Qwen3.5 Plus

+ contribute

Qwen3.5 Plus 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 2026-02-16). API model qwen3.5-plus; Epoch model_metadata: 'Qwen 3.5 Plus (hosted 397B-A17B)'. Kept distinct from open-weights qwen3-5-397b-a17b (hosted product with its own context/tools, following the qwen3-6-plus precedent). Model Studio pricing says the alias is currently equivalent to qwen3.5-plus-2026-02-15. Default (thinking) runs used; '_none' runs not mixed in.

68.9±1.7#95 of 719 LLMsfrom 7 benchmark results across 3 sources

$ how it compares

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

#	model	score	where	RAM	released
102	o3 OpenAI	69±1	api $3.50/M		2025-04
103	MiMo-V2.5 (310B-A15B) Xiaomi	69±1	api $0.21/M +local	~100GB	2026-04
104	Qwen3.5 Plus Alibaba	69±2	api $0.90/M		2026-02
105	Qwen3.5 122B-A10B Alibaba	69±1	api $1.10/M +local	~75GB	2026-02
106	Gemini 3.5 Flash-Lite Google	69±1	api $0.85/M		2026-07
	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

agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #105 of 300 * · 12% of its score · 1 test

Beats Grok 4.20 (0309 reasoning), Grok 4.3, o3-pro here, though they rank higher overall. Trails SmolLM3 3B, Nova 2 Pro (Preview), Mistral Medium 3.5 (128B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Vibe Code Bench (test split, 50 web apps)	15.7% ✎	▃··▃·▃██▃▃▃█ beats 5/14	very hard · avg 2.3%	▇▇▇▇▇ 12%	sharp · noisy

coding▁▁▁▃▆██▇▆▄▃▁ #138 of 458 * · 12% of its score · 1 test

Trails Devstral Small 2 24B, Llama 3.1 Nemotron Ultra 253B v1, Nemotron 3.5 Lightning 30B-A3B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Vibe Code Bench (test split, 50 web apps)	15.7% ✎	▃··▃·▃██▃▃▃█ beats 5/14	very hard · avg 2.3%	▇▇▇▇▇ 12%	sharp · noisy

math▁▂▃▅▆▅▄█▄▁▁▁ #81 of 398 * · 15% of its score · 1 test

Beats Claude Sonnet 4.6, Claude Opus 4.5, Qwen3.5 397B-A17B here, though they rank higher overall. Trails Granite 4.2 30B, INTELLECT-3, EXAONE 4.5 33B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
OTIS mock AIME 2024–2025	86.7% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 129/193	very hard · avg 8.5%	▇▇▇▇▇▇ 15%	sharp · noisy

other tests5 not in a task · 72% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond	84.8% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 144/208	hard · avg 40%	▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%	sharp
Mystery Game Puzzles (Epoch)	16.0% ✎	█··▂▃▇▄█▂▃▁▁ beats 23/74	very hard · avg 9.4%	▇▇▇▇▇▇ 14%	sharp · too hard for it · noisy
Chess Puzzles (Epoch)	22.0% ✎	█▁▁▁▁▂▁▄▂▂▁▁ beats 88/135	very hard · avg 5.9%	▇▇▇▇▇ 13%	sharp · noisy
SimpleQA Verified	25.4% ✎	▁▁▃▂▃▃▆▆█▃▂▅ beats 16/78	very hard · avg 8.0%	▇▇▇▇ 9.5%	at its level
Vectara hallucination leaderboard (HHEM-2.3, factual consistency rate)	89.3% ✎	▁▂▁▂▅█▂▃▄▃▁▁ beats 36/98	very easy · avg 90%	▇ 0.0%	blunt

$ where to run it

Through an API

api · Alibaba Cloud Model Studio · $0.90/M · $0.4 in / $2.4 out per 1M tokens · 1M context · www.alibabacloud.com ↗ · price sourceUSD per 1M tokens, Singapore (International), qwen3.5-plus (currently equivalent to qwen3.5-plus-2026-02-15), 0<Token<=256K input tier (256K-1M tier $0.5/$3 excluded): input $0.4, output $2.4. 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… 87%, Vibe Code Bench (Vals AI, arX… 12%, 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	5	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 87%	CC BY 4.0
Vibe Code Bench (Vals AI, arXiv:2603.04601v3)	1	▇▇▇▇ 12%	CC-BY-4.0
Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository)	1	▇ 0%	Apache-2.0
prior · pull toward the middle		▇ 1%
weighted average		= 68.9