Qwen3.7 Max

Tool callingStructured outputReasoning

Website

Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks

Context: 1M
Released: 4mo ago
Input / 1M tokens: $1.48
Output / 1M tokens: $4.43
Cached input / 1M tokens: $0.30
Cache write / 1M tokens: $1.84

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
FrontierMath-Tier-4-v2-Private	34.1% Epoch AI · qwen3.7-max Epoch AI evaluation
FrontierMath-Tiers-1-3-v2-Private	64.6% Epoch AI · qwen3.7-max Epoch AI evaluation
GPQA diamond	90.9% Epoch AI · qwen3.7-max Epoch AI evaluation
OTIS Mock AIME 2024-2025	95.6% Epoch AI · qwen3.7-max Epoch AI evaluation
SimpleQA Verified	55.8% Epoch AI · qwen3.7-max Epoch AI evaluation
SWE-Bench verified	77.3% Epoch AI · qwen3.7-max Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: Qwen
Model family: Qwen
Type: Language model
Predecessor: —
Successor: —
Released: May 21, 2026
Model ID: qwen/qwen3.7-max
Openness: Closed
License: —
Input modalities: text
Output modalities: text
Modality: text->text
Tokenizer: Qwen
Max output tokens: 131K
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: alibaba/qwen3.7-max
Source family: qwen
Last updated: 2026-05-21
Model context: 1M
Model output limit: 66K
Open weights: No
File attachments: No
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Verified	80.4 · resolved	2026-05-19	Source
SWE-Bench Pro	60.6 · resolve rate	2026-05-19	Source
SWE-Bench Multilingual	78.3 · resolve rate	2026-05-19	Source
Terminal-Bench	69.7 · success rate	Terminus-2 · 2.0 · 2026-05-19	Source
GPQA Diamond	92.4 · accuracy	2026-05-19	Source
Humanity's Last Exam	41.4 · accuracy	2026-05-19	Source
SciCode	53.5	2026-05-19	Source
MCP Atlas	76.4 · success rate	2026-05-19	Source
NL2Repo	47.2	Claude Code · 2026-05-19	Source

Complete source record (JSON)

{
  "id": "alibaba/qwen3.7-max",
  "name": "Qwen3.7 Max",
  "description": "Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks",
  "family": "qwen",
  "last_updated": "2026-05-21",
  "attachment": false,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1000000,
    "output": 65536
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Verified",
      "score": 80.4,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "metric": "resolved",
      "date": "2026-05-19"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 60.6,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "metric": "resolve rate",
      "date": "2026-05-19"
    },
    {
      "name": "SWE-Bench Multilingual",
      "score": 78.3,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "metric": "resolve rate",
      "date": "2026-05-19"
    },
    {
      "name": "Terminal-Bench",
      "score": 69.7,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "metric": "success rate",
      "harness": "Terminus-2",
      "version": "2.0",
      "date": "2026-05-19"
    },
    {
      "name": "GPQA Diamond",
      "score": 92.4,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "metric": "accuracy",
      "date": "2026-05-19"
    },
    {
      "name": "Humanity's Last Exam",
      "score": 41.4,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "metric": "accuracy",
      "date": "2026-05-19"
    },
    {
      "name": "SciCode",
      "score": 53.5,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "date": "2026-05-19"
    },
    {
      "name": "MCP Atlas",
      "score": 76.4,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "metric": "success rate",
      "date": "2026-05-19"
    },
    {
      "name": "NL2Repo",
      "score": 47.2,
      "source": "https://qwen.ai/blog?id=qwen3.7",
      "harness": "Claude Code",
      "date": "2026-05-19"
    }
  ],
  "release_date": "2026-05-21",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Alibaba	alibaba	1M	$1.48	$4.43	$0.30	$1.84	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Alibaba	alibaba/us-east-1	1M	$2.00	$6.00	$0.40	—	99.75%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter