BenchLeader

Qwen3 Coder Next

Quality#244 of 339
42.3Index
Below the median
−7.6 on the median
Price#82 of 255
$0.483per 1M tokens
Cheaper than most
0.6× the median
Speed#126 of 215
70tokens/s
Below the median
0.9× the median
Value#96 of 255
87.6points per $
Above the median
1.6× the median

Better value: Qwen3.5-4B scores 49.3 for $0.060/M, 88% cheaper.

47 cheaper ranked models score higher: GPT-5.6 Luna (58.2, $0.450), Inkling 2 Small (57.9, $0.475), DeepSeek V4 Flash (57.2, $0.262) and 44 more.

As of 15 Nov 2026, Qwen3 Coder Next by Alibaba scores 42.3 on the BenchLeader Index (611 ranked configurations), with its best results in long context (47) and weakest in reasoning (34). API pricing: $0.450 per 1M tokens blended (3 input : 1 output), list price on 15 Nov 2026. It streams about 70 tokens/s (Artificial Analysis). Released 2 Feb 2026.

Key facts (as of 15 Nov 2026)

  • Qwen3 Coder Next API pricing: $0.450 per 1M tokens blended (3 input : 1 output) (list price, 15 Nov 2026).
  • Qwen3 Coder Next streams about 70 tokens/s (Artificial Analysis, 15 Nov 2026).
  • Qwen3 Coder Next was released on 2 Feb 2026 (Alibaba).

In detail. Qwen3 Coder Next is an Alibaba open-weights model, released 2 Feb 2026. Its best configuration ranks #500 of 611 on the BenchLeader Index at 42.3 ±4.6, in the lower half. The ± is the point: 199 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 long context (47) and lowest in reasoning (34). At $0.483 per million tokens blended it is cheaper than most ranked models. Output speed of 70 tokens per second puts it slower than most, with a first answer in 1.6 s. Last measured 3 Feb 2026.stale: no new result in six months

Blended price
$0.483/M
$0.310 in · $1.00 out
via Artificial Analysis
Output speed
70 tok/s
measured by Artificial Analysis
First answer
1.60 s
first token 0.68 s
Context
262k
via models.dev
Full answer
45 s
last measured 13 Nov 2026
Cost per task
–
Tokens per task
–
Released
2 Feb 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index42
  2. Reasoning34
  3. Coding37
  4. Agents & tools38
  5. Instruction following39
  6. Long context47

Embed this rank

More badge styles
[![Qwen3 Coder Next on BenchLeader: #238 overall](https://www.benchleader.com/badge/qwen3-coder-next.svg?style=compact)](https://www.benchleader.com/models/qwen3-coder-next)

Paste it at the top of README.md, beside your other badges. The badge redraws with every data update and links back to this page.

Get an email when Alibaba ships a new model

And once when it gets ranked, plus the weekly review on Mondays.

Choose providers and emails

How its index has moved

9 Sep 2026 to 15 Nov 2026
374349

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.

Metadata

Benchmarknot statedSourceTrend
AA Openness Indexnot in index41.7#151Artificial Analysis

Reasoning

Benchmarknot statedSourceTrend
GPQA Diamond (AA)not in index73.7%#270Artificial Analysis
Humanity's Last Exam (AA)not in index10.2%#342Artificial Analysis
HLE-Diamond (AA)4.3%#160Artificial Analysis
CritPtnot in index0.0%#337Artificial Analysis

Coding

Benchmarknot statedSourceTrend
SciCode36.2%#203SciCode
WeirdML34.4%#132WeirdML
SciCode (AA)not in index36.2%#215Artificial Analysis
Terminal-Bench 4.0 (AA)not in index0.0%#186Artificial Analysis
Terminal-Bench 2.1 (AA)not in index38.2%#148Artificial Analysis

Knowledge

Benchmarknot statedSourceTrend
Global-MMLU-Lite (AA)not in index79.4%#76Artificial Analysis

Instruction following

Benchmarknot statedSourceTrend
IFBench35.2%#315Artificial Analysis

Long context

Benchmarknot statedSourceTrend
AA-LCR v1.147.0%#350Artificial Analysis

Composite

Benchmarknot statedSourceTrend
AA Intelligence Index v4.3.2not in index9.2#415Artificial Analysis
AA Progress Index v1not in index226.9#328Artificial Analysis

API pricing: 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.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
Parasail49 tok/s0.76 s$0.120$0.800262kbf16

Price history

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

$0.00$0.413$0.825$1.24$1.65Sep 26Oct 26Nov 26
input output
Now $0.310 in · $1.00 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.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0004–5.9 s
Summarize a 30-page report12,000 / 600$0.0043–10.1 s
Code edit6,000 / 1,500$0.0034–22.9 s
Agentic coding session60,000 / 4,000$0.023–58.5 s
Structured extraction2,000 / 200$0.0008–4.4 s

More from Alibaba

New this month

See also

Embed or cite

Show where Qwen3 Coder Next ranks on a model card or README. The badge redraws itself with every daily update, carries the data date and links back to this page.

[![Qwen3 Coder Next on BenchLeader: #238 overall](https://www.benchleader.com/badge/qwen3-coder-next.svg)](https://www.benchleader.com/models/qwen3-coder-next)

Cite this

The ranking changes daily, so a reference carries the data date. APA style:

BenchLeader. (2026, November 15). Qwen3 Coder Next on the BenchLeader Index (method v1.4) [Data set]. Retrieved November 15, 2026, from https://www.benchleader.com/models/qwen3-coder-next

BibTeX:

@misc{benchleader_qwen3_coder_next_20261115,
  author       = {{BenchLeader}},
  title        = {{Qwen3 Coder Next on the BenchLeader Index (method v1.4)}},
  year         = {2026},
  month        = nov,
  howpublished = {\url{https://www.benchleader.com/models/qwen3-coder-next}},
  note         = {Data as of 2026-11-15}
}

Every badge style, the embeddable top-10 widget and how to cite the Index

Questions people ask

What are Qwen3 Coder Next's benchmark scores?
As of 15 Nov 2026, Qwen3 Coder Next scores 42.3 ±4.6 on the BenchLeader Index, strongest in long context (47) and weakest in reasoning (34). That rests on independent benchmark results only, and every score on this page links to its publisher.
How does Qwen3 Coder Next rank?
Qwen3 Coder Next is #500 of 611 ranked configurations on 15 Nov 2026. 199 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Fable 5.2 (max effort) at 72.7.
How much does Qwen3 Coder Next cost per 1M tokens?
As of 15 Nov 2026, Qwen3 Coder Next costs $0.310 per 1M input tokens and $1.00 per 1M output tokens, $0.483 blended (three input tokens per output token). The list price last changed on 17 Oct 2026.
When was Qwen3 Coder Next released?
Alibaba released Qwen3 Coder Next on 2 Feb 2026.

Data as of 15 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Qwen3 Coder Next: benchmarks, pricing, speed and rank”, data as of 15 Nov 2026, https://www.benchleader.com/models/qwen3-coder-next.