GPT-5.4 minivs.Kimi K3.1 Pro
Which one is better?
Kimi K3.1 Pro is clearly ahead in the overall index, but costs 2.7 times (input) and 2.2 times (output) as much per token.
5
GPT-5.4 mini
Rank 54 to 60
80
Kimi K3.1 Pro
Rank 10 to 13
230
GPT-5.4 mini
fast
36
Kimi K3.1 Pro
slow
$1.69
GPT-5.4 mini
fairly expensive
$4
Kimi K3.1 Pro
fairly expensive
GPT-5.4 mini
- Subscription
No OpenAI subscription includes this model. Through other providers from ≈ €6.36 a month (ElevenLabs Starter, with limited credits). 36 plans in Germany.
- Via API
$0.75 input, $4.50 output per 1M tokens, unchanged since our price tracking began on Aug 14, 2026.
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.
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-5.4 mini ahead: 0Kimi K3.1 Pro ahead: 8level: 0too little data: 1of 9 areas
AreaGPT-5.4 miniKimi K3.1 Pro0 to 100, higher is betterResult
Areas in the overall index
CodingKimi K3.1 Pro aheadGPT-5.4 mini: 5Kimi K3.1 Pro: 85
ReasoningKimi K3.1 Pro aheadGPT-5.4 mini: 7Kimi K3.1 Pro: 80
Mathematicsonly Kimi K3.1 Pro has a scoreGPT-5.4 mini: not enough dataKimi K3.1 Pro: 81
KnowledgeKimi K3.1 Pro aheadGPT-5.4 mini: 4Kimi K3.1 Pro: 85
AgentsKimi K3.1 Pro aheadGPT-5.4 mini: 9Kimi K3.1 Pro: 80
GeneralKimi K3.1 Pro aheadGPT-5.4 mini: 11Kimi K3.1 Pro: 74
MultimodalKimi K3.1 Pro aheadGPT-5.4 mini: 6Kimi K3.1 Pro: 75
Specialist fields
FinanceKimi K3.1 Pro aheadGPT-5.4 mini: 5Kimi K3.1 Pro: 62
LegalKimi K3.1 Pro aheadGPT-5.4 mini: 3Kimi K3.1 Pro: 68
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-5.4 mini
Reasoning (requested): high
Current attempt
- Run date
- Oct 2, 2026
- API provider
- openrouter
- Requested API model
- openai/gpt-5.4-mini
- API model reported in response
- openai/gpt-5.4-mini
- Reasoning setting
- high
- Pinned endpoint
- OpenAI | openai/gpt-5.4-mini-20260317
- 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
- 13.5 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (2)
- Oct 1, 2026API request failedReasoning setting: high
- Sep 7, 2026API request failedReasoning setting: high
Kimi K3.1 Pro
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-5.4 mini | Kimi K3.1 Pro |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 5 | 80 |
| Rank | Rank 54 to 60 of 95 | Rank 10 to 13 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | $0.75 | $2 |
| Outputwhat the model writes | $4.50 | $10 |
| Speed | ||
| Tokens per second | 230 | 36 |
| Technical | ||
| Context windowhow much text the model reads at once | 400,000 tokens≈ 600 A4 pages | 1.05 M tokens≈ 1,570 A4 pages |
| Knowledge cutoff | Aug 31, 2025 | n/a |
| Released | Mar 17, 2026 | Oct 23, 2026 |
| Availability | Active | Active |
| Open weights | no | n/a |
- 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: GPT-5.4 miniB: Kimi K3.1 Pro
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 12.5%Kimi K3.1 Pro: 37.5%Vals AIAs of 10/26/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 8.8%Kimi K3.1 Pro: 24.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 2.5%Kimi K3.1 Pro: 63.6%Vals AIAs of 10/26/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 48%Kimi K3.1 Pro: 84.9%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 15.2%Kimi K3.1 Pro: 56.1%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-5.4 mini: 3.3%Kimi K3.1 Pro: 10%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Hardware · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Kimi K3.1 Pro: 40%Vals AIAs of 10/26/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 69.7%Kimi K3.1 Pro: 81.9%Vals AIAs of 10/26/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-5.4 mini: 32.2%Kimi K3.1 Pro: 58%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Media · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Kimi K3.1 Pro: 58.3%Vals AIAs of 10/26/2026
Show 31 more benchmarks
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 11.6%Kimi K3.1 Pro: 27.9%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-5.4 mini: 10%Kimi K3.1 Pro: 36.7%Vals AIAs of 10/26/2026
