AlibabaReasoning modelCompare with another model

Qwen3.5 Flash

Reasoning effort

Qwen3.5 Flash is an Alibaba proprietary reasoning model, released 25 Feb 2026. Its best configuration ranks #323 of 775 on the BenchLeader Index at 52.1 ±5.8, in the upper half. The ± is the point: 332 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 (59) and lowest in coding (47). At $0.094 per million tokens blended it is among the cheapest fifth of ranked models. Output speed of 86 tokens per second puts it faster than most, with a first token in 0.6 s. 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 19 Oct 2026.

Blended price: $0.094/M; $0.029 in · $0.287 out
Output speed: 86 tok/s; OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
First answer: 0.58 s
Context: 1M
Full answer: –
Cost per run: –
Released: 25 Feb 2026

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

Overall index52
Reasoning59
Coding47
Maths50
Knowledge50
Human preference57

Versions

Alibaba has shipped 4 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

Model	Released	Index	Rank
Qwen3.8 Flash	26 Aug 2026	–	–
Qwen3.7 Flashno reasoning	27 Jul 2026	–	–
Qwen3.6 Flash	27 Apr 2026	44.1	#542
Qwen3.5 Flashthis page	25 Feb 2026	52.1	#323

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	–	–	86 tok/s	0.58 s	$0.0001	Maths 36
not statedbest	52.1	#323	86 tok/s	0.58 s	$0.0001	Coding 47 · Human preference 57 · Knowledge 50 · Maths 50 · Reasoning 59

How its index has moved

8 Sept 2026 to 17 Oct 2026

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	not stated	Source
GPQA Diamondeffort not stated	–	82.3%#112	Epoch AI Benchmarking Hub
Arena Hard Promptseffort not stated	–	1416#159	Arena (LMArena)
GPQA Diamond (Vals)not in indexeffort not stated	–	82.8%#58	Vals AI
Chess Puzzlesnot in indexeffort not stated	–	14.0%#110	Epoch AI Benchmarking Hub
Mystery Game Puzzlesnot in index	16.0%#83	20.0%#59	Epoch AI Benchmarking Hub
LMCAnot in indexeffort not stated	–	29.1%#140	Epoch AI Benchmarking Hub
DTBenchnot in indexeffort not stated	–	82.9%#116	Epoch AI Benchmarking Hub

Coding

Benchmark	not stated	Source
Arena Coding	1435#163	Arena (LMArena)
Arena WebDev	1244#124	Arena (LMArena)
LiveCodeBench	83.3%#47	Vals AI
SWE-bench (Vals)not in index	64.4%#71	Vals AI
ALE-Benchnot in index	221.8#122	Epoch AI Benchmarking Hub

Agents & tools

Benchmark	not stated	Source	Trend
Terminal-Bench 2.0 (Vals)not in index	24.7%#51	Vals AI
Vending-Bench 2not in index	462.7#59	Andon Labs

Maths

Benchmark	no reasoning	not stated	Source
FrontierMath Tiers 1–3	18.3%#94	9.5%#105	Epoch AI Benchmarking Hub
OTIS Mock AIMEeffort not stated	–	84.4%#97	Epoch AI Benchmarking Hub
AIME (Vals)effort not stated	–	92.5%#19	Vals AI
Arena Mathseffort not stated	–	1402#147	Arena (LMArena)

Knowledge

Benchmark	not stated	Source
SimpleQA Verified	20.3%#72	Epoch AI Benchmarking Hub
MMLU-Pro	84.1%#65	Vals AI
LegalBench	84.3%#36	Vals AI
CorpFin	63.6%#44	Vals AI
TaxEval	72.2%#66	Vals AI
CaseLaw v2not in index	56.0%#31	Vals AI
MedCodenot in index	33.0%#83	Vals AI
MedScribenot in index	70.6%#90	Vals AI

Instruction following

Benchmark	not stated	Source	Trend
Arena Instruction Followingnot in index	1382#162	Arena (LMArena)

Human preference

Benchmark	not stated	Source
Arena Text	1396#155	Arena (LMArena)
Arena Creative Writingnot in index	1338#178	Arena (LMArena)
Arena Multi-turnnot in index	1395#160	Arena (LMArena)
Arena Longer Queriesnot in index	1400#161	Arena (LMArena)

Multimodal

Benchmark	not stated	Source
MMMU-Pro (Vals)not in index	81.9%#38	Vals AI
MortgageTaxnot in index	67.4%#25	Vals AI
SAGEnot in index	42.5%#53	Vals AI

Composite

Benchmark	not stated	Source	Trend
Epoch Capabilities Indexnot in index	143.5#95	Epoch AI Benchmarking Hub

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.

Provider	Speed	First token	Input $/M	Output $/M	Context	Quantisation
Alibaba Cloud Int.	92 tok/s	0.63 s	$0.065	$0.260	1M	–

Price history

Listed price per 1M tokens over time, as recorded by OpenRouter for the provider with the longest history.

input outputnow $0.065 in · $0.260 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 at $0.010 per 1M. Reasoning tokens are not modelled.

Workload	Tokens in / out	Cost	With caching	Time
Chat reply	400 / 300	$0.0001	$0.0001	4.1 s
Summarize a 30-page report	12,000 / 600	$0.0005	$0.0003	7.6 s
Code edit	6,000 / 1,500	$0.0006	$0.0005	18.0 s
Agentic coding session	60,000 / 4,000	$0.0029	$0.0020	47.1 s
Structured extraction	2,000 / 200	$0.0001	$0.0001	2.9 s