Object Detection on Colon-Bench (272 videos)
50.9PrecisionGemini 3 Flash
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| Gemini 3 Flash2026.03 | 50.9 | 52.7 | 51.8 | 32.6 | 17 | 79.8 | |
| Gemini 3 Pro2026.03 | 42.2 | 42.5 | 42.3 | 23.7 | 11.1 | 76.3 | |
| Qwen-VL Max2026.03 | 39 | 22.2 | 28.3 | 10.6 | 3.8 | 71.4 | |
| Gemini 3.1 Flash Lite2026.03 | 36.8 | 32.5 | 34.5 | 18.1 | 6 | 69.9 | |
| GPT-5.42026.03 | 33.2 | 30.6 | 31.9 | 17.9 | 5.9 | 68.4 | |
| GPT-5.22026.03 | 26.1 | 24.2 | 25.1 | 12.2 | 3.3 | 66.1 | |
| Qwen3-VL 235B2026.03 | 15.7 | 8.2 | 10.8 | 2 | 0.5 | 62.9 | |
| Qwen3-VL 32B2026.03 | 14.4 | 7.6 | 9.9 | 1.5 | 0.4 | 62.1 | |
| Qwen3.5 Plus2026.03 | 10.7 | 10.3 | 10.5 | 2.1 | 0.4 | 61.5 | |
| Seed 1.62026.03 | 10.4 | 6.6 | 8 | 1.1 | 0.2 | 59.7 | |
| Qwen3-VL Plus2026.03 | 10 | 12.7 | 11.2 | 2.9 | 0.7 | 64 | |
| Qwen3.5 397B2026.03 | 9.4 | 8.9 | 9.2 | 1.7 | 0.4 | 62.9 | |
| Qwen3-VL 8B2026.03 | 6.6 | 3.8 | 4.8 | 0.7 | 0.2 | 62.6 | |
| GLM-4.6V2026.03 | 6.6 | 6.2 | 6.4 | 0.5 | 0.1 | 61.6 | |
| Claude Opus 4.62026.03 | 3.5 | 3.7 | 3.6 | 1.1 | 0.1 | 59.5 | |
| Gemini 2.5 Flash Lite2026.03 | 2.5 | 9.5 | 3.9 | 1.7 | 0.4 | 61.8 | |
| Seed 1.6 Flash2026.03 | 1.6 | 0.5 | 0.8 | 0 | 0 | 55.7 | |
| GPT-4o2026.03 | 0.6 | 0.1 | 0.2 | 0 | 0 | 55.4 | |
| Molmo 2-8B2026.03 | 0.2 | 0.1 | 0.1 | 0 | 0 | 53.2 |