Financial research and reasoning on Vals.ai Financial Agent 1.1
62.3ScoreDS-v4-Pro
Evaluation Results
| Method | Links | |
|---|---|---|
| DS-v4-ProWeb search usage=with web search, Parameter Count=1.6T-A49B2026.06 | 62.3 | |
| Qwen-3.5Web search usage=without web search, Parameter Count=397B-17B2026.06 | 61.3 | |
| GLM-5.1Web search usage=with web search, Parameter Count=744B-A40B2026.06 | 60.7 | |
| GLM-5.1Web search usage=without web search, Parameter Count=744B-A40B2026.06 | 60.2 | |
| Nemotron 3 UltraWeb search usage=without web search, Parameter Count=550B-A55B2026.06 | 60.1 | |
| DS-v4-FlashWeb search usage=with web search, Parameter Count=284B-A13B2026.06 | 60.1 | |
| Qwen-3.5Web search usage=with web search, Parameter Count=397B-17B2026.06 | 59 | |
| DS-v4-ProWeb search usage=without web search, Parameter Count=1.6T-A49B2026.06 | 58.9 | |
| Kimi-K2.6Web search usage=with web search, Parameter Count=1T-A32B2026.06 | 58.8 | |
| DS-v4-FlashWeb search usage=without web search, Parameter Count=284B-A13B2026.06 | 58.4 | |
| Kimi-K2.6Web search usage=without web search, Parameter Count=1T-A32B2026.06 | 54 | |
| Nemotron 3 UltraWeb search usage=with web search, Parameter Count=550B-A55B2026.06 | 53.7 | |
| MiniMax-2.7Web search usage=without web search, Parameter Count=230B-A10B2026.06 | 51.3 | |
| MiniMax-2.7Web search usage=with web search, Parameter Count=230B-A10B2026.06 | 50.5 |