Capability
Interactive Agent Reasoning
Score
0.4/100
- Confidence
- 65%
- Evidence records
- 1
Versioned model-family evidence
Evidence preview · noindex
Gemini 3.1 Pro
This profile exposes only reviewed identity, configuration and score facts from the current release. It does not yet contain approved model-specific prose.
- Provider
- Not release-pinned
- Lifecycle
- Active
- Priority
- Core
- Profile metadata
- Release-pinned fields only
Current immutable release
Scores, confidence and missing coverage
A precise 0–100 score is shown only where reviewed evidence supports one. Confidence describes evidence strength separately; an insufficient-evidence row is not a zero.
Capability
Structured Output Reliability
Score
86.944535/100
- Confidence
- 65%
- Evidence records
- 1
Score
Insufficient evidence
- Confidence
- 0%
- Evidence records
- 0
Task
Structured Output
Score
Insufficient evidence
- Confidence
- 0%
- Evidence records
- 0
Identity and provenance
Reviewed configurations
gemini-3-1-pro-preview
Configuration configuration-gemini-3-1-pro-preview-preview · Representative
Reviewed 8 Aug 2026
Selected the highest reviewed, published ARC-AGI-3 RHAE observation for this source family; equal scores resolve by configuration slug ascending.
6112583259b4a37b076acd644e13c4ec0d4120c24ece1c7c197f744bfe674ca1
gemini-3.1-pro
Configuration configuration-sob-cf45c94b7cd67d79d8a525df9ce490e231fb440cf506123c2738d0c5dd70ba7c · Evidence
Reviewed 8 Aug 2026
Selected the exact reviewed product-family configuration from the pinned SOB release.
cf45c94b7cd67d79d8a525df9ce490e231fb440cf506123c2738d0c5dd70ba7c
Traceable inputs
Evidence references
arc-agi-3-official-verified
ARC-AGI-3
Metric: arc-agi-3-rhae
sob-v1
Structured Output Benchmark
Metric: sob-overall