GPT-6 Solvs.DeepSeek V4.1 Flash 1017
Which one is better?
Level in the overall index: the gap is too small for a clear winner. DeepSeek V4.1 Flash 1017 is cheaper: GPT-6 Sol costs 13.3 times (input) and 16.7 times (output) as much per token.
73
GPT-6 Sol
Rank 12 to 18
64
DeepSeek V4.1 Flash 1017
Rank 14 to 22
110
GPT-6 Sol
fairly fast
178
DeepSeek V4.1 Flash 1017
fast
$4
GPT-6 Sol
fairly expensive
$0.26
DeepSeek V4.1 Flash 1017
cheap
GPT-6 Sol
- Subscription
At OpenAI from €23 a month (ChatGPT Plus). Through other providers from ≈ €6.36 a month (ElevenLabs Starter, with limited credits). 57 plans in Germany.
- Via API
$2 input, $10 output per 1M tokens, unchanged since Sep 24, 2026.
- Note
- There is a successor: GPT-6.1 Sol (rank 6 to 9, same price).
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.
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.
GPT-6 Sol ahead: 3DeepSeek V4.1 Flash 1017 ahead: 2level: 1too little data: 4of 10 areas
AreaGPT-6 SolDeepSeek V4.1 Flash 10170 to 100, higher is betterResult
Areas in the overall index
CodingGPT-6 Sol aheadGPT-6 Sol: 84DeepSeek V4.1 Flash 1017: 72
ReasoningGPT-6 Sol aheadGPT-6 Sol: 82DeepSeek V4.1 Flash 1017: 45
Mathematicsonly GPT-6 Sol has a scoreGPT-6 Sol: 88DeepSeek V4.1 Flash 1017: not enough data
KnowledgeGPT-6 Sol aheadGPT-6 Sol: 73DeepSeek V4.1 Flash 1017: 33
AgentsDeepSeek V4.1 Flash 1017 aheadGPT-6 Sol: 65DeepSeek V4.1 Flash 1017: 75
Generalonly GPT-6 Sol has a scoreGPT-6 Sol: 80DeepSeek V4.1 Flash 1017: not enough data
Multimodaltoo little dataGPT-6 Sol: 62DeepSeek V4.1 Flash 1017: 55
Specialist fields
FinancelevelGPT-6 Sol: 47DeepSeek V4.1 Flash 1017: 69
LegalDeepSeek V4.1 Flash 1017 aheadGPT-6 Sol: 52DeepSeek V4.1 Flash 1017: 76
Healthonly GPT-6 Sol has a scoreGPT-6 Sol: 53DeepSeek V4.1 Flash 1017: not enough data
Show 3 more areas that do not count toward the overall index
AreaGPT-6 SolDeepSeek V4.1 Flash 10170 to 100, higher is betterResult
Cybersecurityonly GPT-6 Sol has a scoreGPT-6 Sol: 91DeepSeek V4.1 Flash 1017: not enough data
Searchonly GPT-6 Sol has a scoreGPT-6 Sol: 25DeepSeek V4.1 Flash 1017: not enough data
Productivityonly GPT-6 Sol has a scoreGPT-6 Sol: 30DeepSeek V4.1 Flash 1017: not enough data
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.
GPT-6 Sol
Reasoning (requested): high
Current attempt
- Run date
- Oct 1, 2026
- API provider
- openrouter
- Requested API model
- openai/gpt-6-sol
- API model reported in response
- openai/gpt-6-sol
- Reasoning setting
- high
- Pinned endpoint
- OpenAI | openai/gpt-6-sol-20260922
- Temperature
- Provider default
- Token limit including reasoning
- 8,192 tokens
- Test protocol
- community-visual-tests-v1
- Technical checks
- Passed, not a quality rating
- Response time
- 80.5 s
Visually reviewed. This individual test does not establish overall model quality.
