Back

Alibaba

Qwen3 32B

ReasoningOpen weights
Intelligence
7.2
Rank 558 of 744 measured models
Coding
15.3
Rank 246 of 298 measured models
Output speed
27.2 t/s
Rank 393 of 403 measured models
Price/1M
$0.315
Rank 213 of 659 measured models
Context window
33K
Rank 1012 of 1199 measured models

Qwen3 32B (Reasoning) scores 7.2 on the Artificial Analysis Intelligence Index, ranking 558th of 744 measured models. The closest models on this index are Claude 3.5 Sonnet (June '24) (7.2), GPT-4o (ChatGPT) (7.2), and LFM2.5-8B-A1B (7.2). At $0.315 per million tokens (3:1 input/output blended price), it is cheaper than Claude 3.5 Sonnet (June '24) ($6).

Artificial Analysis Indices
Reasoning
Intelligence7.2
Rank 558 of 744 measured models
Coding15.3
Rank 246 of 298 measured models
Math73.0
Rank 88 of 270 measured models
Agentic0.9
Rank 166 of 189 measured models
Reasoning levels
Each point is a reasoning level of this model: more reasoning often raises the score but costs more. Select a point to open that level.
Intelligence Indexmost efficient ↗Price / 1M tokens
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting7.0
Rank 204 of 218 measured models
Strategy & Ops4.4
Rank 203 of 218 measured models
Legal7.1
Rank 210 of 218 measured models
Engineering12.2
Rank 193 of 217 measured models
Economics11.6
Rank 212 of 225 measured models
Standard Benchmarks
MMLU Pro79.8%
Rank 119 of 349 measured models
GPQA Diamond66.8%
Rank 354 of 619 measured models
HLE7.4%
Rank 380 of 664 measured models
LiveCodeBench54.6%
Rank 132 of 343 measured models
SciCode36.0%
Rank 198 of 231 measured models
MATH-50096.1%
Rank 35 of 202 measured models
AIME 202480.7%
Rank 23 of 194 measured models
AIME 202573.0%
Rank 88 of 270 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy