Models
|
Benchmarks
|
Organizations
|
Recent Records
|
Sources
|
Documentation
Claude Opus 4.8 on OSWorld-Verified
BENCHMARK RECORD: BR-002O48-012
Canonical URL: https://www.benchmarkregistry.org/records/BR-002O48-012
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Identifier BR-002O48-012Record Status ACTIVE Created At 2026-07-12T17:19:47.672Z Updated At 2026-07-12T17:19:47.672Z Superseded By Not applicable
Model
Official Model Name Claude Opus 4.8 Model Identifier ANTHR-O48Organization Anthropic Model Family Claude Model Number 48 Tier O Model Snapshot Unknown Snapshot Label Unknown Provider Model Identifier UnknownSnapshot Date Unknown
Benchmark
Benchmark Family OSWorld-Verified Benchmark Version or Variant Unknown Benchmark Version Reference osworld-verified/defaultBenchmark Organization XLang Lab (University of Hong Kong) Benchmark Status ACTIVE
Result
Metric Overall Score 83.4 Numeric Score 83.4 Evaluation Date Unknown Reported Date 2026-05-28
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 System Card: Claude Opus 4.8 ↗ Source Type SYSTEM_CARD Publisher Anthropic Source Published Date 2026-05-28 Source Accessed At 2026-07-12T17:16:28.964Z Report Type PROVIDER Evaluator Anthropic Evaluator Type MODEL_PROVIDER
Provenance
Record Status
This record is ACTIVE . Registry identifiers remain reserved when record status changes.