Qwen3.7 Max

+ contribute

Qwen3.7 Max is a closed-weights language model from Alibaba, released May 2026.

74.1±0.7#48 of 719 LLMsfrom 16 benchmark results across 6 sources

$ how it compares

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

#	model	score	where	RAM	released
49	GPT-5.3-Codex OpenAI	74±1	api $4.81/M		2026-02
50	DeepSeek V4 Flash (0731) DeepSeek	74±1	api $0.11/M +local	~92GB	2026-07
51	Qwen3.7 Max Alibaba	74±1	api $3.75/M		2026-05
52	GLM-5.3-Flash Z.ai	74±1	api $0.24/M +local	~103GB	2026-08
53	Gemini 3.5 Flash Google	74±1	api $3.38/M		2026-05
	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▁▁▃▆█▆▅▅▅▄▃▁ #53 of 300 · 27% of its score · 6 tests

Beats Gemini 3.1 Pro (Preview) here, though they rank higher overall. Trails Claude Sonnet 4.6, Kimi K2.6, Qwen3.8 27B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena Agent (October 2026 aggregate IPS)	-0.0513 IPS ✎	▁▁▁▄▃▃▇█▂▂▁▃ beats 11/49	avg -0.312 IPS	▇▇▇▇ 9.3%	sharp
SWE-bench Verified	77.3% ✎	▁··▁·▁▂▁▄█▄▁ beats 24/29	hard · avg 19%	▇▇▇ 8.0%	sharp
Agents' Last Exam overall full-pass rate (fixed OpenClaw + GUI-as-Tool)	11.8% ✎	▄···█▄▄▄█▄·█ beats 5/10	very hard · avg 1.7%	▇▇ 4.1%	typical
MCP-Atlas (public set)	76.4% ✎	█··█·██·████ beats 5/7	hard · avg 29%	▇ 2.7%	at its level
Legal Research Bench (agentic, all-pass)	25.2% ✎	▄█··▄▄▄██·▄█ beats 5/12	very hard · avg 5.8%	▇ 1.7%	at its level
EEGAgentBench overall (tool-based EEG analysis agents, 6 tasks)	52.9% ✎	▂·▁▁··▇▇█▃·▁ beats 23/25	hard · avg 29%	▇ 1.4%	blunt · at its level

coding▁▁▁▃▆██▇▆▄▃▁ #47 of 458 * · 16% of its score · 2 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), Claude Sonnet 4.6, Qwen3.8 27B here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Arena WebDev (Code Arena)	1514.9 ✎	▁▂▄▃▅█▄▇▆▄▁▁ beats 74/119	avg 981	▇▇▇ 8.2%	sharp
SWE-bench Verified	77.3% ✎	▁··▁·▁▂▁▄█▄▁ beats 24/29	hard · avg 19%	▇▇▇ 8.0%	sharp

math▁▂▃▅▆▅▄█▄▁▁▁ #26 of 398 · 40% of its score · 3 tests

Beats DeepSeek V4.1 Flash, Gemini 3.8 Flash, Grok 4.6 here, though they rank higher overall.

test	result	vs the others in its run	difficulty	counts	why
FrontierMath tiers 1–3 v2	64.6% ✎	▂··▁▁▃▄▄█▅▃▃ beats 49/82	very hard · avg 1.2%	▇▇▇▇▇▇▇▇▇ 22%	sharp · at its level
FrontierMath tier 4 v2	34.1% ✎	▁▂▁▂█▅▂▂▁▁▁▁ beats 40/63	very hard · avg 0.1%	▇▇▇▇▇▇▇ 17%	sharp · at its level
OTIS mock AIME 2024–2025	95.6% ✎	▃▃▄▃▃▃▇▇█▃▂▅ beats 165/193	very hard · avg 8.5%	▇ 1.1%	sharp · maxed out · noisy

web search▂▁▂▆▄█▃▃▁▁·▁ #47 of 80 * · 1.7% of its score · 1 test

Beats Gemini 3.1 Pro (Preview) here, though they rank higher overall. Trails GPT-4o mini (2024-07-18), Mistral Small 3.1 24B (2503), Llama 4 Scout (109B-A17B) here, though they rank lower overall.

test	result	vs the others in its run	difficulty	counts	why
Legal Research Bench (agentic, all-pass)	25.2% ✎	▄█··▄▄▄██·▄█ beats 5/12	very hard · avg 5.8%	▇ 1.7%	at its level

other tests6 not in a task · 24% of its score

test	result	vs the others in its run	difficulty	counts	why
EBR-bench (Epoch)	9.5% ✎	▄▂·▆█▂▆▄▆▆·▄ beats 4/23	very hard · avg 0.3%	▇▇▇ 7.7%	sharp
Mystery Game Puzzles (Epoch)	32.0% ✎	█··▂▃▇▄█▂▃▁▁ beats 51/74	very hard · avg 9.4%	▇▇ 5.3%	sharp · noisy
GPQA Diamond	90.9% ✎	▁▁▁▁▂▄▆▄▅▇█▅ beats 179/208	hard · avg 40%	▇▇ 3.9%	sharp
Chess Puzzles (Epoch)	19.0% ✎	█▁▁▁▁▂▃▄▂▂▁▁ beats 74/135	very hard · avg 5.9%	▇ 3.6%	sharp · noisy
Legal Research Bench (single-shot, no tools, all-pass)	2.7% ✎	▃▃█▃·▅···█▃▃ beats 1/12	very hard · avg 0.8%	▇ 2.0%	too hard for it
SimpleQA Verified	55.8% ✎	▁▁▃▂▃▃▆▆█▃▂▅ beats 60/78	very hard · avg 8.0%	▇ 1.8%	at its level

$ where to run it

Through an API

api · Deep Infra · $3.75/M · $2.5 in / $7.5 out per 1M tokens · 1M context · deepinfra.com ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.

$ how the score was worked out · Epoch AI — internal evaluatio… 70%, LMArena leaderboard dataset 17%, Agents' Last Exam — authors'… 4% 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	9	▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 70%	CC BY 4.0
LMArena leaderboard dataset	2	▇▇▇▇▇ 17%	CC BY 4.0
Agents' Last Exam — authors' own fixed-harness model comparison	1	▇ 4%	CC BY 4.0
Legal Research Bench (Vals AI, arXiv:2610.00609v1)	2	▇ 4%	CC-BY-4.0
zai-org/GLM-5.2 model card	1	▇ 3%	mit
EEGAgentBench: Benchmarking LLM Agents on Short- and Long-Horizon EEG Analysis (arXiv:2609.31632v1)	1	▇ 1%	CC BY 4.0
prior · pull toward the middle		▇ 0%
weighted average		= 74.1