Benchmark
Finance Agent
Finance Agent is a benchmark for evaluating AI models on agentic financial analysis tasks, testing their ability to process financial data, perform…
- Modality
- text
- Categories
- reasoning, finance, agents
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 8
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Claude Opus 4.6 | Anthropic | 0.607 | 2026-02-05 | evidence |
| Claude Opus 4.7 | Anthropic | 0.644 | 2026-04-16 | evidence |
| Claude Opus 4.8 | Anthropic | 0.539 | 2026-05-28 | evidence |
| Claude Sonnet 4.6 | Anthropic | 0.633 | 2026-02-17 | evidence |
| Gemini 3.5 Flash | 0.579 | 2026-05-19 | evidence | |
| GPT-5.4 | OpenAI | 0.56 | 2026-03-05 | evidence |
| GPT-5.5 | OpenAI | 0.6 | 2026-04-23 | evidence |
| Nemotron 3 Ultra (550B A55B) | NVIDIA | 0.537 | 2026-06-04 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.