BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database

Claude Opus 4.8 on DeepSWE

BENCHMARK RECORD: BR-002O48-022

Report record

Canonical URL: https://www.benchmarkregistry.org/records/BR-002O48-022

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-002O48-022
Record Status
ACTIVE
Created At
2026-07-12T17:55:43.644Z
Updated At
2026-07-12T17:55:43.644Z
Superseded By
Not applicable

Model

Official Model Name
Claude Opus 4.8
Model Identifier
ANTHR-O48
Organization
Anthropic
Model Family
Claude
Model Number
48
Tier
O
Model Snapshot
Unknown
Snapshot Label
Unknown
Provider Model Identifier
Unknown
Snapshot Date
Unknown

Benchmark

Benchmark Family
DeepSWE
Benchmark Version or Variant
Unknown
Benchmark Version Reference
deepswe/default
Benchmark Organization
Datacurve
Benchmark Status
ACTIVE

Result

Metric
Resolved
Score
59% ±2%
Numeric Score
59
Evaluation Date
Unknown
Reported Date
Unknown

Evaluation Context

Configuration Reference
CFG-000002
Shots
Unknown
Reasoning Mode
Unknown
Reasoning Effort
max
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
DeepSWE Leaderboard
Source Type
LEADERBOARD
Publisher
DataCurve
Source Published Date
Unknown
Source Accessed At
2026-07-12T17:54:52.430Z
Report Type
BENCHMARK_OWNER
Evaluator
DeepSWE
Evaluator Type
BENCHMARK_OWNER

Provenance

DateEventSourceDetails
2026-07-12T17:55:43.644ZRecord created manuallyDeepSWE Leaderboard—

Record Status

This record is ACTIVE. Registry identifiers remain reserved when record status changes.