What are Qwen3 Coder 30B A3B Instruct's benchmark scores?

As of 25 Oct 2026, Qwen3 Coder 30B A3B Instruct scores 43.7 ±2.6 on the BenchLeader Index, strongest in agents & tools (47) and weakest in instruction following (36). That rests on 6 independent benchmark results, and every score on this page links to its publisher.

How does Qwen3 Coder 30B A3B Instruct rank?

Qwen3 Coder 30B A3B Instruct is #562 of 785 ranked configurations on 25 Oct 2026. 285 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.

How much does Qwen3 Coder 30B A3B Instruct cost per 1M tokens?

As of 25 Oct 2026, Qwen3 Coder 30B A3B Instruct costs $0.190 per 1M input tokens and $0.770 per 1M output tokens, $0.335 blended (three input tokens per output token). The list price last changed on 21 Oct 2026.

When was Qwen3 Coder 30B A3B Instruct released?

Alibaba released Qwen3 Coder 30B A3B Instruct on 31 Jul 2025.

Alibaba Open weights: Qwen/Qwen3-Coder-30B-A3B-Instruct Compare with another model

Qwen3 Coder 30B A3B Instruct

Qwen3 Coder 30B A3B Instruct is an Alibaba open-weights model, released 31 Jul 2025. Its best configuration ranks #562 of 785 on the BenchLeader Index at 43.7 ±2.6, in the lower half. The ± is the point: 285 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in agents & tools (47) and lowest in instruction following (36). At $0.335 per million tokens blended it is cheaper than most ranked models. Output speed of 244 tokens per second puts it in the fastest quarter, with a first answer in 1.1 s. Last measured 31 Jul 2025.stale: no new result in six months

Blended price: $0.335/M; $0.190 in · $0.770 out
Output speed: 244 tok/s; measured by Artificial Analysis
First answer: 1.07 s; first token 1.31 s
Context: 262k
Full answer: 3.12 s; median, reasoning included
Cost per run: –
Released: 31 Jul 2025

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

Overall index44
Reasoning41
Agents & tools47
Knowledge39
Instruction following36
Long context40
Composite40

How its index has moved

9 Sept 2026 to 21 Oct 2026

The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.

Benchmark results

See all LLM benchmarks. 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	not stated	Source
GPQA Diamond (AA)not in index	51.6%#419	Artificial Analysis
Humanity's Last Exam (AA)not in index	3.9%#559	Artificial Analysis
CritPt	0.0%#315	Artificial Analysis

Coding

Benchmark	not stated	Source
SWE-bench Verified (any scaffold)not in index	60.4%#29	SWE-bench

Agents & tools

Benchmark	not stated	Source
Terminal-Bench Hard	15.2%#193	Artificial Analysis
τ²-Bench Telecom (AA)not in index	34.5%#238	Artificial Analysis

Knowledge

Benchmark	not stated	Source
AA-Omniscience	-50.7#393	Artificial Analysis
AA-Omniscience: accuracynot in index	16.4%#390	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	19.7%#283	Artificial Analysis

Instruction following

Benchmark	not stated	Source
IFBench	32.6%#340	Artificial Analysis

Long context

Benchmark	not stated	Source
AA-LCR	32.7%#382	Artificial Analysis

Composite

Benchmark	not stated	Source
AA Intelligence Index v4.3.2	9.6#393	Artificial Analysis

Where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

Provider	Speed	First token	Input $/M	Output $/M	Context	Quantisation
Amazon Bedrock	260 tok/s	0.59 s	$0.150	$0.600	262k	–
SiliconFlow	30 tok/s	0.99 s	$0.070	$0.280	262k	fp8

Price history

The price above, per 1M tokens, every day it changed.

input outputnow $0.190 in · $0.770 out

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

Workload	Tokens in / out	Cost	With caching	Time
Chat reply	400 / 300	$0.0003	–	2.3 s
Summarize a 30-page report	12,000 / 600	$0.0027	–	3.5 s
Code edit	6,000 / 1,500	$0.0023	–	7.2 s
Agentic coding session	60,000 / 4,000	$0.015	–	17.5 s
Structured extraction	2,000 / 200	$0.0005	–	1.9 s

New this month

Questions people ask

What are Qwen3 Coder 30B A3B Instruct's benchmark scores?: As of 25 Oct 2026, Qwen3 Coder 30B A3B Instruct scores 43.7 ±2.6 on the BenchLeader Index, strongest in agents & tools (47) and weakest in instruction following (36). That rests on 6 independent benchmark results, and every score on this page links to its publisher.
How does Qwen3 Coder 30B A3B Instruct rank?: Qwen3 Coder 30B A3B Instruct is #562 of 785 ranked configurations on 25 Oct 2026. 285 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
How much does Qwen3 Coder 30B A3B Instruct cost per 1M tokens?: As of 25 Oct 2026, Qwen3 Coder 30B A3B Instruct costs $0.190 per 1M input tokens and $0.770 per 1M output tokens, $0.335 blended (three input tokens per output token). The list price last changed on 21 Oct 2026.
When was Qwen3 Coder 30B A3B Instruct released?: Alibaba released Qwen3 Coder 30B A3B Instruct on 31 Jul 2025.

Data as of 25 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Qwen3 Coder 30B A3B Instruct: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/qwen3-coder-30b-a3b.