Models/Qwen3.6 Plus

MDL

Qwen3.6 Plus

Alibaba

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0.5 / $3

in / out

Context

tokens

Avg score

63.0

7 benchmarks

AA Intelligence

39.6

index

Speed

53 tok/s

TTFT 1.6s

Released

Apr 2, 2026

About

Qwen3.6 Plus is a open-weights model in the Qwen3.6 family from Alibaba. Benchmarked on 7 evals, averaging 63.0.

Benchmark scores · 7

avg 63.0 — higher is better

τ²-benchartificial-analysis · 2026-07

97.7

GPQA Diamondartificial-analysis · 2026-07

88.2

IFBenchartificial-analysis · 2026-07

75.2

AA Long-Context Reasoningartificial-analysis · 2026-07

69.7

Terminal-Bench Hardartificial-analysis · 2026-07

43.9

SciCodeartificial-analysis · 2026-07

40.7

Humanity's Last Examartificial-analysis · 2026-07

25.7

The research behind this model

all papers mentioning it →

A Deterministic Agentic Workflow for HS Tariff Classification: Multi-Dimensional Rule Reasoning with Interpretable DecisionsMay 14, 2026

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details

PublisherAlibaba

FamilyQwen3.6

Parameters—

License—

WeightsOpen

ReleasedApr 2, 2026

Performance & price

Output speed53 tok/s

Latency (TTFT)1.6s

First answer1m 47s

Price in / out$0.5 / $3 per 1M

Blended price$1.13 / 1M

Coding index54.5

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$3/M