KimiReleased Oct 23, 2026
NewProprietary
Kimi K3.1 Pro
Strongest in Knowledge Work (#5 of 174) and Academic Reasoning (#8 of 201); weakest in Mathematical Reasoning (#15 of 174). Abstract Reasoning and Computer Use are estimated, because no results are published yet.
Composite IQ ?
131
Effective cost
Not priced
No standard API rate
Speed
51tok/s
52s typical response
Context
1Mtokens
1,048,576 tokens in
Evidence
5of 7 dims
12 of 39 benchmarks
IQ profile
Seven dimensions, averaged equally into Composite IQ
MeasuredEstimated95% range
#1 in dimensionTop-10 median
IQ dimensions
Ranks are among models scored in each dimension. Ranges are model-based estimates, not calibrated confidence intervals.
DimensionIQPosition · 70–160RankEvidencevs Top 10
Kimi K3.1 Pro95% range (model-based, uncalibrated)Top-10 median#1 in dimension100 = average human
Benchmark results
12 of 39 Composite IQ benchmarks have a published result for Kimi K3.1 Pro. Benchmarks without a result stay listed so gaps are visible.
Abstract Reasoning IQ 110 · estimatedNo published results0/5
No published results yet for Abstract Reasoning. The 110 shown is estimated from Kimi K3.1 Pro's other dimensions and will be replaced as results come in. How estimates work
ARC-AGI-3ARC-AGI-2ARC-AGI-1Chess PuzzlesMystery Game Puzzles
Mathematical Reasoning IQ 138 · measuredBest: #12 of 63 on MathArena1/5
BenchmarkScorePercentileRankLeader · source
MathArena
Full source leaderboard reconciliation · Oct 26
59.3%
#12 / 63
Leader gpt-6.1-sol · 84.0%
Full source leaderboard reconciliation · Oct 26
Full source leaderboard reconciliation · Oct 26
Not yet reported
FrontierMath Tier 4FrontierMath Tier 1-3ProofBench 1.1AIME
Academic Reasoning IQ 135 · measuredBest: #8 of 166 on SciCode4/6
BenchmarkScorePercentileRankLeader · source
SciCode
Artificial Analysis v4.3.2 · Oct 26
60.8%
#8 / 166
Leader opus-5.5 · 66.9%
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
Humanity's Last Exam
Artificial Analysis v4.3.2 · Oct 26
52.5%
#10 / 166
Leader opus-5.5 · 61.4%
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
CritPt
Artificial Analysis v4.3.2 · Oct 26
24.6%
#17 / 158
Leader Muse Wonder Full · 32.9%
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
MMMU-Pro
Artificial Analysis v4.3.2 · Oct 26
83.9%
#11 / 88
Leader fable-5.1 · 90.6%
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
Not yet reported
GPQA DiamondMMLU-Pro
Programmatic Reasoning IQ 143 · measuredBest: #1 of 103 on Terminal-Bench 4.01/6
BenchmarkScorePercentileRankLeader · source
Terminal-Bench 4.0
Artificial Analysis v4.3.2 · Oct 26
67.2%
#1 / 103
Leader on this benchmark
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
Not yet reported
LiveCodeBenchIOI V2ProgramBenchSWE-rebenchMirrorCode
Computer Use IQ 129 · estimatedNo published results0/5
No published results yet for Computer Use. The 129 shown is estimated from Kimi K3.1 Pro's other dimensions and will be replaced as results come in. How estimates work
BrowseCompOSWorld-VerifiedMCP AtlasArena.ai Agent ArenaAgents' Last Exam
Reliability IQ 128 · measuredBest: #2 of 153 on AA Long Context Reasoning v1.12/6
BenchmarkScorePercentileRankLeader · source
AA Long Context Reasoning v1.1
Artificial Analysis v4.3.2 · Oct 26
86.3%
#2 / 153
Leader kimi-k3 · 88.7%
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
AA Omniscience
Artificial Analysis v4.3.2 · Oct 26
29.5
#14 / 157
Leader opus-5.5 · 46.4
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
Not yet reported
SimpleQA VerifiedBullshitBench v2IFBenchFACTS Grounding
Knowledge Work IQ 133 · measuredBest: #2 of 105 on AutomationBench-AA4/6
BenchmarkScorePercentileRankLeader · source
AutomationBench-AA
Artificial Analysis v4.3.2 · Oct 26
73.3%
#2 / 105
Leader Gemini 4 Argon · 77.5%
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
GDP.pdf
Artificial Analysis v4.3.2 · Oct 26
31.4%
#2 / 105
Leader Muse Wonder Full · 32.6%
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
AA-Briefcase v1.1 Elo
Artificial Analysis v4.3.2 · Oct 26
1,678
#4 / 110
Leader sonnet-5.5 · 1,816
Artificial Analysis v4.3.2 · Oct 26
Artificial Analysis v4.3.2 · Oct 26
AA-AnalystAgent
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 26
38.8%
#23 / 34
Leader gemini-3.7-flash · 60.0%
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 26
Full source leaderboard reconciliation vpass^5-2026-09-29 · Oct 26
Not yet reported
GDPval-AA v2.1EnterpriseOps-Gym-AA
Release & availability
Facts from the publisher's announcement and documentation.
- Released
- Developer
- Kimi
- Access
- Available through Kimi products and the Kimi API as kimi-k3.1-pro. Full model weights are planned for release by November 4, 2026; they are not yet available.
- Weights
- ProprietaryHosted access only
- Inputs
- textimage
- Context
- 1,048,576 tokens
- API price
- No per-token rateThe publisher lists standard Kimi API token prices in CNY: ¥13 per million input tokens and ¥68 per million output tokens. A verified standard USD price for the intended endpoint is not recorded.
What Kimi says
- Post-trained successor to Kimi K3 with a 1,048,576-token context window and native vision input.
- The publisher reports improvements in coding, 3D creation and financial research.
Limitations
- Publisher benchmark claims use specific agent harnesses and effort settings; independent results are not yet imported.
- Full weights and license terms are pending the planned release.
- The faster Highspeed service tier offers the same model quality at a different speed and price.
Publisher statements, not AI IQ measurements.
About this score
How much of Kimi K3.1 Pro's IQ is measured, and how the rest is estimated.
12/ 39benchmark results
5/ 7dimensions measured
2estimated
0/5Abstract
1/5Math
4/6Academic
1/6Coding
0/5Computer Use
2/6Reliability
4/6Knowledge Work
Bar height = share of benchmarks with resultsEstimatedNo score
Measured results are shown as published
Every score in the benchmark tables comes from its source unchanged. Composite IQ averages all seven dimensions equally.
Estimates fill the gaps
Abstract Reasoning and Computer Use have no published results yet, so their IQ is estimated from Kimi K3.1 Pro's other dimensions. Missing benchmarks can also draw on its predecessor, Kimi K3; a predecessor is an estimation input, not evidence that this model has the predecessor's measured results.
A missing result is not a zero
Benchmark versions and evaluation harnesses can differ between sources, so small gaps between models may not be meaningful.
Compare Kimi K3.1 Pro
Side-by-side pages for the models it is most often weighed against.
#1 overall
gpt-6.1-sol
IQ141 10 higherEffective cost$6.20
Predecessor
kimi-k3
IQ127 4 lowerEffective cost$19.88
Closest IQ
Muse Wonder
IQ130 1 lowerEffective cost$30.55
Most similar profile
Muse Wonder Full
IQ130 1 lower
#2 overall
opus-5.5
IQ141 10 higherEffective cost$35.16
#3 overall
Gemini 4 Argon
IQ140 9 higher
Kimi K3.1 ProComparison model
Frequently asked questions
Quick answers about Kimi K3.1 Pro, drawn from the same data as the rest of this page.
How AI IQ scores models →Get this data from the API →- What is the IQ of Kimi K3.1 Pro?
- Kimi K3.1 Pro has an estimated IQ of 131, which ranks #11 out of 174 public models on the AI IQ leaderboard. The score combines seven equally weighted reasoning dimensions using measured benchmark results and conservative estimates for missing coverage.
- What is Kimi K3.1 Pro best at?
- Among the dimensions with published benchmark results, Kimi K3.1 Pro ranks highest in Knowledge Work (IQ 133, #5 of 174) and Academic Reasoning (IQ 135, #8 of 201). Its lowest-ranked measured dimension is Mathematical Reasoning (IQ 138, #15 of 174).
- What is the EQ of Kimi K3.1 Pro?
- Kimi K3.1 Pro doesn't have an EQ score yet. EQ (emotional reasoning) is calculated from EQ-Bench 4 and AttuneBench, and neither has published a result for Kimi K3.1 Pro. AI IQ doesn't estimate EQ from other benchmarks, so the score appears once one of those results is published.
- Which benchmarks has Kimi K3.1 Pro been tested on?
- Kimi K3.1 Pro has published results on 12 of the 39 benchmarks behind AI IQ's Composite IQ, including Terminal-Bench 4.0, AA Long Context Reasoning v1.1, AutomationBench-AA, GDP.pdf and AA-Briefcase v1.1 Elo.
- How much does Kimi K3.1 Pro cost?
- AI IQ doesn't have a verified standard per-token API price for Kimi K3.1 Pro, so it can't calculate an effective cost. This is common for models offered only through subscriptions, restricted-access programs, or self-hosting.
- Is Kimi K3.1 Pro open source?
- No — Kimi K3.1 Pro is a proprietary model. Its weights are not publicly available, so it is used through hosted APIs and products.
- Who developed Kimi K3.1 Pro?
- Kimi K3.1 Pro was developed by Kimi, based in China.
- When was Kimi K3.1 Pro released?
- Kimi K3.1 Pro was publicly released on October 23, 2026.
- How large is the context window of Kimi K3.1 Pro?
- Kimi K3.1 Pro supports a context window of 1,048,576 tokens — the amount of text it can consider in a single request.
- How fast is Kimi K3.1 Pro?
- In independent measurements, Kimi K3.1 Pro generates about 51 tokens per second, with a typical response time of about 52 seconds.