Effort not specified
KimiReleased Oct 23, 2026
Kimi K3.1 Pro
Model brief
Research statusLimited evidence · Checked
We have not found enough reliable, model-specific information to publish a brief yet.
Measured performance
All leaderboards ↗Benchmark results
Effort not specified
GDPval-AA ↗2.1
1,845.72Effort not specified
AutomationBench-AA ↗AA Index 4.3.2 collection
73.3%Effort not specified
Effort not specified · Harness unreported
SciCode ↗AA Index 4.3.2 collection
60.76%AA · Under reviewEffort not specified
Humanity’s Last Exam ↗AA Index 4.3.2 collection
52.46%Effort not specified
GDP.pdf ↗AA Index 4.3.2 collection
31.4%Effort not specified
CritPt ↗AA Index 4.3.2 collection
24.57%AA · Under reviewEffort not specified
AA-Omniscience ↗AA Index 4.3.2 collection
29.52Effort not specified
AA-LCR ↗1.1
86.33%Effort not specified
Provider measurements
1 configurationSpeed
≈10K input tokens1 requestmedian / 72h
Artificial Analysis · first-party providers · serving endpoint not reported
Kimi
Kimi K3.1 Pro
Reasoning Not reported
- Output rate
- 84.1655 tok/s
- Time to first chunk
- 3.08462 s
Last checked Source ↗
Methodology 2.2.0 & measurement details
First chunk includes request processing and network time, and may include reasoning.
- Prompt
- long · ≈10,000 input tokens
- Parallel requests
- 1
- Minimum answer
- 1,500 tokens
- Aggregation
- median over 72 hours
- Token counting
- o200k_base
- Benchmark client
- Google Cloud us-central1-a
- Serving endpoint
- Not reported
- Serving region
- Not reported
- Sample size
- Not reported
- Window end
- Not reported
Access & cost
0 quotesPrices across providers
No listed provider price
Model specifications
- Developer
- Kimi
- Modality
- Language
- Context
- 1,000,000 tokens
- Maximum output
- Not reported
- Weights
- Closed weights
- Released
- Oct 23, 2026
- First discovered
- Oct 23, 2026
Exact identities
- artificial-analysis
665c67ca-09eb-48f0-a7a3-0096e1d5de51
Sources
Updated Oct 23, 2026