What are Qwen3.5 2B's benchmark scores?

As of 25 Oct 2026, Qwen3.5 2B (thinking effort) scores 39.4 ±3.3 on the BenchLeader Index, strongest in reasoning (41) and weakest in multimodal (25). That rests on 7 independent benchmark results, and every score on this page links to its publisher.

How does Qwen3.5 2B rank?

Qwen3.5 2B (thinking effort) is #687 of 785 ranked configurations on 25 Oct 2026. 233 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.

When was Qwen3.5 2B released?

Alibaba released Qwen3.5 2B on 2 Mar 2026. BenchLeader has results for it at 2 reasoning-effort settings.

Alibaba Open weights: Qwen/Qwen3.5-2BReasoning modelCompare with another model

Qwen3.5 2B

Reasoning effort

Qwen3.5 2B is an Alibaba open-weights reasoning model, released 2 Mar 2026. Its best configuration (thinking reasoning effort) ranks #687 of 785 on the BenchLeader Index at 39.4 ±3.3, in the lower half. The ± is the point: 233 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 reasoning (41) and lowest in multimodal (25). It has been measured at 2 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 2 Mar 2026.stale: no new result in six months

Blended price: –
Output speed: –
First answer: –
Context: 262k
Full answer: –
Cost per run: –
Released: 2 Mar 2026

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

Overall index39
Reasoning41
Agents & tools37
Knowledge34
Instruction following35
Multimodal25
Long context34
Composite37

Reasoning-effort configurations

The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.

Effort	Index	Rank	Speed	First answer	Chat reply cost	Categories
no reasoning	37.7	#726	–	–	–	Agents & tools 37 · Composite 36 · Instruction following 33 · Knowledge 24 · Long context 31 · Multimodal 25 · Reasoning 41
thinkingbest	39.4	#687	–	–	–	Agents & tools 37 · Composite 37 · Instruction following 35 · Knowledge 34 · Long context 34 · Multimodal 25 · Reasoning 41

How its index has moved

9 Sept 2026 to 23 Oct 2026

thinking
no reasoning

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	no reasoning	thinking	Source
GPQA Diamond (AA)not in index	43.8%#455	45.6%#450	Artificial Analysis
Humanity's Last Exam (AA)not in index	5.0%#459	2.6%#612	Artificial Analysis
CritPt	0.0%#315	0.0%#315	Artificial Analysis

Coding

Benchmark	no reasoning	thinking	Source
Terminal-Bench 2.1 (AA)not in index	0.0%#232	3.0%#218	Artificial Analysis

Agents & tools

Benchmark	no reasoning	thinking	Source
Terminal-Bench Hard	3.8%#298	3.8%#298	Artificial Analysis
τ²-Bench Telecom (AA)not in index	81.6%#116	69.0%#159	Artificial Analysis
GDPval-AA v2.1not in index	0.0%#124	0.0%#124	Artificial Analysis

Knowledge

Benchmark	no reasoning	thinking	Source
AA-Omniscience	-83.1#547	-60.2#467	Artificial Analysis
AA-Omniscience: accuracynot in index	7.4%#524	8.1%#519	Artificial Analysis
AA-Omniscience: non-hallucinationnot in index	2.3%#548	25.8%#237	Artificial Analysis

Instruction following

Benchmark	no reasoning	thinking	Source
IFBench	29.1%#368	31.5%#351	Artificial Analysis

Multimodal

Benchmark	no reasoning	thinking	Source
MMMU-Pro	42.7%#261	43.0%#259	Artificial Analysis

Long context

Benchmark	no reasoning	thinking	Source
AA-LCR	14.0%#456	21.0%#428	Artificial Analysis

Composite

Benchmark	no reasoning	thinking	Source
AA Intelligence Index v4.3.2	6.2#538	6.9#501	Artificial Analysis

New this month

Questions people ask

What are Qwen3.5 2B's benchmark scores?: As of 25 Oct 2026, Qwen3.5 2B (thinking effort) scores 39.4 ±3.3 on the BenchLeader Index, strongest in reasoning (41) and weakest in multimodal (25). That rests on 7 independent benchmark results, and every score on this page links to its publisher.
How does Qwen3.5 2B rank?: Qwen3.5 2B (thinking effort) is #687 of 785 ranked configurations on 25 Oct 2026. 233 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.
When was Qwen3.5 2B released?: Alibaba released Qwen3.5 2B on 2 Mar 2026. BenchLeader has results for it at 2 reasoning-effort settings.

Data as of 25 Oct 2026. Compare these configurations.

Cite as: BenchLeader, “Qwen3.5 2B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/qwen3-5-2b.