VENICE ATLAS · MODEL DOSSIER · QWEN 3.7 MAX

Model overview

Qwen 3.7 Max

Name: Qwen 3.7 Max
Brand: venice.ai
Price: 2.7000 USD
Availability: InStock

Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.

qwen-3-7-max · venice.ai

Text · Venice catalog$2.70 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$2.70 per 1M tokensper 1M tokens

Context window1MMax tokens

Benchmarks42Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Biology#837.15 rating Chat#327.41 rating Chemistry#440.43 rating Coding#2234.96 rating Economics#128.47 rating Finance#140.90 rating Frontend Development#928.11 rating General intelligence#3145.19 rating Healthcare#144.82 rating Instruction Following#330.06 rating Language#141.57 rating Legal#144.48 rating Math#342.86 rating Physics#341.08 rating Productivity#117.69 rating Reasoning#2645.95 rating Spatial Reasoning#1525.11 rating Structured Output#627.41 rating Tool Calling#2226.65 rating

Agents8 results

CoWorkBenchcoworkbench · agents

67.2%

ReportedOct 2026

Finance Agent v2finance-agent-v2 · agents

48.4%

ReportedOct 2026

Kernel Bench L3kernel-bench-l3 · agents

96.0%

ReportedOct 2026

MCP-Markmcp-mark · agents

60.8%

ReportedOct 2026

QwenSVGqwen-svg · agents

80.4%

ReportedOct 2026

QwenWorldBenchqwenworldbench · agents

57.3%

ReportedOct 2026

SpreadSheetBench-v1spreadsheetbench-v1 · agents

87.0%

ReportedOct 2026

VITA-Benchvita-bench · agents

47.9%

ReportedOct 2026

Chat1 result

IFEvalifeval · chat

94.3%

ReportedOct 2026

Coding5 results

Claw-Evalclaw-eval · code

65.2%

ReportedOct 2026

NL2Reponl2repo · code

47.2%

ReportedOct 2026

QwenWebBenchqwenwebbench · code

78.4%

ReportedOct 2026

SkillsBenchskillsbench · code

59.2%

ReportedOct 2026

ZClawBenchzclawbench · code

64.3%

ReportedOct 2026

General intelligence3 results

Includeinclude · general

86.2%

ReportedOct 2026

MAXIFEmaxife · general

89.2%

ReportedOct 2026

NOVA-63nova-63 · general

59.0%

ReportedOct 2026

Instruction Following1 result

IFBenchifbench · instruction_following

79.1%

ReportedOct 2026

Language5 results

MMLU-Prommlu-pro · language

89.6%

ReportedOct 2026

MMLU-ProXmmlu-prox · language

87.0%

ReportedOct 2026

MMLU-Reduxmmlu-redux · language

95.0%

ReportedOct 2026

MMMLUmmmlu · language

90.3%

ReportedOct 2026

WMT24++wmt24++ · language

85.8%

ReportedOct 2026

Long Context1 result

MRCR 128K (8-needle)mrcr-128k-(8-needle) · long_context

90.4%

ReportedOct 2026

Math5 results

HMMT Feb 26hmmt-feb-26 · math

97.1%

ReportedOct 2026

IMO-AnswerBenchimo-answerbench · math

90.0%

ReportedOct 2026

LiveBenchlivebench · math

74.3%

ReportedOct 2026

MathArena Apexmatharena-apex · math

44.5%

ReportedOct 2026

PolyMATHpolymath · math

86.5%

ReportedOct 2026

Reasoning1 result

CritPTcritpt · reasoning

11.4%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $2.70
Output price per 1M tokens: $8.05
Cache read price per 1M tokens: $0.27
Cache write price per 1M tokens: $3.35
Blended price per 1M tokens (50/50): $5.38

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionVideo inputWeb search

Endpoint metadata

Privacy: anonymized
Quantization: not-available
Maximum completion tokens: 66K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Max Images: 10
Quantization: not-available
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: No
Optimized For Code: Yes
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: Yes
Supports Multiple Images: Yes
Supports Response Schema: No
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: No

Related models

Qwen 3.7 Max

Benchmark results

More from qwen