Multi-digit Multiplication on HDS numerical 1.0 (test)
11.0759Beta 0openai-gpt-5.4
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| openai-gpt-5.4Modality=numerical2026.04 | 11.0759 | -0.1614 | 68.6056 | 0.6405 | |
| openai-gpt-5.4Modality=image-numerical2026.04 | 10.522 | -0.1572 | 66.918 | 0.6212 | |
| x-ai-grok-4.20Modality=numerical2026.04 | 8.1114 | -0.116 | 69.9351 | 0.5236 | |
| openai-gpt-4oModality=numerical2026.04 | 7.4068 | -0.1398 | 52.9859 | 0.632 | |
| qwen-qwen3-vl-235b-a22b-instructModality=numerical2026.04 | 7.011 | -0.0945 | 74.179 | 0.3812 | |
| openai-gpt-4oModality=image-numerical2026.04 | 6.921 | -0.1341 | 51.6105 | 0.6438 | |
| google-gemini-2.5-flashModality=numerical2026.04 | 6.7901 | -0.1271 | 53.4081 | 0.5823 | |
| qwen-qwen3-vl-235b-a22b-instructModality=image-numerical2026.04 | 6.6806 | -0.0889 | 75.1491 | 0.3451 | |
| google-gemini-2.5-flashModality=image-numerical2026.04 | 6.4986 | -0.123 | 52.854 | 0.5785 | |
| qwen-qwen3-vl-30b-a3b-instructModality=image-numerical2026.04 | 5.9858 | -0.1203 | 49.7559 | 0.5364 | |
| qwen-qwen3-vl-30b-a3b-instructModality=numerical2026.04 | 5.9834 | -0.1167 | 51.2903 | 0.556 | |
| x-ai-grok-4.20Modality=image-numerical2026.04 | 5.5582 | -0.0898 | 61.8681 | 0.5078 |