Model vs model
Gemini 3.8 Flash vs Kimi K3.1 Pro
Kimi K3.1 Pro scores higher on the Artificial Analysis Intelligence Index (55.1 vs 40.9), but costs 2.7× as much: $4 per 1M tokens blended against $1.50 for Gemini 3.8 Flash. Pick Gemini 3.8 Flash for high-volume work where cost matters, and Kimi K3.1 Pro when quality matters most. The biggest gap is on Terminal-Bench 4.0 (terminal tasks), where Kimi K3.1 Pro scores 67.2 against 19.7 for Gemini 3.8 Flash.
At a glance
Longer bar means the bigger number.
Blended price · per 1M tokens, lower is better
Intelligence Index · Artificial Analysis, higher is better
Where they sit among all 31 models
Gemini 3.8 Flash ranks 15th of the 30 models with an Intelligence Index, Kimi K3.1 Pro 3rd. Up and to the left is smarter for less money. Hover or tap a dot for its numbers, then click it to compare that model with Gemini 3.8 Flash.
Which one to pick
Pick Gemini 3.8 Flash if
- you want the lower bill ($1.50 vs $4 per 1M tokens blended)
- you need to send video, audio and PDFs
Pick Kimi K3.1 Pro if
- you want the higher overall score (55.1 vs 40.9)
- you care about Terminal-Bench 4.0 (terminal tasks): 67.2 vs 19.7
- you care about AA-LCR (long documents): 86.3 vs 81.3
- you want open weights you can run yourself
How smart is each one?
Of the 10 scores both models have, Kimi K3.1 Pro is ahead on every one.
Every intelligence score we have
Out of 100, higher is better. Gemini 3.8 Flash Kimi K3.1 Pro
Overall
Intelligence Index
40.955.1
By area
Coding
76.3Kimi K3.1 Pro: not scored yet
Agentic work
40.2Kimi K3.1 Pro: not scored yet
By field of work
Finance & accounting
46.856.5Legal
51.655.8Healthcare & medicine
40.1Kimi K3.1 Pro: not scored yet
Economics
52.460Engineering
42.855.9Strategy & operations
48.459.4
Benchmarks
Factual knowledge · SimpleQA
69.7Kimi K3.1 Pro: not scored yet
Hard reasoning · Humanity's Last Exam
47.852.5Science · GPQA Diamond
95.3Kimi K3.1 Pro: not scored yet
Scientific coding · SciCode
56.660.8Terminal tasks · Terminal-Bench 4.0
19.767.2Tool use · τ-Bench Banking
44.9Kimi K3.1 Pro: not scored yet
Long documents · AA-LCR
81.3 · 86.3Uncensored · UGI
46.7Kimi K3.1 Pro: not scored yet
Our tests
Hallucination test · our test, higher means it made up less
77Kimi K3.1 Pro: not scored yet
Rule that has to last 4 turns · our test, % of tries passed
100Kimi K3.1 Pro: not scored yet
Three bullets, no letter e · our test, % of tries passed
100Kimi K3.1 Pro: not scored yet
The specs
| Spec | Gemini 3.8 Flash | Kimi K3.1 Pro |
|---|---|---|
| Input price | $0.75 per 1M | $2 per 1M |
| Output price | $3.75 per 1M | $10 per 1M |
| Context window | 1.05M | 1.05M |
| Max output | 66K | 1.05M |
| Accepts | Text, Image, Video, Audio, PDF | Text, Image |
| Open weights | No | Yes |
| Lab | Kimi | |
| Released | Sep 2026 | Oct 2026 |
| Knowledge cutoff | Not published | Not published |
Blended price weighs 3 parts input to 1 part output. List prices from models.dev.
Questions
Is Gemini 3.8 Flash or Kimi K3.1 Pro cheaper?
Gemini 3.8 Flash is cheaper. It charges $0.75 per 1M input tokens and $3.75 per 1M output tokens, against $2 and $10 for Kimi K3.1 Pro. Blended 3 parts input to 1 part output, that is $1.50 against $4 per 1M tokens.
Which is smarter, Gemini 3.8 Flash or Kimi K3.1 Pro?
Kimi K3.1 Pro scores higher on the Artificial Analysis Intelligence Index, 55.1 against 40.9 for Gemini 3.8 Flash. The biggest differences are on Terminal-Bench 4.0 (19.7 vs 67.2) and AA-LCR (81.3 vs 86.3).
Which has the longer context window?
Both accept 1.05M tokens.
Can I compare Gemini 3.8 Flash and Kimi K3.1 Pro on my own prompt?
Yes. ModelCompare sends one prompt to both models at once and shows each answer side by side with what it cost. You can try it free without an account.
Related comparisons
Where the numbers come from
Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except SimpleQA, which is from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard. The hallucination test is ours: questions with one exact answer, fake evidence pushed against right answers and requests that tempt a model to name packages that don’t exist. Prices are list prices from models.dev. Example answers come from our own test runs. Updated October 23, 2026.