Search operators

brand: benchmark: record: model: metric: date: org:

Separate values with commas, or alternatives with uppercase OR. Example: brand:Meta, Anthropic benchmark:GPQA

Claude Opus 4.6 on SWE-bench Pro Private Dataset

BENCHMARK RECORD: BR-002O46-040

Report record

Canonical URL: https://www.benchmarkregistry.org/records/BR-002O46-040

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-002O46-040
Record Status
WITHDRAWN
Created At
2026-07-13T13:20:30.723Z
Updated At
2026-07-13T13:24:25.131Z
Superseded By
Not applicable

Model

Official Model Name
Claude Opus 4.6
Model Identifier
ANTHR-O46
Organization
Anthropic
Model Family
Claude
Model Number
46
Tier
O
Model Snapshot
Unknown
Snapshot Label
Unknown
Provider Model Identifier
Unknown
Snapshot Date
Unknown

Benchmark

Benchmark Family
SWE-bench
Benchmark Version or Variant
Pro Private Dataset
Benchmark Version Reference
swe-bench/pro-private
Benchmark Organization
Princeton University
Benchmark Status
ACTIVE

Result

Metric
Resolved
Score
47.10 ±6.07
Numeric Score
47.1
Evaluation Date
Unknown
Reported Date
2026-04-08

Evaluation Context

Configuration Reference
CFG-000041
Shots
Unknown
Reasoning Mode
reasoning
Reasoning Effort
Unknown
Pass Count
Unknown
Agent Scaffold
Unknown
Evaluation Harness
mini-swe-agent
Temperature
Unknown
Top P
Unknown
Max Output Tokens
Unknown
System Prompt Description
Unknown
Additional Configuration
None reported

Source and Reporting

Primary Source
SWE-Bench Pro (Private Dataset)
Source Type
LEADERBOARD
Publisher
Scale AI
Source Published Date
Unknown
Source Accessed At
2026-07-13T12:57:12.424Z
Report Type
INDEPENDENT
Evaluator
Scale AI
Evaluator Type
INDEPENDENT_ORGANIZATION

Provenance

DateEventSourceDetails
2026-07-13T13:20:30.723ZRecord created manuallySWE-Bench Pro (Private Dataset)
2026-07-13T13:24:25.083ZRecord withdrawn

Record Status

This record is WITHDRAWN.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