Kimi K3.1 Provs.Qwen 3.8 Max 0902
Which one is better?
Kimi K3.1 Pro is clearly ahead in the overall index, but costs 1.2 times (input) and 2 times (output) as much per token.
80
Kimi K3.1 Pro
Rank 10 to 13
50
Qwen 3.8 Max 0902
Rank 23 to 31
36
Kimi K3.1 Pro
slow
41
Qwen 3.8 Max 0902
slow
$4
Kimi K3.1 Pro
fairly expensive
$2.48
Qwen 3.8 Max 0902
fairly expensive
Kimi K3.1 Pro
- Subscription
At Moonshot AI from ≈ €20.14 a month (Kimi Plus, with limited credits). 4 plans in Germany.
- Via API
$2 input, $10 output per 1M tokens.
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.
Kimi K3.1 Pro ahead: 8Qwen 3.8 Max 0902 ahead: 0level: 1too little data: 1of 10 areas
AreaKimi K3.1 ProQwen 3.8 Max 09020 to 100, higher is betterResult
Areas in the overall index
CodingKimi K3.1 Pro aheadKimi K3.1 Pro: 85Qwen 3.8 Max 0902: 51
ReasoningKimi K3.1 Pro aheadKimi K3.1 Pro: 80Qwen 3.8 Max 0902: 50
MathematicsKimi K3.1 Pro aheadKimi K3.1 Pro: 81Qwen 3.8 Max 0902: 42
KnowledgeKimi K3.1 Pro aheadKimi K3.1 Pro: 85Qwen 3.8 Max 0902: 39
AgentsKimi K3.1 Pro aheadKimi K3.1 Pro: 80Qwen 3.8 Max 0902: 46
GeneralKimi K3.1 Pro aheadKimi K3.1 Pro: 74Qwen 3.8 Max 0902: 54
MultimodalKimi K3.1 Pro aheadKimi K3.1 Pro: 75Qwen 3.8 Max 0902: 56
Specialist fields
FinanceKimi K3.1 Pro aheadKimi K3.1 Pro: 62Qwen 3.8 Max 0902: 45
LegallevelKimi K3.1 Pro: 68Qwen 3.8 Max 0902: 76
Healthonly Qwen 3.8 Max 0902 has a scoreKimi K3.1 Pro: not enough dataQwen 3.8 Max 0902: 31
Show 3 more areas that do not count toward the overall index
AreaKimi K3.1 ProQwen 3.8 Max 09020 to 100, higher is betterResult
Cybersecurityonly Qwen 3.8 Max 0902 has a scoreKimi K3.1 Pro: not enough dataQwen 3.8 Max 0902: 4
Productivityonly Qwen 3.8 Max 0902 has a scoreKimi K3.1 Pro: not enough dataQwen 3.8 Max 0902: 62
Educationonly Qwen 3.8 Max 0902 has a scoreKimi K3.1 Pro: 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.
Kimi K3.1 Pro
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 | Kimi K3.1 Pro | Qwen 3.8 Max 0902 |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 80 | 50 |
| Rank | Rank 10 to 13 of 95 | Rank 23 to 31 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $2 | $1.65 |
| Outputwhat the model writes | $10 | $4.951 |
| Speed | ||
| Tokens per second | 36 | 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 23, 2026 | Sep 2, 2026 |
| Availability | Active | API-only |
| Open weights | n/a | no |
- Kimi K3.1 Pro, API price listed by Artificial Analysis: $2 input, $10 output, and $0.20 cached input per 1 million tokens. Kimi's official API publishes CNY rates separately. Source
- Kimi K3.1 Pro, Official API pricing: K3.1 Pro: CNY 13 input, CNY 68 output, CNY 13 cache write, and CNY 1.30 cache hit per million tokens. Source
- Kimi K3.1 Pro, Highspeed API pricing: CNY 26 input, CNY 136 output, CNY 26 cache write, and CNY 1.30 cache hit per million tokens. Source
- Kimi K3.1 Pro, International API pricing in USD: The international Kimi platform lists $2 input, $10 output, $2 cache write and $0.20 cache hit per million tokens. Highspeed costs $4/$20/$4/$0.20. Checked October 29, 2026. Separately documented CNY tariffs remain separate observations. 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: Kimi K3.1 ProB: Qwen 3.8 Max 0902
EMB v1.1Overall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 70%Qwen 3.8 Max 0902: 66%Vals AIAs of 10/26/2026
IOIOverall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 81.9%Qwen 3.8 Max 0902: 68.9%Vals AIAs of 10/24/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 37.5%Qwen 3.8 Max 0902: 47.6%Vals AIAs of 10/26/2026
MysteryMechanismOverall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 26.1%Qwen 3.8 Max 0902: 23.9%Vals AIAs of 10/24/2026
ProofBench v1.1Overall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 91%Qwen 3.8 Max 0902: 58%Vals AIAs of 10/24/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 24.9%Qwen 3.8 Max 0902: 32.1%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 63.6%Qwen 3.8 Max 0902: 34.3%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceOverall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 31.4%Qwen 3.8 Max 0902: 12.9%Vals AIAs of 10/25/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 84.9%Qwen 3.8 Max 0902: 64.7%Vals AIAs of 10/26/2026
EMB v1.1Comps · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 67.4%Qwen 3.8 Max 0902: 65.7%Vals AIAs of 10/26/2026
Show 53 more benchmarks
IOIIOI 2024 · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 100%Qwen 3.8 Max 0902: 78.2%Vals AIAs of 10/24/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 56.1%Qwen 3.8 Max 0902: 59.1%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 10%Qwen 3.8 Max 0902: 20%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 40%Qwen 3.8 Max 0902: 0%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceEarth Sciences · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 12.5%Qwen 3.8 Max 0902: 12.5%Vals AIAs of 10/25/2026
EMB v1.1Dataroom · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 87.6%Qwen 3.8 Max 0902: 84.3%Vals AIAs of 10/26/2026