DeepSeek V4.1 Flash 1017
Not tested yet
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 | GPT-6 Sol | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 73 | 64 |
| Rank | Rank 12 to 18 of 95 | Rank 14 to 22 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $2above 272,000 tokens: $4 | $0.15 |
| Outputwhat the model writes | $10above 272,000 tokens: $15 | $0.60 |
| Speed | ||
| Tokens per second | 110 | 178 |
| Technical | ||
| Context windowhow much text the model reads at once | 1.05 M tokens≈ 1,580 A4 pages | 1.05 M tokens≈ 1,570 A4 pages |
| Knowledge cutoff | Apr 20, 2026 | n/a |
| Released | Sep 22, 2026 | Oct 17, 2026 |
| Availability | Active | Open Source |
| Open weights | no | yes |
- 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: GPT-6 SolB: DeepSeek V4.1 Flash 1017
Code MigrationOverall · higher is betterTest setup not documented as identicalGPT-6 Sol: 57.2%DeepSeek V4.1 Flash 1017: 44.2%Vals AIAs of 10/18/2026
CritPt v2Overall · higher is betterGPT-6 Sol: 30.9%DeepSeek V4.1 Flash 1017: 24.0%Artificial AnalysisAs of 10/29/2026
EMBOverall · higher is betterTest setup not documented as identicalGPT-6 Sol: 71.5%DeepSeek V4.1 Flash 1017: 61.8%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalGPT-6 Sol: 49.1%DeepSeek V4.1 Flash 1017: 57%Vals AIAs of 10/20/2026
GDPval-AAOverall · higher is betterGPT-6 Sol: 1,516.8 eloDeepSeek V4.1 Flash 1017: 1,745.77 eloArtificial AnalysisAs of 10/29/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 28.8%DeepSeek V4.1 Flash 1017: 45.2%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevOverall · higher is betterGPT-6 Sol: 1,677DeepSeek V4.1 Flash 1017: 1,666LMArenaAs of 10/27/2026
MMMU-ProOverall · higher is betterGPT-6 Sol: 82.9%DeepSeek V4.1 Flash 1017: 80.6%Artificial AnalysisAs of 10/29/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalGPT-6 Sol: 15%DeepSeek V4.1 Flash 1017: 44.4%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalGPT-6 Sol: 44.4%DeepSeek V4.1 Flash 1017: 31.8%Vals AIAs of 10/26/2026
Show 54 more benchmarks
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-6 Sol: 87.8%DeepSeek V4.1 Flash 1017: 87.7%Vals AIAs of 10/26/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalGPT-6 Sol: 52.9%DeepSeek V4.1 Flash 1017: 35.6%Vals AIAs of 10/18/2026
EMBComps · higher is betterTest setup not documented as identicalGPT-6 Sol: 73.3%DeepSeek V4.1 Flash 1017: 49.8%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalGPT-6 Sol: 43.2%DeepSeek V4.1 Flash 1017: 58.4%Vals AIAs of 10/20/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 39.4%DeepSeek V4.1 Flash 1017: 59.1%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevHTML development · higher is betterGPT-6 Sol: 1,678DeepSeek V4.1 Flash 1017: 1,705LMArenaAs of 10/27/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 6.7%DeepSeek V4.1 Flash 1017: 23.3%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalGPT-6 Sol: 6.7%DeepSeek V4.1 Flash 1017: 6.7%Vals AIAs of 10/26/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalGPT-6 Sol: 70%DeepSeek V4.1 Flash 1017: 70%Vals AIAs of 10/18/2026
EMBDataroom · higher is betterTest setup not documented as identicalGPT-6 Sol: 83.9%DeepSeek V4.1 Flash 1017: 82.8%Vals AIAs of 10/20/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 36%DeepSeek V4.1 Flash 1017: 45.2%Vals AIAs of 10/20/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6 Sol: 80.5%DeepSeek V4.1 Flash 1017: 91.3%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevReact development · higher is betterGPT-6 Sol: 1,680DeepSeek V4.1 Flash 1017: 1,672LMArenaAs of 10/27/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 50.7%DeepSeek V4.1 Flash 1017: 73.2%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalGPT-6 Sol: 41.7%DeepSeek V4.1 Flash 1017: 25%Vals AIAs of 10/26/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalGPT-6 Sol: 4.375 / 5DeepSeek V4.1 Flash 1017: 3.992 / 5Vals AIAs of 10/18/2026
EMBDCF · higher is betterTest setup not documented as identicalGPT-6 Sol: 63.1%DeepSeek V4.1 Flash 1017: 53%Vals AIAs of 10/20/2026
Finance Agent (v2)Comparables · higher is betterTest setup not documented as identicalGPT-6 Sol: 40.8%DeepSeek V4.1 Flash 1017: 47.5%Vals AIAs of 10/20/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 27.9%DeepSeek V4.1 Flash 1017: 44.2%Vals AIAs of 10/26/2026
LMArena Code Arena WebDevWeb development · higher is betterGPT-6 Sol: 1,677DeepSeek V4.1 Flash 1017: 1,666LMArenaAs of 10/27/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 23.2%DeepSeek V4.1 Flash 1017: 56.4%Vals AIAs of 10/26/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalGPT-6 Sol: 45.5%DeepSeek V4.1 Flash 1017: 42.4%Vals AIAs of 10/26/2026
