comparables · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 47.5%Qwen 3.8 Max 0902: 44.3%Vals AIAs of 10/20/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 44.2%Qwen 3.8 Max 0902: 46.5%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevWeb development · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 1,666Qwen 3.8 Max 0902: 1,676LMArenaAs of 10/27/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 56.4%Qwen 3.8 Max 0902: 49.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 42.4%Qwen 3.8 Max 0902: 48.5%Vals AIAs of 10/26/2026
EMBLBO · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 57.8%Qwen 3.8 Max 0902: 46.9%Vals AIAs of 10/20/2026
EMB v1.1LBO · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 62.5%Qwen 3.8 Max 0902: 50.4%Vals AIAs of 10/26/2026
Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 66.3%Qwen 3.8 Max 0902: 60.5%Vals AIAs of 10/20/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 87.8%Qwen 3.8 Max 0902: 86.7%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 75%Qwen 3.8 Max 0902: 71.4%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 18.5%Qwen 3.8 Max 0902: 14.8%Vals AIAs of 10/26/2026
EMBM&A · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 62.3%Qwen 3.8 Max 0902: 60.7%Vals AIAs of 10/20/2026
EMB v1.1M&A · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 73.1%Qwen 3.8 Max 0902: 73%Vals AIAs of 10/26/2026
Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 75.3%Qwen 3.8 Max 0902: 67.7%Vals AIAs of 10/20/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 37%Qwen 3.8 Max 0902: 48.1%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 55.8%Qwen 3.8 Max 0902: 27.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 38.1%Qwen 3.8 Max 0902: 33.3%Vals AIAs of 10/26/2026
EMBMisc · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 60.9%Qwen 3.8 Max 0902: 60.7%Vals AIAs of 10/20/2026
EMB v1.1Misc · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 65.7%Qwen 3.8 Max 0902: 65%Vals AIAs of 10/26/2026
Finance Agent (v2)Financial Modeling · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 22.8%Qwen 3.8 Max 0902: 20.4%Vals AIAs of 10/20/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 84.9%Qwen 3.8 Max 0902: 84.2%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 72.5%Qwen 3.8 Max 0902: 62.1%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Security · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 26.7%Qwen 3.8 Max 0902: 40%Vals AIAs of 10/26/2026
EMBOperating · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 66.1%Qwen 3.8 Max 0902: 65.1%Vals AIAs of 10/20/2026
EMB v1.1Operating · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 66%Qwen 3.8 Max 0902: 69.4%Vals AIAs of 10/26/2026
Finance Agent (v2)General Qualitative Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 74.1%Qwen 3.8 Max 0902: 63.4%Vals AIAs of 10/20/2026
Legal Research BenchConstitutional / Civil Rights · All-pass · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 42.1%Qwen 3.8 Max 0902: 34.2%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 33.3%Qwen 3.8 Max 0902: 20%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Software · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 37%Qwen 3.8 Max 0902: 40.7%Vals AIAs of 10/26/2026
EMBScratch · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 68.5%Qwen 3.8 Max 0902: 64.5%Vals AIAs of 10/20/2026
EMB v1.1Scratch · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 67.3%Qwen 3.8 Max 0902: 66.3%Vals AIAs of 10/26/2026
Finance Agent (v2)General Quantitative Analysis · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 79.2%Qwen 3.8 Max 0902: 67.4%Vals AIAs of 10/20/2026
Legal Research BenchConstitutional / Civil Rights · Weighted partial credit · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 86.6%Qwen 3.8 Max 0902: 85.2%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 79.4%Qwen 3.8 Max 0902: 64.9%Vals AIAs of 10/26/2026
EMBTemplate · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 54.7%Qwen 3.8 Max 0902: 55.1%Vals AIAs of 10/20/2026
EMB v1.1Template · higher is betterTest setup not documented as identicalDeepSeek V4.1 Flash 1017: 70.8%Qwen 3.8 Max 0902: 65.3%Vals AIAs of 10/26/2026
Compare another matchup
More matchups
Related LLM comparisons
Compare DeepSeek V4.1 Flash 1017 and Qwen 3.8 Max 0902 with other leading models.