BENCHMARK REGISTRY
Public Artificial Intelligence Benchmark Records Database
Search operators

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

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

SWE-bench: Pro Private Dataset

Benchmark Family
SWE-bench
Version or Variant
Pro Private Dataset
Canonical Reference
swe-bench/pro-private
Release Date
Unknown
Status
ACTIVE

Table may be scrolled horizontally on narrow displays.

Record No. Model Benchmark Metric Score Eval Date Source Model ID
BR-0015-061 GPT-5 SWE-bench Pro Private Dataset Resolved 14.86 ±4.20 Unknown Primary source OPNAI-5
BR-00152-055 GPT-5.2 SWE-bench Pro Private Dataset Resolved 23.81 ±5.09 Unknown Primary source OPNAI-52
BR-00154-052 GPT-5.4 SWE-bench Pro Private Dataset Resolved 43.40 ±6.03 Unknown Primary source OPNAI-54
BR-002O41-012 Claude 4.1 Opus SWE-bench Pro Private Dataset Resolved 17.75 ±4.51 Unknown Primary source ANTHR-O41
BR-002O45-038 Claude Opus 4.5 SWE-bench Pro Private Dataset Resolved 23.44 ±5.07 Unknown Primary source ANTHR-O45
BR-002O46-036 Claude Opus 4.6 SWE-bench Pro Private Dataset Resolved 47.10 ±6.07 Unknown Primary source ANTHR-O46
BR-002S4-037 Claude 4 Sonnet SWE-bench Pro Private Dataset Resolved 9.06 ±3.39 Unknown Primary source ANTHR-S4
BR-00325P-027 Gemini 2.5 Pro SWE-bench Pro Private Dataset Resolved 10.14 ±3.56 Unknown Primary source GOOGL-G25P
BR-00330P-009 Gemini 3 Pro SWE-bench Pro Private Dataset Resolved 17.95 ±4.78 Unknown Primary source GOOGL-G30P
BR-00331P-025 Gemini 3.1 Pro SWE-bench Pro Private Dataset Resolved 32.20 ±5.69 Unknown Primary source GOOGL-G31P
BR-009MS11-005 Muse Spark 1.1 SWE-bench Pro Private Dataset Resolved 51.50 ±5.50 Unknown Primary source META-MS11
BR-009MUSESPARK-017 Muse Spark SWE-bench Pro Private Dataset Resolved 44.70 ±6.05 Unknown Primary source META-MUSESPARK