COMPARE.

alibaba

Qwen3.7 Plus

Models

Context window

1,000,000 tokens

Maximum output

64,000 tokens

Open weights

No

Reasoning

Yes

2026-06-02

Document intelligence OmniDocBench 1.5 · 1.5 · reported score#1^* · 91.40^*Platform unreported

ECI 147.8^*General capability index

alibaba

Qwen 3.8 27B

Models

Context window

262,144 tokens^*

Maximum output

32,768 tokens^*

Open weights

Yes^*

Reasoning

Yes^*

2026-08-14

Document intelligence OmniDocBench 1.5 · 1.5 · reported score#2^* · 91.10^*Platform unreported

ECI 152.7^*General capability index

alibaba

Qwen3.6 27B

Models

Context window

262,144 tokens

Maximum output

65,536 tokens

Open weights

Yes

Reasoning

Yes

2026-04-22

Document intelligence OmniDocBench 1.5 · 1.5 · reported score#3^* · 89.40^*Platform unreported

ECI 146.7^*General capability index

meta

Muse Glimmer 30B

Models

Context window

131,072 tokens

Maximum output

131,072 tokens

Open weights

Yes

Reasoning

Yes

2026-08-10

Document intelligence OmniDocBench 1.5 · 1.5 · reported score#4^* · 75.80^*Platform unreported

Radar · unrated0/4 core tests · not enough evidence