Models
|
Benchmarks
|
Organizations
|
Recent Records
|
Sources
|
Documentation
GLM-5.2 on SWE-Marathon
BENCHMARK RECORD: BR-01152-018
Canonical URL: https://www.benchmarkregistry.org/records/BR-01152-018
Benchmark scores may depend on benchmark version, evaluation configuration, model snapshot, and evaluator. Records sharing a benchmark name are not necessarily directly comparable.
Record
Record Identifier BR-01152-018Record Status ACTIVE Created At 2026-07-12T18:30:19.403Z Updated At 2026-07-12T18:30:19.403Z Superseded By Not applicable Model
Official Model Name GLM-5.2 Model Identifier GLM-52Organization Zhipu Model Family GLM Model Number 52 Tier Unknown Model Snapshot Unknown Snapshot Label Unknown Provider Model Identifier UnknownSnapshot Date Unknown Benchmark
Benchmark Family SWE-Marathon Benchmark Version or Variant Unknown Benchmark Version Reference swe-marathon/defaultBenchmark Organization Abundant AI Benchmark Status ACTIVE Result
Metric Overall Score 13.0 Numeric Score 13 Evaluation Date Unknown Reported Date 2026-06-13 Evaluation Context
Configuration Reference Unspecified Shots Unknown Reasoning Mode Unknown Reasoning Effort Unknown Pass Count Unknown Agent Scaffold Unknown Evaluation Harness Unknown Temperature Unknown Top P Unknown Max Output Tokens Unknown System Prompt Description Unknown Additional Configuration None reported Source and Reporting
Primary Source GLM-5.2: Built for Long-Horizon Tasks ↗ Source Type MODEL_CARD Publisher Z.ai (Zhipu) Source Published Date 2026-06-13 Source Accessed At 2026-07-12T18:28:40.622Z Report Type PROVIDER Evaluator Zhipu Evaluator Type MODEL_PROVIDER Provenance
Record Status
This record is ACTIVE . Registry identifiers remain reserved when record status changes.