Qwen3.7-Plus

Name: Qwen3.7-Plus
Author: Alibaba

Multimodal

Alibaba

Qwen3.7-Plus is Alibaba Cloud Qwen Team's multimodal agent model that unifies vision and language into a single agent foundation.

Key Specifications

Parameters

Context

1.0M

Release Date

May 31, 2026

Average Score

70.3%

API Documentation Results Blog

Timeline

Key dates in the model's history

Announcement

May 31, 2026

Last Update

August 29, 2026

Technical Specifications

Parameters

Training Tokens

Knowledge Cutoff

Family

Capabilities

MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)

$0.32

Output (per 1M tokens)

$1.28

Max Input Tokens

1.0M

Max Output Tokens

65.5K

Supported Features

Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests

SWE-Bench Verified

• Self-reported

77.7%

Reasoning

Logical reasoning and analysis

GPQA

Diamond • Self-reported

90.3%

Other Tests

Specialized benchmarks

AndroidWorld

• Self-reported

81.0%

Apex

• Self-reported

22.7%

BabyVision

With CI • Self-reported

70.4%

BC-VL

With search • Self-reported

51.1%

BFCL-V4

• Self-reported

72.9%

CharXiv-R

With CI • Self-reported

85.9%

Claw-Eval

• Self-reported

62.7%

ClawEval-MM

• Self-reported

55.7%

CountQA

• Self-reported

77.0%

CoWorkBench

• Self-reported

65.1%

CritPT

• Self-reported

6.0%

DeepPlanning

• Self-reported

62.3%

ERQA

• Self-reported

69.8%

Finance Agent v2

• Verified

38.2%

FrontierCode 1.1

FrontierCode 1.1 current leaderboard; mergeability score: 10.2%. • Verified

10.2%

Global PIQA

• Self-reported

90.3%

HiPhO

• Self-reported

84.1%

HMMT Feb 26

• Self-reported

92.9%

Humanity's Last Exam

• Self-reported

34.7%

IFBench

• Self-reported

79.1%

IFEval

• Self-reported

94.6%

IMO-AnswerBench

• Self-reported

86.0%

Include

• Self-reported

83.0%

LingoQA

• Self-reported

83.4%

LiveCodeBench v6

• Self-reported

89.6%

LVBench

• Self-reported

76.2%

MathVision

• Self-reported

90.3%

MAXIFE

• Self-reported

88.8%

MCP Atlas

Public set • Self-reported

73.2%

MCP-Mark

• Self-reported

58.7%

MedXpertQA-MM

• Self-reported

71.0%

MLVU

M-Avg • Self-reported

87.4%

MMBC

With search • Self-reported

46.3%

MMLU-Pro

• Self-reported

88.5%

MMLU-ProX

• Self-reported

85.4%

MMLU-Redux

• Self-reported

94.5%

MMMLU

• Self-reported

89.0%

MMMU-Pro

• Self-reported

79.0%

MMSearch-Plus

With search • Self-reported

41.4%

MRCR v2

128k • Self-reported

91.7%

NL2Repo

• Self-reported

41.1%

NOVA-63

• Self-reported

58.8%

OCRBench_V2

Chinese • Self-reported

67.1%

ODinW

13 datasets • Self-reported

51.1%

OmniDocBench 1.5

• Self-reported

91.4%

OSWorld-Verified

enable_thinking=False • Self-reported

73.3%

PolyMATH

• Self-reported

84.0%

QwenClawBench

• Self-reported

61.8%

QwenWorldBench

• Self-reported

62.1%

RealWorldQA

• Self-reported

86.9%

SciCode

• Self-reported

51.3%

ScreenSpot Pro

enable_thinking=False • Self-reported

79.0%

SimpleVQA

With search • Self-reported

81.7%

SkillsBench

• Self-reported

54.9%

SpreadSheetBench-v1

• Self-reported

86.3%

SuperGPQA

• Self-reported

71.4%

SURDS

• Self-reported

77.2%

SWE-bench Multilingual

• Self-reported

75.8%

SWE-Bench Pro

• Self-reported

57.6%

Terminal-Bench 2.0

Terminus-2 • Self-reported

70.3%

TVBench

• Self-reported

78.2%

Video-MME

With subtitles • Self-reported

88.0%

VideoMMMU

• Self-reported

85.4%

VisFactor

• Self-reported

42.8%

VITA-Bench

• Self-reported

45.6%

VLADBench

• Self-reported

77.2%

WMT24++

• Self-reported

84.6%

WorldVQA

With search • Self-reported

61.1%

License & Metadata

License

proprietary

Announcement Date

May 31, 2026

Last Updated

August 29, 2026

Similar Models

All Models

Qwen3.6 Plus

Alibaba

Released:Mar 2026

Price:$0.50/1M tokens

Qwen3.6-35B-A3B

Alibaba

MM35.0B

Best score:0.9 (GPQA)

Released:Apr 2026

Qwen3.8-27B

Alibaba

MM27.8B

Best score:0.9 (GPQA)

Released:Aug 2026

Qwen3.8 Flash Next

Alibaba

MM180.0B

Best score:0.9 (GPQA)

Released:Aug 2026

Price:$0.16/1M tokens

ERNIE 5.0

Baidu

Best score:0.8 (GPQA)

Released:Jan 2025

Seed 2.0 Pro

ByteDance

Best score:0.9 (GPQA)

Released:Feb 2026

Price:$0.50/1M tokens

Kimi-k1.5

Moonshot AI

Best score:0.9 (MMLU)

Released:Jan 2025

Gemini 3.1 Pro

Google

Best score:0.9 (GPQA)

Released:Feb 2026

Price:$2.50/1M tokens

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.