Atlas

Models

← All models

Qwen3.7-Max (source unspecified)

Alibaba

This benchmark entry preserves evaluations reported under Qwen3.7-Max or an unversioned provider alias without a verified dated checkpoint. Alibaba documents a text-only May 20 snapshot and a separate June 8 snapshot with visual understanding; the current alias mapping does not establish which artifact a historical evaluation used. Exact release timing, context, and input modalities are left unspecified; reported reasoning controls remain on each run configuration.

Benchmark scores

BenchmarkScore
A-Fantasia46.0
A-Fantasia (Valid Attempts with Retries)46.0
A-Fantasia Backwards Spelling46.0
A-Fantasia Chess16.0
A-Fantasia Chess (Valid Attempts with Retries)16.0
A-Fantasia Cube (Valid Attempts with Retries)76.0
A-Fantasia Cube Rotation76.0
A-Fantasia Spelling (Valid Attempts with Retries)46.0
AA-AnalystAgent (pass@1)48.3
AA-AnalystAgent (pass@5)75.0
AA-AnalystAgent (pass^5)18.8
AA-Briefcase Elo918
AA-Briefcase v1.1 Elo917
AA-LCR69.0
AA-LCR v1.179.0
AA-Omniscience Index13.5
Agents' Last Exam (ALE)11.8
Agents' Last Exam ALE-CLI Pass Rate13.3
Agents' Last Exam ALE-CLI Score34.6
Agents' Last Exam Full-Spectrum Pass Rate10.9
Agents' Last Exam Full-Spectrum Score28.5
Agents' Last Exam Last-Exam Pass Rate0.0
Agents' Last Exam Last-Exam Score6.4
Agents' Last Exam Near-Term Pass Rate17.9
Agents' Last Exam Near-Term Score46.9
Agents' Last Exam Overall Score31.6
Agents' Last Exam Unlicensed Full-Spectrum Pass Rate12.0
Agents' Last Exam Unlicensed Full-Spectrum Score30.4
Agents' Last Exam Unlicensed Last-Exam Pass Rate0.0
Agents' Last Exam Unlicensed Last-Exam Score8.1
Loading Atlas data…