EMBLBO · higher is betterTest setup not documented as identicalGPT-6 Sol: 59.4%DeepSeek V4.1 Flash 1017: 57.8%Vals AIAs of 10/20/2026
Finance Agent (v2)Disclosure Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 55.6%DeepSeek V4.1 Flash 1017: 66.3%Vals AIAs of 10/20/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6 Sol: 80.4%DeepSeek V4.1 Flash 1017: 87.8%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 56.1%DeepSeek V4.1 Flash 1017: 75%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalGPT-6 Sol: 40.7%DeepSeek V4.1 Flash 1017: 18.5%Vals AIAs of 10/26/2026
EMBM&A · higher is betterTest setup not documented as identicalGPT-6 Sol: 83%DeepSeek V4.1 Flash 1017: 62.3%Vals AIAs of 10/20/2026
Finance Agent (v2)Earnings Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 72.4%DeepSeek V4.1 Flash 1017: 75.3%Vals AIAs of 10/20/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 18.5%DeepSeek V4.1 Flash 1017: 37%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 16.3%DeepSeek V4.1 Flash 1017: 55.8%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalGPT-6 Sol: 42.9%DeepSeek V4.1 Flash 1017: 38.1%Vals AIAs of 10/26/2026
EMBMisc · higher is betterTest setup not documented as identicalGPT-6 Sol: 65%DeepSeek V4.1 Flash 1017: 60.9%Vals AIAs of 10/20/2026
Finance Agent (v2)Financial Modeling · higher is betterTest setup not documented as identicalGPT-6 Sol: 19.3%DeepSeek V4.1 Flash 1017: 22.8%Vals AIAs of 10/20/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6 Sol: 78%DeepSeek V4.1 Flash 1017: 84.9%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 49.9%DeepSeek V4.1 Flash 1017: 72.5%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Security · higher is betterTest setup not documented as identicalGPT-6 Sol: 60%DeepSeek V4.1 Flash 1017: 26.7%Vals AIAs of 10/26/2026
EMBOperating · higher is betterTest setup not documented as identicalGPT-6 Sol: 72.9%DeepSeek V4.1 Flash 1017: 66.1%Vals AIAs of 10/20/2026
Finance Agent (v2)General Qualitative Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 53.6%DeepSeek V4.1 Flash 1017: 74.1%Vals AIAs of 10/20/2026
Legal Research BenchConstitutional / Civil Rights · All-pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 18.4%DeepSeek V4.1 Flash 1017: 42.1%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalGPT-6 Sol: 0%DeepSeek V4.1 Flash 1017: 33.3%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Software · higher is betterTest setup not documented as identicalGPT-6 Sol: 53.7%DeepSeek V4.1 Flash 1017: 37%Vals AIAs of 10/26/2026
EMBScratch · higher is betterTest setup not documented as identicalGPT-6 Sol: 69.5%DeepSeek V4.1 Flash 1017: 68.5%Vals AIAs of 10/20/2026
Finance Agent (v2)General Quantitative Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 70%DeepSeek V4.1 Flash 1017: 79.2%Vals AIAs of 10/20/2026
Legal Research BenchConstitutional / Civil Rights · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6 Sol: 78%DeepSeek V4.1 Flash 1017: 86.6%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalGPT-6 Sol: 53.7%DeepSeek V4.1 Flash 1017: 79.4%Vals AIAs of 10/26/2026
EMBTemplate · higher is betterTest setup not documented as identicalGPT-6 Sol: 73.5%DeepSeek V4.1 Flash 1017: 54.7%Vals AIAs of 10/20/2026
Finance Agent (v2)Market Analysis · higher is betterTest setup not documented as identicalGPT-6 Sol: 58%DeepSeek V4.1 Flash 1017: 62.7%Vals AIAs of 10/20/2026
Legal Research BenchCriminal · All-pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 26.3%DeepSeek V4.1 Flash 1017: 35.1%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalGPT-6 Sol: 26.7%DeepSeek V4.1 Flash 1017: 45.7%Vals AIAs of 10/26/2026
Finance Agent (v2)Precedents · higher is betterTest setup not documented as identicalGPT-6 Sol: 28.5%DeepSeek V4.1 Flash 1017: 26.5%Vals AIAs of 10/20/2026
Legal Research BenchCriminal · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-6 Sol: 79.7%DeepSeek V4.1 Flash 1017: 83.2%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalGPT-6 Sol: 69.5%DeepSeek V4.1 Flash 1017: 79.5%Vals AIAs of 10/26/2026
Legal Research BenchFamily · All-pass · higher is betterTest setup not documented as identicalGPT-6 Sol: 9.1%DeepSeek V4.1 Flash 1017: 27.3%Vals AIAs of 10/26/2026
Compare another matchup
More matchups
Related LLM comparisons
Compare GPT-6 Sol and DeepSeek V4.1 Flash 1017 with other leading models.