Financial Question Answering on Finance Agent periodic-filing (10-K/10-Q) leaderboard v2
57.9AccuracyGemini 3.5 Flash
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 3.5 FlashCost / query=$2.512026.06 | 57.9 | |
| Claude Fable 5Cost / query=$8.062026.06 | 56.3 | |
| Claude Opus 4.8Cost / query=$4.222026.06 | 53.9 | |
| GPT-5.5Cost / query=$4.152026.06 | 51.8 | |
| MiniMax M3Cost / query=$0.322026.06 | 48.3 |