Question Answering on MTBench Finance
91.3AccuracyTS-Debate
Evaluation Results
| Method | Links | |
|---|---|---|
| TS-Debate2026.01 | 91.3 | |
| Zero-ShotMultimodal Context=true2026.01 | 84.7 | |
| Zero-ShotMultimodal Context=false2026.01 | 82.3 | |
| ByMyEyes2026.01 | 82.3 | |
| CoTMultimodal Context=true2026.01 | 81.7 | |
| CoTMultimodal Context=false2026.01 | 79.7 | |
| VL-Time2026.01 | 77.3 | |
| MADMultimodal Context=false2026.01 | 75 | |
| MADMultimodal Context=true2026.01 | 74.7 |