Vals AI benchmark for realistic financial analyst agent tasks across qualitative analysis, quantitative analysis, market work, comparables, precedents, earnings, disclosure, and modeling.
BenchLM mirrors the public Vals AI Finance Agent v2 leaderboard captured from https://www.vals.ai/benchmarks/fabv2 and updated by Vals on May 28, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.
Finance Agent v2 is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.
BenchLM mirrors the published finance agent v2 score view for Finance Agent v2. Gemini 3.5 Flash leads the public snapshot at 57.9% , followed by Claude Opus 4.8 (53.9%) and GPT-5.5 (51.8%). BenchLM does not use these results to rank models overall.
Gemini 3.5 Flash
google/gemini-3.5-flash
Claude Opus 4.8
Anthropic
anthropic/claude-opus-4-8
GPT-5.5
OpenAI
openai/gpt-5.5
The published Finance Agent v2 snapshot is tightly clustered at the top: Gemini 3.5 Flash sits at 57.9%, while the third row is only 6.1 points behind. The broader top-10 spread is 13.8 points, so the benchmark still separates strong models even when the leaders cluster.
20 models have been evaluated on Finance Agent v2. The benchmark falls in the Agentic category. This category carries a 22% weight in BenchLM.ai's overall scoring system. Finance Agent v2 is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Financial analyst task categories
Format
Mean score across repeated runs
Difficulty
Professional expert-task agent workflow
Vals reports Finance Agent v2 as a multi-category benchmark with severity-weighted partial credit and repeated runs per model. BenchLM mirrors the public Vals leaderboard as a display-only expert-task benchmark.
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.
Vals AI benchmark for realistic financial analyst agent tasks across qualitative analysis, quantitative analysis, market work, comparables, precedents, earnings, disclosure, and modeling.
Gemini 3.5 Flash currently leads the published Finance Agent v2 snapshot with 57.9% finance agent v2 score. BenchLM shows this benchmark for display only and does not use it in overall rankings.
20 AI models are included in BenchLM's mirrored Finance Agent v2 snapshot, based on the public leaderboard captured on May 28, 2026.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.