AlibabaAuto-detected

Qwen2.5-Max

Not yet ranked: too few independent results so far.

Blended price: –
Output speed: –
First answer: –
Context: 32k

How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.

Reasoning55
Coding53
Human preference55
Composite39

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Default” means the publisher did not say which setting was used.

Effort	Index	Rank	Speed	First answer	Chat reply cost	Categories
maxbest	–	–	–	–	–	Coding 53 · Composite 39 · Human preference 55 · Reasoning 55
default	–	–	–	–	–

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmark	max	default	Source
LMArena Hard Prompts	1385#162	–	LMArena
GPQA Diamond (AA)not in index	58.7%#366	–	Artificial Analysis
Humanity's Last Exam (AA)not in index	3.8%#477	–	Artificial Analysis

Coding

Benchmark	max	default	Source
LMArena Coding	1402#171	–	LMArena
SWE-bench Verified (any scaffold)not in index	–	40.2%#51	SWE-bench

Human preference

Benchmark	max	default	Source
LMArena Text	1374#157	–	LMArena

Composite

Benchmark	max	default	Source
Epoch Capabilities Indexnot in index	132.5#125	–	Epoch AI Benchmarking Hub
AA Intelligence Index	8.0#370	–	Artificial Analysis