Qwen3.5 Flash

+ contribute

Qwen3.5 Flash is a closed-weights language model from Alibaba, released February 2026. Licence: proprietary.

Catalogue identity notes

Comparison model from the Epoch AI internal-evaluation CSVs (Epoch release date 2026-02-25). API model qwen3.5-flash; Epoch model_metadata: 'Qwen 3.5 Flash (hosted 35B-A3B)'. Kept distinct from open-weights qwen3-5-35b-a3b (hosted product, qwen3-6-flash precedent). Default (thinking) runs used; '_none' runs not mixed in.

64.8±1.1#144 of 719 LLMsfrom 9 benchmark results across 3 sources

$ how it compares

The LLMs ranked either side of Qwen3.5 Flash, out of 828 with a score, then more from Alibaba.

#	model	score	where	RAM	released
163	DeepSeek R1 0528 DeepSeek	65±1	api $0.91/M +local	~110GB	2025-05
164	EXAONE 4.5 33B LG AI Research	65±2	local	~24GB	2026-04
165	Qwen3.5 Flash Alibaba	65±1	api $0.17/M		2026-02
166	ChatGPT-4o (2025-03-26) OpenAI	65±2	comparison only		2025-03
167	INTELLECT-3 Prime Intellect	65±1	local	~48GB	2025-11
	more from Alibaba
18	Qwen3.8 Max (2.4T-A95B) Alibaba	78±1	api $3.00/M +local	~380GB	2026-08
34	Qwen3.8 Max (0902) Alibaba	76±1	api $3.00/M		2026-09
37	Qwen3.8-Flash-Next Alibaba	75±1	local	~59GB	2026-08

see all LLMs · find the ones that fit your machine

$ what it's good at

coding▁▁▁▃▆██▇▆▄▃▁ #163 of 458 * · 19% of its score · 1 test

Beats Gemini 2.5 Pro, Qwen3-Coder-Next (80B-A3B) here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 8B Reasoning 2512, Phi-4-reasoning 14B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena WebDev (Code Arena)	1243.1 ✎	▁▂▄▃▅█▄▇▆▄▁▁ beats 11/119	avg 981	▇▇▇▇▇▇▇▇ 19%	sharp

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #113 of 393 * · 11% of its score · 1 test

Beats LongCat 2.0 (1.6T-A48B), Step 3.5 Flash (196B-A11B), GPT-5 mini here, though they rank higher overall. Trails Nemotron-Cascade-8B, Gemini 2.5 Flash, Mistral Large 3 (675B-A41B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1395.9 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 241/379	avg 1268	▇▇▇▇ 11%	blunt

math▁▂▃▅▆▅▄█▄▁▁▁ #156 of 398 * · 42% of its score · 2 tests

Beats MiMo-V2.5 (310B-A15B), MiniMax-M2.7, MiniMax-M2.1 here, though they rank higher overall. Trails Qwen3-VL 4B Thinking, Granite 4.2 3B, DeepSeek R1 0528 Qwen3 8B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
FrontierMath tiers 1–3 v2	9.5% ✎	▂··▁▃▃▄▄█▅▃▃ beats 6/82	very hard · avg 1.2%	▇▇▇▇▇▇▇▇▇▇▇▇▇ 32%	sharp
OTIS mock AIME 2024–2025	84.4% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 123/193	very hard · avg 8.5%	▇▇▇▇ 10%	sharp · at its level · noisy

other tests5 not in a task · 28% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond	82.3% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 132/208	hard · avg 40%	▇▇▇▇▇▇▇ 18%	sharp · at its level
SimpleQA Verified	20.3% ✎	▁▁▃▂▃▃▆▆█▃▂▅ beats 13/78	very hard · avg 8.0%	▇ 3.3%	at its level
Chess Puzzles (Epoch)	21.0% ✎	█▁▁▁▁▂▁▄▂▂▁▁ beats 83/135	very hard · avg 5.9%	▇ 3.2%	sharp · too hard for it · noisy
Mystery Game Puzzles (Epoch)	20.0% ✎	█··▂▃▇▄█▂▃▁▁ beats 33/74	very hard · avg 9.4%	▇ 2.9%	sharp · too hard for it · noisy
Vectara hallucination leaderboard (HHEM-2.3, factual consistency rate)	89.5% ✎	▁▂▁▂▅█▂▃▄▃▁▁ beats 41/98	very easy · avg 90%	▇ 0.0%	blunt

$ where to run it

Through an API

api · Alibaba Cloud Model Studio · $0.18/M · $0.1 in / $0.4 out per 1M tokens · 1M context · www.alibabacloud.com ↗ · price sourceUSD per 1M tokens, Singapore (International), qwen3.5-flash (currently equivalent to qwen3.5-flash-2026-02-23), 0<Token<=1M single tier: input $0.1, output $0.4. Batch and context-cache discounts, higher tiers and free quota excluded. Observed 2026-09-28.

$ how the score was worked out · Epoch AI — internal evaluatio… 69%, LMArena leaderboard dataset 30%, Vectara hallucination leaderb… 0%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

source	results	share of the score	licence
Epoch AI — internal evaluations	6	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 69%	CC BY 4.0
LMArena leaderboard dataset	2	▇▇▇▇▇▇▇▇▇ 30%	CC BY 4.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)	1	▇ 0%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 64.8