Qwen3.5 0.8B

Alibaba

Verified against Artificial Analysis · Jul 13, 2026

Capability

percentile index

Price /M

$0 / $0

in / out

Context

—

Avg score

12.4

7 benchmarks

AA Intelligence

5.5

index

Weights

Open

Released

Mar 2, 2026

About

Qwen3.5 0.8B is a open-weights model in the Qwen3.5 family from Alibaba. Benchmarked on 7 evals, averaging 12.4.

Benchmark scores · 7

avg 12.4 — higher is better

τ²-benchartificial-analysis · 2026-07

47.7

IFBenchartificial-analysis · 2026-07

21.5

GPQA Diamondartificial-analysis · 2026-07

11.1

AA Long-Context Reasoningartificial-analysis · 2026-07

5.3

Humanity's Last Examartificial-analysis · 2026-07

1.2

SciCodeartificial-analysis · 2026-07

Terminal-Bench Hardartificial-analysis · 2026-07

Details

PublisherAlibaba

FamilyQwen3.5

Parameters—

License—

WeightsOpen

ReleasedMar 2, 2026

Performance & price

Price in / out$0 / $0 per 1M

Coding index0.0

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$0/M