Skip to content
Bencher

Models · Qwen (Alibaba) · Out sinceReleased 25 Feb 2026

Qwen3.5-35B-A3B

Available on OpenRouterOn OpenRouterAvailable nowGenerally availableClosed (can't be downloaded)Proprietary

Qwen3.5-35B-A3B is made by Qwen (Alibaba). We don't have enough test results yet to rank it. It's cheap to use.

Auto-created from OpenRouter catalog; verify details.

Writing & creativity
—
Research & analysis
—
Coding
—
Price
Cheap$0.16 / $1.30
Price per 1M (blended)Blended / 1M
$0.45
MemoryContext
262K
Longest answerMax output
—
Test resultsResults
3 (3 independent3 indep.)
Out sinceReleased
25 Feb 2026
Made byVendor
Qwen (Alibaba)
UnderstandsInputs
—

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

You can't choose how long this one thinks.

No adjustable reasoning setting listed.

Read more

Links

Using it through OpenRouter

On OpenRouter

OpenRouter is a service that gives access to many AI models in one place. This model is listed there as qwen/qwen3.5-35b-a3b.

Route it as qwen/qwen3.5-35b-a3b at $0.16 in / $1.30 out per 1M tokens, 262K context. Listed since 25 Feb 2026.

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
NotesNotes
EuroEval Swedish (generative)1.6DefaultQwen/Qwen3.5-35B-A3B-FP8 (val)Independent testIndependentEuroEval (Alexandra Institute) ↗29 Sep 2026—EuroEval rank tier 5; ±0.23; lower is better; task scores (first metric): SweDN summarisation 38.42 ± 0.23, Skolprov 82.15 ± 2.91, Swedish facts 22.47 ± 0.00, ScaLA-sv 66.01 ± 1.76
SWE-rebench17.1%DefaultQwen3.5-35B-A3BIndependent testIndependentSWE-rebench (Nebius) ↗1 Oct 2026SWE-rebench standard scaffoldtime window 2026-05-15..2026-07-01 (111 problems, 65 repos); ±1.07; pass@5 36.9%; $0.99/problem
Vectara Hallucination Leaderboard (HHEM)10.5%Defaultqwen/qwen3.5-35b-a3bIndependent testIndependentVectara ↗22 Sep 2026—factual consistency 89.5 %; answer rate 99.8 %; avg summary 94.9 words; HHEM-2.3 judge; effort not stated (API default)