Qwen3.7 Plus

+ contribute

Qwen3.7 Plus is a closed-weights language model from Alibaba, released June 2026.

72.1±0.7#66 of 719 LLMsfrom 33 benchmark results across 6 sources

$ how it compares

The LLMs ranked either side of Qwen3.7 Plus, out of 828 with a score, then more from Alibaba.

#	model	score	where	RAM	released
69	DeepSeek V4 Pro (Preview, Apr 2026) DeepSeek	72±1	local	~604GB	2026-04
70	Claude Opus 4.5 Anthropic	72±1	api $10.00/M		2025-11
71	Qwen3.7 Plus Alibaba	72±1	api $0.70/M		2026-06
72	Kimi K2.7 Code Moonshot AI	72±1	api $1.71/M +local	~359GB	2026-06
73	DeepSeek V4 Flash (Preview, Apr 2026) DeepSeek	72±1	local	~103GB	2026-04
	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▁▁▃▆█▆▅▅▅▄▃▁ #60 of 300 · 22% of its score · 7 tests

Beats Gemini 3.6 Flash, GPT-5 Pro, LongCat 2.0 (1.6T-A48B) here, though they rank higher overall. Trails MiniMax-M3, GLM-5.1 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena Agent (October 2026 aggregate IPS)	-0.0715 IPS ✎	▁▁▁▄▂▃▇█▂▂▁▃ beats 7/49	avg -0.312 IPS	▇▇▇ 8.3%	sharp
SWE-bench Pro public set, Qwen-refined lab +1	57.6% ✎	▂·····▂·▂█▃▅ beats 9/12	hard · avg 18%	▇▇ 4.3%	at its level · several runs
Terminal-Bench 2.1 lab	64.0% ✎	▁·▁·▁▁▄▃▄█▃▇ beats 27/56	hard · avg 16%	▇ 2.9%	at its level · small run
SWE-bench Multilingual lab	75.8% ✎	▁··▁▃▂▅▇█▃▃▁ beats 43/60	hard · avg 29%	▇ 2.7%	at its level
OSWorld-Verified lab	73.3% ✎	█▄·▂▆▂▄▂▆▄▆█ beats 14/25	hard · avg 27%	▇ 1.7%	at its level · small run
WebArena-Verified lab	55.3% ✎	█···█······█ beats 1/2	hard · avg 22%	▇ 1.1%	at its level · small run
DeepSWE v1.1 (resolved) lab	16.5% ✎	▃····▁▁▁▆██▆ beats 0/28	hard · avg 15%	▇ 0.7%	at its level · noisy

coding▁▁▁▃▆██▇▆▄▃▁ #48 of 458 · 12% of its score · 4 tests

Beats GPT-5.4, DeepSeek V4 Flash Vision (Exp), Gemini 3.1 Pro (Preview) here, though they rank higher overall. Trails Mistral Large 4 (public preview) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LiveCodeBench v6 (window unspecified) lab +1	89.6% ✎	▃▅█▅▅▃▅···▃█ beats 13/16	medium · avg 46%	▇▇ 4.6%	small run · several runs
SWE-bench Pro public set, Qwen-refined lab +1	57.6% ✎	▂·····▂·▂█▃▅ beats 9/12	hard · avg 18%	▇▇ 4.3%	at its level · several runs
SWE-bench Multilingual lab	75.8% ✎	▁··▁▃▂▅▇█▃▃▁ beats 43/60	hard · avg 29%	▇ 2.7%	at its level
DeepSWE v1.1 (resolved) lab	16.5% ✎	▃····▁▁▁▆██▆ beats 0/28	hard · avg 15%	▇ 0.7%	at its level · noisy

chat & writing▁▁▁▃▅▄▅█▆▆▇▃ #47 of 393 * · 4.1% of its score · 1 test

Beats MiMo-V2.6-Flash (309B-A15B), GPT-6 Luna, GPT-5.6 Luna here, though they rank higher overall. Trails Claude Sonnet 4.5, MiMo-V2.5-Pro (1T-A42B), GLM-5 here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
LMArena (text)	1455.8 ✎	▁▁▁▂▃▃▃▆▆▇█▃ beats 323/379	avg 1268	▇▇ 4.1%	blunt

math▁▂▃▅▆▅▄█▄▁▁▁ #78 of 398 * · 22% of its score · 2 tests

Beats Claude Sonnet 4.6, Claude Opus 4.5 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
FrontierMath tiers 1–3 v2	34.4% ✎	▂··▁▁▃▄▄█▅▃▃ beats 24/82	very hard · avg 1.2%	▇▇▇▇▇▇▇▇ 20%	sharp · at its level
OTIS mock AIME 2024–2025	93.3% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 154/193	very hard · avg 8.5%	▇ 1.4%	sharp · noisy

vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #27 of 147 · 15% of its score · 7 tests