IOIIOI 2025 · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 75.5%Qwen 3.8 Max 0902: 68.3%Vals AIAs of 10/24/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 81.9%Qwen 3.8 Max 0902: 90.5%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 58%Qwen 3.8 Max 0902: 62.6%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 58.3%Qwen 3.8 Max 0902: 50%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceEngineering Sciences · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 22.2%Qwen 3.8 Max 0902: 0%Vals AIAs of 10/25/2026
EMB v1.1DCF · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 64.4%Qwen 3.8 Max 0902: 54.2%Vals AIAs of 10/26/2026
IOIIOI 2026 · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 70.2%Qwen 3.8 Max 0902: 60.2%Vals AIAs of 10/24/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 27.9%Qwen 3.8 Max 0902: 46.5%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 36.7%Qwen 3.8 Max 0902: 49.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 81.8%Qwen 3.8 Max 0902: 48.5%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceLife Sciences · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 36.8%Qwen 3.8 Max 0902: 10.5%Vals AIAs of 10/25/2026
EMB v1.1LBO · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 55.2%Qwen 3.8 Max 0902: 50.4%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 66.3%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 identicalKimi K3.1 Pro: 64.8%Qwen 3.8 Max 0902: 71.4%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 55.6%Qwen 3.8 Max 0902: 14.8%Vals AIAs of 10/26/2026
Terminal-Bench-ScienceMathematical Sciences · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 23.5%Qwen 3.8 Max 0902: 11.8%Vals AIAs of 10/25/2026
EMB v1.1M&A · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 78.1%Qwen 3.8 Max 0902: 73%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 29.6%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 identicalKimi K3.1 Pro: 27.9%Qwen 3.8 Max 0902: 27.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 73.8%Qwen 3.8 Max 0902: 33.3%Vals AIAs of 10/26/2026
Terminal-Bench-SciencePhysical Sciences · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 47.1%Qwen 3.8 Max 0902: 23.5%Vals AIAs of 10/25/2026
EMB v1.1Misc · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 68.1%Qwen 3.8 Max 0902: 65%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 75.8%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 identicalKimi K3.1 Pro: 68.8%Qwen 3.8 Max 0902: 62.1%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Security · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 73.3%Qwen 3.8 Max 0902: 40%Vals AIAs of 10/26/2026
EMB v1.1Operating · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 69.3%Qwen 3.8 Max 0902: 69.4%Vals AIAs of 10/26/2026
Legal Research BenchConstitutional / Civil Rights · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 31.6%Qwen 3.8 Max 0902: 34.2%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 13.3%Qwen 3.8 Max 0902: 20%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Software · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 53.7%Qwen 3.8 Max 0902: 40.7%Vals AIAs of 10/26/2026
EMB v1.1Scratch · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 68.1%Qwen 3.8 Max 0902: 66.3%Vals AIAs of 10/26/2026
Legal Research BenchConstitutional / Civil Rights · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 74.5%Qwen 3.8 Max 0902: 85.2%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 61.9%Qwen 3.8 Max 0902: 64.9%Vals AIAs of 10/26/2026
EMB v1.1Template · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 71.3%Qwen 3.8 Max 0902: 65.3%Vals AIAs of 10/26/2026
Legal Research BenchCriminal · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 28.1%Qwen 3.8 Max 0902: 40.4%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 30%Qwen 3.8 Max 0902: 33.3%Vals AIAs of 10/26/2026
Legal Research BenchCriminal · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 69.7%Qwen 3.8 Max 0902: 84.9%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 72.9%Qwen 3.8 Max 0902: 75.6%Vals AIAs of 10/26/2026
Legal Research BenchFamily · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 13.6%Qwen 3.8 Max 0902: 18.2%Vals AIAs of 10/26/2026
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 30%Qwen 3.8 Max 0902: 43.3%Vals AIAs of 10/26/2026
Legal Research BenchFamily · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 63.6%Qwen 3.8 Max 0902: 75.4%Vals AIAs of 10/26/2026
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 53.8%Qwen 3.8 Max 0902: 60.8%Vals AIAs of 10/26/2026
Legal Research BenchHealth · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 73.3%Qwen 3.8 Max 0902: 73.3%Vals AIAs of 10/26/2026
Tax Agent BenchWeighted Pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 63.7%Qwen 3.8 Max 0902: 66%Vals AIAs of 10/26/2026
Legal Research BenchHealth · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 90.5%Qwen 3.8 Max 0902: 96.2%Vals AIAs of 10/26/2026
Legal Research BenchImmigration · All-pass · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 18.2%Qwen 3.8 Max 0902: 45.5%Vals AIAs of 10/26/2026
Legal Research BenchImmigration · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 32.7%Qwen 3.8 Max 0902: 79.4%Vals AIAs of 10/26/2026
Legal Research BenchOverall · Weighted partial credit · higher is betterTest setup not documented as identicalKimi K3.1 Pro: 71.4%Qwen 3.8 Max 0902: 86.1%Vals AIAs of 10/26/2026
Compare another matchup
More matchups
Related LLM comparisons
Compare Kimi K3.1 Pro and Qwen 3.8 Max 0902 with other leading models.