Search operators

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

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

Gemini 3 Flash on SWE-bench Pro Public Dataset

BENCHMARK RECORD: BR-00330F-009

Report record

Canonical URL: https://www.benchmarkregistry.org/records/BR-00330F-009

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-00330F-009
Record Status
ACTIVE
Created At
2026-07-13T13:16:10.160Z
Updated At
2026-07-13T13:16:10.160Z
Superseded By
Not applicable

Model

Official Model Name
Gemini 3 Flash
Model Identifier
GOOGL-G30F
Organization
Google
Model Family
Gemini
Model Number
30
Tier
F
Model Snapshot
Unknown
Snapshot Label
Unknown
Provider Model Identifier
Unknown
Snapshot Date
Unknown

Benchmark

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

Result

Metric
Resolved
Score
34.63 ±3.55
Numeric Score
34.63
Evaluation Date
Unknown
Reported Date
2026-01-12

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
SWE-Bench Pro (Public Dataset)
Source Type
LEADERBOARD
Publisher
Scale AI
Source Published Date
Unknown
Source Accessed At
2026-07-13T12:57:10.168Z
Report Type
INDEPENDENT
Evaluator
Scale AI
Evaluator Type
INDEPENDENT_ORGANIZATION

Provenance

DateEventSourceDetails
2026-07-13T13:16:10.160ZRecord created manuallySWE-Bench Pro (Public Dataset)

Record Status

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