Multimodal Mathematical Reasoning on MathVerse vision-only
61.5AccuracyInternVL3.5-8B
Evaluation Results
| Method | Links | |
|---|---|---|
| InternVL3.5-8BModel Scale=8B, Optimization Method=N/A2026.06 | 61.5 | |
| InternVL3.5-4B (+GNDPO)Model Scale=4B, Optimization Method=GNDPO2026.06 | 53.2 | |
| InternVL3.5-4B (+OPD)Model Scale=4B, Optimization Method=OPD2026.06 | 52.9 | |
| InternVL3.5-4B (+GSPO)Model Scale=4B, Optimization Method=GSPO2026.06 | 52.7 | |
| InternVL3.5-4B (Base (Instruct))Model Scale=4B, Optimization Method=Base (Instruct)2026.06 | 50 | |
| InternVL3.5-2B (+GNDPO)Model Scale=2B, Optimization Method=GNDPO2026.06 | 43.7 | |
| InternVL3.5-2B (+GSPO)Model Scale=2B, Optimization Method=GSPO2026.06 | 43.2 | |
| InternVL3.5-2B (+OPD)Model Scale=2B, Optimization Method=OPD2026.06 | 42 | |
| InternVL3.5-2B (Base (Instruct))Model Scale=2B, Optimization Method=Base (Instruct)2026.06 | 39.6 | |
| InternVL3.5-1B (+GNDPO)Model Scale=1B, Optimization Method=GNDPO2026.06 | 28.4 | |
| InternVL3.5-1B (+OPD)Model Scale=1B, Optimization Method=OPD2026.06 | 28.3 | |
| InternVL3.5-1B (+GSPO)Model Scale=1B, Optimization Method=GSPO2026.06 | 28.2 | |
| InternVL3.5-1B (Base (Instruct))Model Scale=1B, Optimization Method=Base (Instruct)2026.06 | 27 |