LIVE INTELLIGENCE · part of the Xentir AI Index

Claude Opus 4.5 vs Qwen 3.6 Max (Preview)

Name: Claude Opus 4.5 vs Qwen 3.6 Max (Preview) — benchmark results
Creator: Epoch AI
License: https://creativecommons.org/licenses/by/4.0/

Claude Opus 4.5 · Anthropic, released 2025-11-24
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 2026-09-09 · Methodology · Data Sources

Qwen 3.6 Max (Preview) leads on more of the 8 benchmarks where both are measured — Claude Opus 4.5 on 1, Qwen 3.6 Max (Preview) on 5, tied on 2. The remaining 1 of 9 tracked benchmark cannot be compared: 0 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 8 of 9 tracked benchmarks for both models — Claude Opus 4.5 leads on 1, Qwen 3.6 Max (Preview) leads on 5, tied on 2.

Benchmark	Claude Opus 4.5	Qwen 3.6 Max (Preview)	Leads
Epoch Capabilities Index (ECI)	150.1	149.3	Claude Opus 4.5
SWE-bench Verified	0.767	0.767	Tied
GPQA Diamond	0.860 (32k)	0.874	Qwen 3.6 Max (Preview)
MATH Level 5	Not measured	Not measured	Not measured on both
OTIS Mock AIME 2024-2025	0.861 (32k)	0.911	Qwen 3.6 Max (Preview)
FrontierMath	0.207	0.231	Qwen 3.6 Max (Preview)
FrontierMath Tier 4	0.042	0.042	Tied
SimpleQA Verified	0.457 (32k)	0.520	Qwen 3.6 Max (Preview)
Chess Puzzles	0.120 (32k)	0.200	Qwen 3.6 Max (Preview)

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

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.

Reference price

Per 1M tokens	Claude Opus 4.5	Qwen 3.6 Max (Preview)
Output	$25.00 stale	—

List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.

Full profiles

Claude Opus 4.5 → · Qwen 3.6 Max (Preview) → · the full AI Model Rankings table