FinRiskAtlas - FinRisk-Ask - Balanced Action Agreement: leaderboard
Metric: BAcc (%). Source: arxiv.org. 33 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3 | 59.46 |
| 2 | Qwen 3 8B | 59.39 |
| 3 | Qwen 3 32B | 58.19 |
| 4 | Qwen3-Next-80B | 56.21 |
| 5 | Claude Opus 4.7 | 56.11 |
| 6 | GPT-5.6 Terra | 56.11 |
| 7 | Ling-2.6-flash | 56.03 |
| 8 | Nemotron 3 Ultra | 55.69 |
| 9 | Kimi K2.5 | 55.68 |
| 10 | GLM-5 | 55.26 |
| 11 | Qwen 3 14B | 54.83 |
| 12 | Qwen 3 4B | 54.68 |
| 13 | GPT-5.6 Luna | 54.21 |
| 14 | GPT-5.6 Sol | 54.05 |
| 15 | Qwen 3 235B A22B | 53.63 |
Interactive version: theaggregate.ai/benchmark?slug=finriskatlas-finrisk-ask-balanced-action-agreement · How It Works · Data refreshed daily, snapshot 2026-09-19.