ResearchBenchmarksClassification on MTBench FinanceClassification on MTBench FinanceFollow54.3AccuracyTS-Debate26.11633.43340.7548.067Jan 27, 2026Evaluation resultsMethodMethodLinksAccuracyTS-Debate2026.0154.3ByMyEyes2026.0144.5Zero-ShotMultimodal Context=trueMultimodal Context=true2026.0137.5CoTMultimodal Context=trueMultimodal Context=true2026.0137MADMultimodal Context=trueMultimodal Context=true2026.0134.7MADMultimodal Context=falseMultimodal Context=false2026.0130VL-Time2026.0130CoTMultimodal Context=falseMultimodal Context=false2026.0127.5Zero-ShotMultimodal Context=falseMultimodal Context=false2026.0127.2