LIVE INTELLIGENCE · part of the Xentir AI Index

Kimi K2.7 Code vs Qwen 3.6 Max (Preview)

Kimi K2.7 Code OPEN WEIGHTS · Moonshot, released 2026-06-12
Qwen 3.6 Max (Preview) · Alibaba, released 2026-04-20

“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-07-26 · Methodology · Data Sources

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — Kimi K2.7 Code leads on 4, Qwen 3.6 Max (Preview) leads on 1.

Benchmark	Kimi K2.7 Code	Qwen 3.6 Max (Preview)	Leads
Epoch Capabilities Index (ECI)	149.7	149.7	Kimi K2.7 Code
SWE-bench Verified	Not measured	0.767	Not measured on both
GPQA Diamond	0.895	0.891	Kimi K2.7 Code
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.964	0.911	Kimi K2.7 Code
FrontierMath	Not measured	0.231	Not measured on both
FrontierMath Tier 4	Not measured	0.042	Not measured on both
SimpleQA Verified	0.392	0.569	Qwen 3.6 Max (Preview)
Chess Puzzles	0.210	0.170	Kimi K2.7 Code

Benchmark results measure specific tasks and should not be treated as a universal measure of model quality. A model with no row here for a benchmark has not been measured on it — that is left blank, never estimated.

Full profiles

Kimi K2.7 Code → · Qwen 3.6 Max (Preview) → · the full AI Model Rankings table