A financial analysis and decision-making benchmark for expert agentic workflows.
BenchLM mirrors the published score view for Finance Agent v2. Gemini 3.5 Flash leads the public snapshot at 57.9%. BenchLM does not use these results to rank models overall.
Year
2026
Tasks
Financial analysis and decision-making
Format
Pass rate
Difficulty
Professional expert-task agent workflow
Google reported Finance Agent v2 in the Gemini 3.5 Flash launch comparison table. BenchLM stores it as a display-only expert-task benchmark until Google publishes the full methodology page.
Version
Finance Agent v2 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
A financial analysis and decision-making benchmark for expert agentic workflows.
Gemini 3.5 Flash by Google currently leads with a score of 57.9% on Finance Agent v2.
1 AI models have been evaluated on Finance Agent v2 on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.