Beats Claude Sonnet 5.5, MiMo-V2.6-Pro, GPT-5.6 Terra here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
CharXiv (reasoning questions) lab +1	84.4% ✎	▄▂▄▆▄▄▆··▄█▂ beats 19/21	medium · avg 39%	▇▇▇ 6.8%	several runs
Arena vision (style controlled)	1265.5 ✎	▁▁▂▂▂▂▄▅▅▆██ beats 115/145	avg 1068	▇ 2.8%	blunt
SciDocBench scientific-document workflows (overall, 496 instances)	55.9% ✎	▃▃···█▃▅▃·▃▅ beats 8/11	hard · avg 26%	▇ 1.4%	blunt · at its level
Arena document (style controlled)	1452.5 ✎	▁▁▃▃▄▃▇█▅▇▄▅ beats 13/37	avg 1335	▇ 1.4%	blunt
OmniDocBench 1.5 overall (higher is better) lab	91.4% ✎	▂··▂▂▂··▂▂█▅ beats 13/13	easy · avg 69%	▇ 1.3%	small run
SpaceCast-Bench predictive spatial reasoning (overall, 16 task types)	55.3% ✎	▃·▅▃▅▃··▅··█ beats 9/11	very hard · avg 32%	▇ 0.4%	blunt · at its level · noisy
RealWorldQA lab	86.9% ✎	▂▃▂█▃██▆█▂▆▆ beats 38/38	easy · avg 72%	▇ 0.4%	blunt · small run

other tests8 not in a task · 33% of its score

test	result	vs the others in its run	difficulty	counts	why
GPQA Diamond +2	87.9% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 161/208	hard · avg 41%	▇▇▇▇▇▇ 15%	sharp · several runs
Humanity's Last Exam lab +1	34.7% ✎	▁▁▁▃▆▆▇██▆▁▃ beats 81/104	very hard · avg 5.1%	▇▇ 5.0%	at its level · several runs
Mystery Game Puzzles (Epoch)	17.0% ✎	█··▂▃▇▄█▂▃▁▁ beats 28/74	very hard · avg 9.4%	▇ 3.6%	sharp · noisy
IFBench (aggregation unspecified) lab +1	79.1% ✎	▃▇▂▄▅▅▂▄▄▆█▇ beats 72/80	medium · avg 42%	▇ 3.2%	several runs
Chess Puzzles (Epoch)	24.0% ✎	█▁▁▁▁▂▁▄▂▂▁▁ beats 93/135	very hard · avg 5.9%	▇ 2.7%	sharp · noisy
NL2Repo lab	41.1% ✎	▂▂·▂▂▄█▆▆▂▄▆ beats 10/21	very hard · avg 9.6%	▇ 2.0%	at its level · small run
ERQA lab	69.8% ✎	▃··▃··█·▃█▅▅ beats 12/12	hard · avg 35%	▇ 1.1%	at its level · small run
AndroidWorld lab	81.0% ✎	▁·▁▁▂▃█▅▂▂·▃ beats 23/24	medium · avg 46%	▇ 0.9%	blunt · at its level · small run

$ where to run it

Through an API

api · Alibaba Cloud Model Studio · $0.70/M · $0.4 in / $1.6 out per 1M tokens · 1M context · www.alibabacloud.com ↗ · price sourceUSD per 1M tokens, Singapore (International), qwen3.7-plus, ≤256K input tier list price (a limited-time 20% discount is also advertised and not applied); 256K–1M input tier priced higher. Observed 2026-09-25.

$ how the score was worked out · Epoch AI — internal evaluatio… 32%, Qwen/Qwen3.8-27B model card 26%, Qwen (Alibaba) vendor-reporte… 23% and 3 more

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	▇▇▇▇▇▇▇▇▇▇ 32%	CC BY 4.0
Qwen/Qwen3.8-27B model card · lab-reported	14	▇▇▇▇▇▇▇▇ 26%	apache-2.0
Qwen (Alibaba) vendor-reported benchmark scores for its own models (qwen.ai launch posts, Qwen2.5-VL and Qwen3-VL technical reports, Qwen3.8-Flash-Next card) · lab-reported	8	▇▇▇▇▇▇▇ 23%	Factual vendor-reported score (not licensed content)
LMArena leaderboard dataset	4	▇▇▇▇▇ 17%	CC BY 4.0
SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding (arXiv:2609.05141v2)	1	▇ 1%	CC BY 4.0
SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language Models (arXiv:2610.12402v1)	1	▇ 0%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 72.1