MDL
Qwen3 Coder 30B A3B Instruct
Alibaba
Verified against Artificial Analysis · Jul 13, 2026
Capability
51
percentile index
Price /M
$0.45 / $2.25
in / out
Context
160K
tokens
Avg score
38.5
11 benchmarks
AA Intelligence
13.6
index
Speed
103 tok/s
TTFT 1.5s
Released
Jul 31, 2025
About
Qwen3 Coder 30B A3B Instruct is a open-weights model in the Qwen3 family from Alibaba. Benchmarked on 11 evals, averaging 38.5.
Benchmark scores · 11
avg 38.5 — higher is betterThe research behind this model
all papers mentioning it →FPMoE: A Sparse Mixture-of-Experts Approach to Functional Code GenerationMay 27, 2026LCC-LLM: Leveraging Code-Centric Large Language Models for Malware AttributionMay 7, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed103 tok/s
Latency (TTFT)1.5s
Price in / out$0.45 / $2.25 per 1M
Blended price$0.9 / 1M
Math index29.0
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$2.25/M