#3
Kimi K3
Moonshot AI · Proprietary · Reasoning · 1.05M context
83/ 100 composite
Released 2026-07-16
Benchmark Scores by Category
Coding
64.4
Knowledge
84.8
Agentic
94.7
Multimodal
89.6
Scores based on weighted benchmarks: SWE-bench, LiveCodeBench (Coding); HLE, MMLU-Pro (Knowledge); ARC-AGI-2, LongBench v2 (Reasoning); Terminal-Bench, BrowseComp (Agentic); FrontierMath, AIME (Math).
API Pricing
Input
$3
per 1M tokens
Output
$15
per 1M tokens
Value Score
5.3
score per $1 output
Estimate Your Costs
Use our cost calculators to estimate monthly spend based on your specific workload: