MDL
Qwen3 32B
Alibaba
Verified against Artificial Analysis · Jul 13, 2026
Capability
58
percentile index
Price /M
$0.7 / $8.4
in / out
Context
131.1K
tokens
Avg score
43.9
11 benchmarks
AA Intelligence
11.5
index
Speed
100 tok/s
TTFT 1.1s
Released
Apr 28, 2025
About
Qwen3 32B is a open-weights model in the Qwen3 family from Alibaba. Benchmarked on 11 evals, averaging 43.9.
Benchmark scores · 11
avg 43.9 — higher is betterThe research behind this model
all papers mentioning it →Program-as-Weights: A Programming Paradigm for Fuzzy Functions▲ 118 on HF · Jul 2, 2026OpenThoughts-Agent: Data Recipes for Agentic Models▲ 46 on HF · Jun 23, 2026CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents▲ 37 on HF · Jun 22, 2026ChLogic: Evaluating Robustness of Logical Reasoning in Chinese Expressions▲ 8 on HF · Jun 16, 2026Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns▲ 2 on HF · Jun 17, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed100 tok/s
Latency (TTFT)1.1s
First answer21s
Price in / out$0.7 / $8.4 per 1M
Blended price$2.63 / 1M
Coding index15.3
Math index73.0
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$8.4/M