Kimi K3.1 Pro · Intelligence Index v5.0 ↗
1 more reported result
55.09 index · Kimi K3.1 Pro · Intelligence Index v4.3.2 · Artificial Analysis ↗
Kimi / MODEL EVIDENCE
Kimi K3.1 Pro
66 benchmarks · 97 observations · 32 sources · released 2026-10-23
Scores at a glance
58 benchmarks · large dot: Kimi K3.1 Pro; small dots: closest models where reported
AA-Briefcase v1.1 ↗1677.79 Elo
Kimi K3.1 Pro · AA-Briefcase v1.1 · overall Elo ↗
1 more reported result
1678 Elo · Kimi K3.1 Pro (max) · AA-Briefcase v1.1 · AA-Briefcase v1.1 (Elo-score) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
AutomationBench-AA ↗73.30%
Kimi K3.1 Pro · AutomationBench-AA · guardrail-gated objective score ↗
1 more reported result
73.3% · Kimi K3.1 Pro (max) · AutomationBench-AA · Automation Bench-AA · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
GDP.pdf ↗31.40%
Kimi K3.1 Pro · GDP.pdf · all-pass ↗
2 more reported results
85.7% · Kimi K3.1 Pro (max) · GDP.pdf · GDP.pdf w/ python · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
34.6% · Kimi K3.1 Pro (max) · GDP.pdf · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
Terminal-Bench 4.0 ↗67.17%
Kimi K3.1 Pro · Terminal-Bench 4.0 · AA harness ↗
2 more reported results
63.64 % · Kimi K3.1 Pro (Mini-SWE-agent) · Terminal-Bench 4.0 · Score · Vals AI · Terminal-Bench 4.0 ↗
65.7% · Kimi K3.1 Pro (max) · Terminal-Bench 4.0 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
Kimi K3.1 Pro · Terminal-Bench-Science 0.1 · AA harness ↗
1 more reported result
38.1% · Kimi K3.1 Pro (max) · Terminal-Bench-Science 0.1 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
FrontierCode 2.0 ↗25.45%
Kimi K3.1 Pro · FrontierCode 2.0 · AA implementation ↗
Kimi K3.1 Pro · CritPt v2 · hard subset · AA implementation ↗
HLE-Diamond ↗37.30%
Kimi K3.1 Pro · HLE-Diamond · AA implementation ↗
1 more reported result
39.4% · Kimi K3.1 Pro (max) · HLE-Diamond · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
AA-Omniscience v1.1 ↗29.87 index
Kimi K3.1 Pro · AA-Omniscience v1.1 · error-penalized index ↗
1 more reported result
29.52 index · Kimi K3.1 Pro · AA-Omniscience · error-penalized score · Artificial Analysis ↗
Kimi K3.1 Pro · AA-Omniscience v1.1 · accuracy ↗
1 more reported result
51.02% · Kimi K3.1 Pro · AA-Omniscience · accuracy · Artificial Analysis ↗
Kimi K3.1 Pro · AA-Omniscience v1.1 · hallucination rate, lower is better ↗
1 more reported result
43.89% · Kimi K3.1 Pro · AA-Omniscience · hallucination rate, lower is better · Artificial Analysis ↗
GDPval-AA v2.1 ↗1845.72 Elo
Kimi K3.1 Pro · GDPval-AA v2.1 · Elo ↗
1 more reported result
1846 Elo · Kimi K3.1 Pro (max) · GDPval-AA v2.1 · GDPval-AA v2.1 (Elo-score) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
AA-3D ↗1110.16 Elo
Kimi K3.1 Pro · AA-3D · Elo ↗
AA-AnalystAgent ↗38.75%
Kimi K3.1 Pro · AA-AnalystAgent · strict score ↗
FrontierCode 1.1 ↗47.07%
Kimi K3.1 Pro · FrontierCode 1.1 · AA implementation ↗
AA-LCR v1.1 ↗86.33%
Kimi K3.1 Pro · AA-LCR v1.1 ↗
SciCode ↗60.76%
Kimi K3.1 Pro · SciCode · AA implementation ↗
Humanity’s Last Exam ↗52.46%
Kimi K3.1 Pro · Humanity’s Last Exam · AA implementation ↗
2 more reported results
70% · Kimi K3.1 Pro (max) · Humanity’s Last Exam · HLE-Full w/ tools · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
51.1% · Kimi K3.1 Pro (max) · Humanity’s Last Exam · HLE-Full · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
MMMU-Pro ↗83.87%
Kimi K3.1 Pro · MMMU-Pro · AA implementation ↗
2 more reported results
90% · Kimi K3.1 Pro (max) · MMMU-Pro · MMMU-Pro w/ python · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
84.1% · Kimi K3.1 Pro (max) · MMMU-Pro · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
CritPt v2 ↗68.00%
Kimi K3.1 Pro · CritPt v2 · code tools ↗
CritPt ↗24.57%
Kimi K3.1 Pro · CritPt · original ↗
AA-PersonalityBench ↗62.88 percentile
Kimi K3.1 Pro · AA-PersonalityBench · expressiveness ↗
7 more reported results
87.62 percentile · Kimi K3.1 Pro · AA-PersonalityBench · organization · Artificial Analysis ↗
23.28 percentile · Kimi K3.1 Pro · AA-PersonalityBench · informativeness · Artificial Analysis ↗
87.62 percentile · Kimi K3.1 Pro · AA-PersonalityBench · transparency · Artificial Analysis ↗
50.50 percentile · Kimi K3.1 Pro · AA-PersonalityBench · warmth · Artificial Analysis ↗
62.88 percentile · Kimi K3.1 Pro · AA-PersonalityBench · conviction · Artificial Analysis ↗
52.98 percentile · Kimi K3.1 Pro · AA-PersonalityBench · imagination · Artificial Analysis ↗
20.80 percentile · Kimi K3.1 Pro · AA-PersonalityBench · slop · Artificial Analysis ↗
Vals Index ↗62.52 %
Kimi K3.1 Pro · Vals Index · Accuracy ↗
Vals Finance Index ↗56.01 %
Kimi K3.1 Pro · Vals Finance Index · Accuracy ↗
Vals Legal Index ↗67.04 %
Kimi K3.1 Pro · Vals Legal Index · Accuracy ↗
Legal Research Bench ↗37.5 %
Kimi K3.1 Pro · Legal Research Bench · All-Pass ↗
HLAB-Vals-1.1 ↗11.67 %
Kimi K3.1 Pro · HLAB-Vals-1.1 · Task Pass Rate ↗
Vals Finance Agent v2.1 ↗61.49 %
Kimi K3.1 Pro · Finance Agent · Accuracy ↗
Kimi K3.1 Pro · Excel Modeling Benchmark · Accuracy ↗
Tax Agent Bench ↗24.87 %
Kimi K3.1 Pro · Tax Agent Bench · Accuracy ↗
Vibe Code Bench ↗84.89 %
Kimi K3.1 Pro (OpenHands) · Vibe Code Bench · original task set ↗
SWE-Marathon ↗51.7%
Kimi K3.1 Pro (max) · SWE-Marathon · SWE Marathon v1.1 · Kimi K3.1 Pro · complete release comparison ↗
BenchCAD ↗72.8%
Kimi K3.1 Pro (max) · BenchCAD · BenchCAD w/o tools · Kimi K3.1 Pro · complete release comparison ↗
1 more reported result
92.7% · Kimi K3.1 Pro (max) · BenchCAD · BenchCAD w/ tools · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
ProgramBench ↗31.5%
Kimi K3.1 Pro (max) · ProgramBench · Program Bench · Kimi K3.1 Pro · complete release comparison ↗
DeepSWE v1.1 ↗75.5%
Kimi K3.1 Pro (max) · DeepSWE v1.1 · Kimi K3.1 Pro · complete release comparison ↗
PostTrainBench ↗36.5%
Kimi K3.1 Pro (max) · PostTrainBench · PostTrain Bench v1.2 · Kimi K3.1 Pro · complete release comparison ↗
Kimi K3.1 Pro (max) · Kimi Code Bench 2.0 · Kimi Code Bench 2.0 (Internal) · Kimi K3.1 Pro · complete release comparison ↗
Kimi K3.1 Pro (max) · Kimi Code Bench 3.0 · Kimi Code Bench 3.0 Long-horizon (Internal) · Kimi K3.1 Pro · complete release comparison ↗
BrowseComp ↗92.1%
Kimi K3.1 Pro (max) · BrowseComp · Kimi K3.1 Pro · complete release comparison ↗
BioMysteryBench ↗80.6%
Kimi K3.1 Pro (max) · BioMysteryBench · Kimi K3.1 Pro · complete release comparison ↗
CharXiv ↗93.4%
Kimi K3.1 Pro (max) · CharXiv · CharXiv (RQ) w/ python · Kimi K3.1 Pro · complete release comparison ↗
1 more reported result
89% · Kimi K3.1 Pro (max) · CharXiv · CharXiv (RQ) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
Chartography ↗90.2%
Kimi K3.1 Pro (max) · Chartography · ChartoGraphy w/ python · Kimi K3.1 Pro · complete release comparison ↗
BabyVision ↗95.4%
Kimi K3.1 Pro (max) · BabyVision · BabyVision w/ python · Kimi K3.1 Pro · complete release comparison ↗
ZeroBench ↗63%
Kimi K3.1 Pro (max) · ZeroBench · ZeroBench_main w/ python (pass@5) · Kimi K3.1 Pro · complete release comparison ↗
2 more reported results
29.8% · Kimi K3.1 Pro (max) · ZeroBench · ZeroBench_main · avg@5 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
39% · Kimi K3.1 Pro (max) · ZeroBench · ZeroBench_main · pass@5 · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
Agents’ Last Exam ↗43.2%
Kimi K3.1 Pro (max) · Agents’ Last Exam · Agents' Last Exam (ALL) · Kimi K3.1 Pro · complete release comparison ↗
1 more reported result
44.2% · Kimi K3.1 Pro (max) · Agents’ Last Exam · Agents' Last Exam (CLI) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
Kimi K3.1 Pro (max) · APEX-Agents · original · Kimi K3.1 Pro · complete release comparison ↗
OfficeQA Pro ↗64.4%
Kimi K3.1 Pro (max) · OfficeQA Pro · OfficeQA Pro v2 ↗
1 more reported result
67.4% · Kimi K3.1 Pro (max) · OfficeQA Pro · OfficeQA Pro v1 · Introducing Kimi K3.1 Pro ↗
Kimi K3.1 Pro (max) · Vals Finance Agent v2 · Frontier Finance · Kimi K3.1 Pro · complete release comparison ↗
Kimi K3.1 Pro (max) · Harvey Legal Agent Benchmark · Kimi K3.1 Pro · complete release comparison ↗
HANDBOOK.md ↗44.6%
Kimi K3.1 Pro (max) · HANDBOOK.md · Kimi K3.1 Pro · complete release comparison ↗
OSWorld 2.1 ↗79.6%
Kimi K3.1 Pro (max) · OSWorld 2.1 · OSWorld V2.1 · Kimi K3.1 Pro · complete release comparison ↗
DECK-Arena ↗1456 Elo
Kimi K3.1 Pro (max) · DECK-Arena · DECK-Arena (Internal, Elo-score) · Kimi K3.1 Pro · complete release comparison ↗
Design Bench ↗957 Elo
Kimi K3.1 Pro (max) · Design Bench · Design Bench (Internal, Elo-score) · Kimi K3.1 Pro · complete release comparison ↗
Kimi K3.1 Pro (max) · Kimi Hallucination Benchmark · Kimi Hallu Bench Hard w/ tools (Internal, lower is better) · Kimi K3.1 Pro · complete release comparison ↗
1 more reported result
5.4% · Kimi K3.1 Pro (max) · Kimi Hallucination Benchmark · Kimi Hallu Bench w/o tools (Internal, lower is better) · Kimi K3.1 Pro · complete release comparison · Introducing Kimi K3.1 Pro ↗
GPQA Diamond ↗94.2%
Kimi K3.1 Pro (max) · GPQA Diamond · GPQA-Diamond · Kimi K3.1 Pro · complete release comparison ↗
ExploitBench ↗74.7%
Kimi K3.1 Pro (max) · ExploitBench · Kimi K3.1 Pro · complete release comparison ↗
ExploitGym ↗20.7%
Kimi K3.1 Pro (max) · ExploitGym · Kimi K3.1 Pro · complete release comparison ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Muse Wonder →Meta
18 of 30 shared benchmark comparisons
18 of 30 shared benchmark comparisons
GPT-6.1 Sol →OpenAI
29 of 30 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
POST-TRAINING / SOURCE DISCLOSURE
What the Kimi K3.1 Pro report says
K3.1 Pro starts from Kimi K3 and expands joint reinforcement learning across many downstream domains. The announcement ties the scale-up to long-context inference, sandbox infrastructure, rollout scheduling and environment checks.
- Kimi K3 starting checkpoint
- Joint reinforcement learning across downstream domains
- Scaled rollout and environment infrastructure
The announcement does not specify the complete loss, training mixture or per-stage compute. The systems note is background; it does not establish that K3.1 Pro uses DAPO.
Reports featuring this model
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- AA-3D: Interactive 3D Experience Benchmark | Artificial Analysis ↗
- AA-AnalystAgent Benchmark | Artificial Analysis ↗
- AA-Briefcase v1.1: Agentic Knowledge Work Benchmark | Artificial Analysis ↗
- AA-PersonalityBench: AI Personality & Communication Style Benchmark | Artificial Analysis ↗
- Artificial Analysis Intelligence Index v5.0 — Artificial Analysis ↗
- AA-LCR v1.1: Long Context Reasoning Benchmark | Artificial Analysis ↗
- AutomationBench-AA: Agentic SaaS Workflow Benchmark | Artificial Analysis ↗
- CritPt Benchmark | Artificial Analysis ↗
- CritPt v2 Benchmark | Artificial Analysis ↗
- CritPt v2 — Hard Subset — Artificial Analysis ↗
- FrontierCode 1.1 Benchmark | Artificial Analysis ↗
- FrontierCode 2.0 Benchmark — Artificial Analysis ↗
- GDP.pdf Benchmark | Artificial Analysis ↗
- GDPval-AA v2.1 Benchmark | Artificial Analysis ↗
- HLE-Diamond Benchmark — Artificial Analysis ↗
- Humanity's Last Exam Benchmark | Artificial Analysis ↗
- MMMU-Pro Benchmark | Artificial Analysis ↗
- AA-Omniscience v1.1: Knowledge and Hallucination Benchmark — Artificial Analysis ↗
- SciCode Benchmark | Artificial Analysis ↗
- Terminal-Bench-Science 0.1 Benchmark | Artificial Analysis ↗
- Terminal-Bench 4.0 Benchmark | Artificial Analysis ↗
- Introducing Kimi K3.1 Pro ↗
- Excel Modeling Benchmark — evaluation methodology and results ↗
- Finance Agent — evaluation methodology and results ↗
- Vals Finance Index — evaluation methodology and results ↗
- HLAB-Vals-1.1 — evaluation methodology and results ↗
- Vals Legal Index — evaluation methodology and results ↗
- Legal Research Bench — evaluation methodology and results ↗
- Tax Agent Bench — evaluation methodology and results ↗
- Terminal-Bench 4.0 — evaluation methodology and results ↗
- Vals Index — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
Kimi K3.1 Pro · Kimi K3.1 Pro (Mini-SWE-agent) · Kimi K3.1 Pro (OpenHands) · Kimi K3.1 Pro (max)