LIVE INTELLIGENCE · part of the Xentir AI Index

Qwen 3.5 Flash (hosted 35B-A3B) vs Qwen 3.6 Flash (2026-04-16)

Qwen 3.5 Flash (hosted 35B-A3B) · Alibaba, released 2026-02-25
Qwen 3.6 Flash (2026-04-16) · Alibaba, released 2026-04-27

“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 7 of 9 tracked benchmarks for both models — Qwen 3.5 Flash (hosted 35B-A3B) leads on 1, Qwen 3.6 Flash (2026-04-16) leads on 5, tied on 1.

Benchmark	Qwen 3.5 Flash (hosted 35B-A3B)	Qwen 3.6 Flash (2026-04-16)	Leads
Epoch Capabilities Index (ECI)	144.1	144.2	Qwen 3.6 Flash (2026-04-16)
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.838	0.844	Qwen 3.6 Flash (2026-04-16)
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.856	0.861	Qwen 3.6 Flash (2026-04-16)
FrontierMath	0.062	0.103	Qwen 3.6 Flash (2026-04-16)
FrontierMath Tier 4	0.000	0.000	Tied
SimpleQA Verified	0.198	0.212	Qwen 3.6 Flash (2026-04-16)
Chess Puzzles	0.200	0.172	Qwen 3.5 Flash (hosted 35B-A3B)

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

Qwen 3.5 Flash (hosted 35B-A3B) → · Qwen 3.6 Flash (2026-04-16) → · the full AI Model Rankings table