Short-form Question Answering on TQA (TriviaQA) (test)
68.4F1 ScoreAGAR
Evaluation Results
| Method | Links | |
|---|---|---|
| AGARBackbone=InternVL3.5-8B2026.06 | 68.4 | |
| AGARBackbone=GLM-4.1V-9B-Thinking2026.06 | 68.1 | |
| VARBackbone=GLM-4.1V-9B-Thinking2026.06 | 67.6 | |
| CGRBackbone=GLM-4.1V-9B-Thinking2026.06 | 67.4 | |
| AGLABackbone=GLM-4.1V-9B-Thinking2026.06 | 67.2 | |
| UniformBackbone=InternVL3.5-8B2026.06 | 67.1 | |
| Plain VQABackbone=InternVL3.5-8B2026.06 | 66.5 | |
| RandomBackbone=InternVL3.5-8B2026.06 | 66.4 | |
| VEA-BrBackbone=GLM-4.1V-9B-Thinking2026.06 | 66.4 | |
| UniformBackbone=GLM-4.1V-9B-Thinking2026.06 | 65.7 | |
| VEA-ConBackbone=InternVL3.5-8B2026.06 | 65.3 | |
| RandomBackbone=GLM-4.1V-9B-Thinking2026.06 | 65.3 | |
| VEA-ConBackbone=GLM-4.1V-9B-Thinking2026.06 | 65.2 | |
| Plain VQABackbone=GLM-4.1V-9B-Thinking2026.06 | 65.1 | |
| VEA-BrBackbone=InternVL3.5-8B2026.06 | 62.8 | |
| AGLABackbone=InternVL3.5-8B2026.06 | 61.7 | |
| VARBackbone=InternVL3.5-8B2026.06 | 59.5 | |
| CGRBackbone=InternVL3.5-8B2026.06 | 35 |