Terminal-Bench 4.0ML · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Kimi K3.1 Pro: 81.8%Vals AIAs of 10/26/2026
Legal Research BenchBusiness & Commercial · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 71.2%Kimi K3.1 Pro: 66.3%Vals AIAs of 10/26/2026
Tax Agent BenchCurrent & Temporal Analysis · higher is betterTest setup not documented as identicalGPT-5.4 mini: 38.6%Kimi K3.1 Pro: 64.8%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Operations · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Kimi K3.1 Pro: 55.6%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 14.8%Kimi K3.1 Pro: 29.6%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-5.4 mini: 7%Kimi K3.1 Pro: 27.9%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Science · higher is betterTest setup not documented as identicalGPT-5.4 mini: 2.4%Kimi K3.1 Pro: 73.8%Vals AIAs of 10/26/2026
Legal Research BenchCivil Litigation · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 67.3%Kimi K3.1 Pro: 75.8%Vals AIAs of 10/26/2026
Tax Agent BenchFact-Pattern Analysis · higher is betterTest setup not documented as identicalGPT-5.4 mini: 36.5%Kimi K3.1 Pro: 68.8%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Security · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Kimi K3.1 Pro: 73.3%Vals AIAs of 10/26/2026
Legal Research BenchConstitutional / Civil Rights · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 13.2%Kimi K3.1 Pro: 31.6%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalGPT-5.4 mini: 3.3%Kimi K3.1 Pro: 13.3%Vals AIAs of 10/26/2026
Terminal-Bench 4.0Software · higher is betterTest setup not documented as identicalGPT-5.4 mini: 7.4%Kimi K3.1 Pro: 53.7%Vals AIAs of 10/26/2026
Legal Research BenchConstitutional / Civil Rights · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 74.1%Kimi K3.1 Pro: 74.5%Vals AIAs of 10/26/2026
Tax Agent BenchForms & Filings · higher is betterTest setup not documented as identicalGPT-5.4 mini: 33.5%Kimi K3.1 Pro: 61.9%Vals AIAs of 10/26/2026
Legal Research BenchCriminal · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 5.3%Kimi K3.1 Pro: 28.1%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalGPT-5.4 mini: 20%Kimi K3.1 Pro: 30%Vals AIAs of 10/26/2026
Legal Research BenchCriminal · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 64.4%Kimi K3.1 Pro: 69.7%Vals AIAs of 10/26/2026
Tax Agent BenchNumbers & Calculations · higher is betterTest setup not documented as identicalGPT-5.4 mini: 52.3%Kimi K3.1 Pro: 72.9%Vals AIAs of 10/26/2026
Legal Research BenchFamily · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Kimi K3.1 Pro: 13.6%Vals AIAs of 10/26/2026
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalGPT-5.4 mini: 10%Kimi K3.1 Pro: 30%Vals AIAs of 10/26/2026
Legal Research BenchFamily · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 51.6%Kimi K3.1 Pro: 63.6%Vals AIAs of 10/26/2026
Tax Agent BenchRule & Source Lookup · higher is betterTest setup not documented as identicalGPT-5.4 mini: 26.5%Kimi K3.1 Pro: 53.8%Vals AIAs of 10/26/2026
Legal Research BenchHealth · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 16.7%Kimi K3.1 Pro: 73.3%Vals AIAs of 10/26/2026
Tax Agent BenchWeighted Pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 36.6%Kimi K3.1 Pro: 63.7%Vals AIAs of 10/26/2026
Legal Research BenchHealth · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 73.8%Kimi K3.1 Pro: 90.5%Vals AIAs of 10/26/2026
Legal Research BenchImmigration · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 18.2%Kimi K3.1 Pro: 18.2%Vals AIAs of 10/26/2026
Legal Research BenchImmigration · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 68.4%Kimi K3.1 Pro: 32.7%Vals AIAs of 10/26/2026
Legal Research BenchOverall · Weighted partial credit · higher is betterTest setup not documented as identicalGPT-5.4 mini: 67.3%Kimi K3.1 Pro: 71.4%Vals AIAs of 10/26/2026
Compare another matchup
More matchups
Related LLM comparisons
Compare GPT-5.4 mini and Kimi K3.1 Pro with other leading models.