LIVE INTELLIGENCE · part of the Xentir AI Index

Claude Sonnet 4.5 vs Qwen 3.5 Plus (hosted 397B-A17B)

Claude Sonnet 4.5 · Anthropic, released 2025-09-29
Qwen 3.5 Plus (hosted 397B-A17B) · Alibaba, released 2026-02-16

“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 — Claude Sonnet 4.5 leads on 1, Qwen 3.5 Plus (hosted 397B-A17B) leads on 6.

Benchmark	Claude Sonnet 4.5	Qwen 3.5 Plus (hosted 397B-A17B)	Leads
Epoch Capabilities Index (ECI)	146.8	147.0	Qwen 3.5 Plus (hosted 397B-A17B)
SWE-bench Verified	0.713	Not measured	Not measured on both
GPQA Diamond	0.823 (59k)	0.842	Qwen 3.5 Plus (hosted 397B-A17B)
MATH Level 5	0.977 (32k)	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.778 (59k)	0.850	Qwen 3.5 Plus (hosted 397B-A17B)
FrontierMath	0.152 (32k)	0.210	Qwen 3.5 Plus (hosted 397B-A17B)
FrontierMath Tier 4	0.042 (32k)	0.021	Claude Sonnet 4.5
SimpleQA Verified	0.236 (59k)	0.260	Qwen 3.5 Plus (hosted 397B-A17B)
Chess Puzzles	0.120 (32k)	0.170	Qwen 3.5 Plus (hosted 397B-A17B)

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

Claude Sonnet 4.5 → · Qwen 3.5 Plus (hosted 397B-A17B) → · the full AI Model Rankings table