Slide Editing on TSBench TextEditing
98.28Success Rate (%)TALK-TO-YOUR-SLIDES
Evaluation Results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| TALK-TO-YOUR-SLIDESBackbone=GPT-4.1-mini2025.05 | 98.28 | 2.6 | 3.01 | 3.09 | 3.54 | 3.6 | 58.17 | 3.35 | 1.66 | 3.3 | |
| TALK-TO-YOUR-SLIDESEvaluation Model=Claude 3.5 Haiku2025.05 | 97.71 | 2.55 | 2.95 | 3.04 | 3.49 | 3.54 | 56.1 | 3.28 | 1.62 | 2.9 | |
| Direct code gen.Backbone=GPT-4.1-mini2025.05 | 76.72 | 0 | 0 | 1.04 | 1.04 | 1.04 | 18.55 | 1.03 | 0.41 | 1 | |
| Direct code gen.Evaluation Model=Claude 3.5 Haiku2025.05 | 75.91 | 0 | 0 | 1.02 | 1 | 1.03 | 17.92 | 1.02 | 0.4 | 0.9 | |
| UI AgentBackbone=GPT-4.1-mini2025.05 | 65.48 | 0.48 | 0.67 | 1.58 | 1.48 | 1.56 | 110.84 | 101.48 | 2.1 | 15.9 | |
| UI AgentEvaluation Model=Claude 3.5 Haiku2025.05 | 64.62 | 0.47 | 0.65 | 1.55 | 1.45 | 1.53 | 106.1 | 96.3 | 2.03 | 12.7 |