Model Profile
google/gemini-3.1-pro-preview
Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.
Identity
ID: external/google/gemini-3-1-pro-preview
Author: google
Origin: external_benchmark_shadow
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 45.7%
Evidence points: 312
Raw rows: 496
Weighted rows: 40
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 0
Price / 1M tokens: $4.50 (blended 3:1)
Intelligence Profile
Dimension Breakdown
No eq benchmarks found
No accuracy benchmarks found
* Low confidence — limited benchmark evidence for this dimension
3/5 dimensions scored · Last updated Apr 21, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
Vals Finance Agent
overall_accuracy_pct
Normalized value 94.3% · confidence 100.0%
Strongest impact in Thesis red teaming
vals_finance_agent.overall_accuracy_pct · Mar 31, 2026
SimpleQA Verified
simpleqa_verified_score_pct
Normalized value 100.0% · confidence 100.0%
Strongest impact in Knowledge base Q&A (fast, no citations)
simpleqa_verified.simpleqa_verified_score_pct · Apr 1, 2026
Vals CorpFin v2
overall_accuracy_pct
Normalized value 89.1% · confidence 100.0%
Strongest impact in Thesis red teaming
vals_corp_fin_v2.overall_accuracy_pct · Mar 31, 2026
FACTS Benchmark Suite
facts_search_score_pct
Normalized value 100.0% · confidence 100.0%
Strongest impact in Knowledge base Q&A (fast, no citations)
facts_benchmark_suite.facts_search_score_pct · Apr 1, 2026
FACTS Benchmark Suite
facts_grounding_score_pct
Normalized value 76.1% · confidence 100.0%
Strongest impact in Knowledge base Q&A (fast, no citations)
facts_benchmark_suite.facts_grounding_score_pct · Apr 1, 2026
FACTS Benchmark Suite
average_score_pct
Normalized value 100.0% · confidence 100.0%
Strongest impact in Knowledge base Q&A (fast, no citations)
facts_benchmark_suite.average_score_pct · Apr 1, 2026
Coverage Diagnostics
actively scoredUse-Case Scores
146
Total Measurements
496
Weighted Measurements
40
Weighted Sources
19
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Thesis red teaming use_case.fin.thesis_red_team | 48.9% |
| Earnings call synthesis use_case.fin.earnings_call_synthesis | 44.1% |
| Transaction anomaly narrative use_case.fin.transaction_anomaly_narrative | 43.3% |
| AML alert triage use_case.fin.aml_alert_triage | 41.5% |
| KYC profile synthesis use_case.fin.kyc_profile_synthesis | 41.5% |
| Accounts payable invoice extraction (text) use_case.fin.ap_invoice_extraction | 38.8% |
| Filings summarization (10-K/10-Q) use_case.fin.filings_summarization | 38.5% |
| Knowledge base Q&A (fast, no citations) use_case.business.kb_qna_fast | 37.8% |
| Literature synthesis with citations use_case.bio.literature_synthesis | 37.7% |
| Cross-paper contradiction analysis use_case.bio.paper_contradictions | 37.7% |
| Component selection assistant use_case.eng.component_selection | 35.5% |
| Runbook step assistant use_case.sre.runbook_steps | 34.1% |