LIVE INTELLIGENCE · part of the Xentir AI Index

Qwen 3.5 Flash (hosted 35B-A3B) vs Qwen3-Max

Name: Qwen 3.5 Flash (hosted 35B-A3B) vs Qwen3-Max — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Qwen 3.5 Flash (hosted 35B-A3B) · Alibaba, released 2026-02-25
Qwen3-Max · Alibaba, released 2025-09-24

“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 2026-09-10 · Methodology · Data Sources

Qwen 3.5 Flash (hosted 35B-A3B) leads on more of the 5 benchmarks where both are measured — Qwen 3.5 Flash (hosted 35B-A3B) on 4, Qwen3-Max on 1. The remaining 4 of 9 tracked benchmarks cannot be compared: 3 have a result for only one of the two models, 1 for neither. Nothing on this page is estimated to fill those in.

Head-to-head

Measured on 5 of 9 tracked benchmarks for both models — Qwen 3.5 Flash (hosted 35B-A3B) leads on 4, Qwen3-Max leads on 1.

Benchmark	Qwen 3.5 Flash (hosted 35B-A3B)	Qwen3-Max	Leads
Epoch Capabilities Index (ECI)	144.0	142.4	Qwen 3.5 Flash (hosted 35B-A3B)
SWE-bench Verified	Not measured	Not measured	Not measured on both
GPQA Diamond	0.823	0.726	Qwen 3.5 Flash (hosted 35B-A3B)
MATH Level 5	Not measured	0.971	Comparison unavailable — Qwen 3.5 Flash (hosted 35B-A3B) has no published result
OTIS Mock AIME 2024-2025	0.844	0.733	Qwen 3.5 Flash (hosted 35B-A3B)
FrontierMath	0.062	Not measured	Comparison unavailable — Qwen3-Max has no published result
FrontierMath Tier 4	0.000	Not measured	Comparison unavailable — Qwen3-Max has no published result
SimpleQA Verified	0.203	0.487	Qwen3-Max
Chess Puzzles	0.210	0.040	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.

What remains uncertain

Qwen 3.5 Flash (hosted 35B-A3B) has no published result on MATH Level 5.
Qwen3-Max has no published result on FrontierMath, FrontierMath Tier 4.
1 tracked benchmark has no published result for either model.

A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.

Full profiles

Qwen 3.5 Flash (hosted 35B-A3B) → · Qwen3-Max → · the full AI Model Rankings table