Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is Qwen3-32B?

95 SI-IQ · 90% interval 89–100
Rank 71 of 80 ranked models · Plausible rank range 66–73

Qwen3-32B is a model from Alibaba, released on Apr 28, 2025. Its SI-IQ is 95 (90% interval 89–100), estimated from 5 benchmark results by 4 independent evaluators.

Facts

Developer: Alibaba
Released: Apr 28, 2025
Access: Open weights (restricted licence)
Benchmarks used: 5 results from 4 evaluators

Ability by area (SI-IQ, 90% interval)

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark	Area	Score	Implied SI-IQ	Evaluated by	As listed by the source	Retrieved	Source
OTIS Mock AIME 2024–2025	Math	66.9%	101	Epoch AI	`Qwen3-32B`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
Aider Polyglot	Coding	40.0%	90	Aider	`Qwen3 32B`	Oct 18, 2026	Aider LLM Leaderboards · data file
GPQA Diamond	Knowledge	65.7%	90	Epoch AI	`Qwen3-32B`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	55.7%	80	OpenRouter	`qwen/qwen3-32b-04-28` DeepInfra · median over providers (4 of 4 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file
Berkeley Function Calling Leaderboard	Agents	48.7%	96	UC Berkeley (Gorilla)	`Qwen3-32B (FC)`	Oct 18, 2026	Berkeley Function Calling Leaderboard · data file
τ²-bench Airline (OpenRouter run)	Agents	45.2%	82	OpenRouter	`qwen/qwen3-32b-04-28` DeepInfra · median over providers (4 of 4 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file

Human preference (Arena)

On the Arena leaderboard, where people vote between two anonymous answers, Qwen3-32B has a rating of 1,347 (1,337–1,356) from 3,926 votes (published Oct 15, 2026). Human preference is a different measure from benchmark ability and is not part of SI-IQ. Arena (Hugging Face)

Models with similar SI-IQ

Model	SI-IQ
Claude Sonnet 4Anthropic	97	Qwen3-32B vs Claude Sonnet 4
Claude Opus 4Anthropic	98	Qwen3-32B vs Claude Opus 4
GPT-4.1 miniOpenAI	91	Qwen3-32B vs GPT-4.1 mini
GPT-4.1OpenAI	91	Qwen3-32B vs GPT-4.1
Claude 3.7 SonnetAnthropic	99	Qwen3-32B vs Claude 3.7 Sonnet

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Aider polyglot leaderboard data (Apache-2.0); Arena leaderboard dataset on Hugging Face (CC BY 4.0); Berkeley Function Calling Leaderboard, Gorilla project (Apache-2.0); Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..