Gemini 4 Carbonvs.Kimi K3
Which one is better?
Gemini 4 Carbon is clearly ahead in the overall index.
Gemini 4 Carbon
Rank 1 to 5
Kimi K3
Rank 18 to 24
Gemini 4 Carbon
fairly fast
Kimi K3
slow
Gemini 4 Carbon
Kimi K3
expensive
Gemini 4 Carbon
- Subscription
Subscriptions in Germany: n/a
- Via API
n/a (no API price known).
Kimi K3
- Subscription
At Moonshot AI from ≈ €20.14 a month (Kimi Plus, with limited credits). Through other providers from ≈ €1.06 a month (Command Code Go, with limited credits). 45 plans in Germany.
- Via API
$3 input, $15 output per 1M tokens, unchanged since our price tracking began on Aug 14, 2026.
- Note
- There is a successor: Kimi K3.1 Pro (rank 10 to 13, $2 input, $10 output).
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.
Gemini 4 Carbon ahead: 6Kimi K3 ahead: 0level: 0too little data: 4of 10 areas
Show 3 more areas that do not count toward the overall index
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.
Gemini 4 Carbon
Not tested yet
Kimi K3
Reasoning (requested): high
Current attempt
- Run date
- Oct 1, 2026
- API provider
- openrouter
- Requested API model
- moonshotai/kimi-k3
- API model reported in response
- moonshotai/kimi-k3
- Reasoning setting
- high
- Pinned endpoint
- Moonshot AI | moonshotai/kimi-k3-20260715
- 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
- 173.4 s
Visually reviewed. This individual test does not establish overall model quality.
Earlier attempts (1)
- 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 | Gemini 4 Carbon | Kimi K3 |
|---|---|---|
| Intelligence | ||
| Overall index0 to 100, higher is better | 96 | 59 |
| Rank | Rank 1 to 5 of 95 | Rank 18 to 24 of 95 |
| Price per 1M tokens | ||
| Inputwhat you send | n/a | $3 |
| Outputwhat the model writes | n/a | $15 |
| Speed | ||
| Tokens per second | 100 | 55 |
| Technical | ||
| Context windowhow much text the model reads at once | 1 M tokens≈ 1,500 A4 pages | 1.05 M tokens≈ 1,570 A4 pages |
| Knowledge cutoff | n/a | n/a |
| Released | n/a | Jul 16, 2026 |
| Availability | Limited access | Active |
| Open weights | no | yes |
- Gemini 4 Carbon, Announced introductory pricing: $2 input and $10 output per 1M tokens. Cached input receives a 95% discount, giving $0.10 per 1M tokens. This announcement does not establish an already available public API. Source
- Gemini 4 Carbon, Announced pricing after the introductory period: Afterward, $4 input and $20 output per 1M tokens. Google has not specified when the introductory period ends. Source
- Gemini 4 Carbon, Artificial Analysis pricing assumptions: Artificial Analysis calculates test costs using $4 input, $20 output, and $0.20 cached input per 1M tokens. These are the evaluator’s pricing assumptions, not confirmation of a publicly available API tariff. 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: Gemini 4 CarbonB: Kimi K3