Kimi K3 Max

Released2026-07-16
Price per 1M$3.00 in · $15.00 out
Overall score59.9 · rank 96
Context window1,048,576 tokens
ProviderMoonshot AI
WeightsOpen weights
ConfigurationMax

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 59.9 96 34
Overall: Coding 59.8 98 26
Overall: Reasoning 60.4 97 15
Overall: Agentic work 59.5 108 24
Overall: Frontend 60.3 67 10
Coding 59.6 95 8
Agents 58.9 95 8
Reasoning 61.6 95 8
Math 60.1 51 4
Knowledge 58.3 50 3
Frontend 60.6 32 2
General 60.8 51 1
Value vs price+4.5139

Evidence

Coding 59.6 ±1.5

BenchmarkResultSourceDate
FrontierSWE 25.9% Epoch AI 2026-11-11
DeepSWE 68.5% Epoch AI 2026-11-11
Code Migration v1.1 28.6% Vals AI 2026-11-09
MirrorCode 54.4% Epoch AI 2026-09-03
IOI 48.9% Vals AI 2026-10-29
SWE-bench Multimodal 44.2% Vals AI 2026-11-09
SciCode 59.5% Epoch AI 2026-11-11
LiveCodeBench (Vals run) 87.2% Vals AI 2026-09-01

Agents 58.9 ±1.5

BenchmarkResultSourceDate
Terminal-Bench 4.0 (Vals run) 17.2% Vals AI 2026-11-09
Terminal-Bench-Science 1.4% Vals AI 2026-11-09
tau2-bench Banking Knowledge 37.1% tau2-bench 2026-07-24
EMB v1.1 (Excel financial modeling) 71.3% Vals AI 2026-11-09
Tax Agent Bench 33.4% Vals AI 2026-11-09
Finance Agent v2.1 60.0% Vals AI 2026-11-09
HLAB-Vals 1.1 (legal agent) 12.9% Vals AI 2026-11-09
CyberBench v1.1 75.2% Vals AI 2026-11-05

Reasoning 61.6 ±1.7

BenchmarkResultSourceDate
ARC-AGI-2 60.4% Epoch AI 2026-11-11
ARC-AGI-2 (ARC Prize verified) 60.4% ARC Prize 2026-11-11
GPQA Diamond 93.1% Epoch AI 2026-07-16
CritPt 23.4% Epoch AI 2026-11-11
ARC-AGI-1 (ARC Prize verified) 94.5% ARC Prize 2026-11-11
ARC-AGI-1 94.5% Epoch AI 2026-11-11
BioMysteryBench 72.6% Vals AI 2026-11-09
Chess Puzzles 36.0% Epoch AI 2026-10-13
SimpleBench 60.7% SimpleBench 2026-07-17
SimpleBench 60.7% Epoch AI 2026-11-11
Mystery Game Puzzles 26.0% Epoch AI 2026-07-29

Math 60.1 ±1.2

BenchmarkResultSourceDate
FrontierMath Tiers 1-3 72.2% Epoch AI 2026-07-17
FrontierMath Tier 4 39.0% Epoch AI 2026-07-17
ProofBench v1.1 87.0% Vals AI 2026-11-09
OTIS Mock AIME 2024-2025 97.2% Epoch AI 2026-07-16

Knowledge 58.3 ±3.6

BenchmarkResultSourceDate
SimpleQA Verified 50.6% Epoch AI 2026-08-27
MMLU-Pro (Vals run) 88.0% Vals AI 2026-09-01
Legal Research Bench 46.2% Vals AI 2026-11-09

Frontend 60.6 ±0.7

BenchmarkResultSourceDate
Vibe Code Bench v1.1 85.0% Vals AI 2026-11-09
LMArena WebDev 1,657 LMArena 2026-11-09

General 60.8 ±4.1

BenchmarkResultSourceDate
LMArena Text 1,487 LMArena 2026-11-09

Names matched to this model

kimi-k3-max

Compare Kimi K3 Max with other models