CaST-Bench (Full Set): leaderboard
Multiple-choice answer accuracy in percent on the full CaST-Bench set (2026) of 2,066 six-option video questions over 1,015 videos, where the model first outputs a grounded spatio-temporal causal chain and then answers; chance is 16.7 percent and higher is better.
Metric: Answer accuracy (%) on the multiple-choice questions (chance 16.67), all 2,066 six-option questions over 1,015 videos; every model must first output a grounded spatio-temporal causal chain (evidence segments with per-second boxes) and then answer; native video input except the GPT-5 models, which get 1 fps frames; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 15 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 50.34 | #276 |
| 2 | GPT-5 | 46.32 | #178 |
| 3 | Gemini 2.5 Flash | 45.6 | #463 |
| 4 | Qwen 3 VL 4B Instruct | 45.3 | #1332 |
| 5 | InternVL3.5-30B-A3B | 44.53 | #1267 |
| 6 | InternVL3.5-14B | 43.27 | #1504 |
| 7 | Qwen 3 VL 8B Instruct | 43.13 | #1029 |
| 8 | Qwen 2.5 VL 7B Instruct | 41.09 | #1902 |
| 9 | InternVL3.5-8B | 40.95 | #1604 |
| 10 | GLM-4.1V-9B (Thinking) | 39.55 | |
| 11 | InternVL2.5-8B | 39.55 | #2370 |
| 12 | Qwen 3 VL 8B (Thinking) | 39.16 | #910 |
| 13 | GPT-5 Mini | 37.22 | #364 |
| 14 | MiMo-VL-7B-RL-2508 | 32.24 | #823 |
| 15 | LLaVA-NeXT-Video-34B | 28.17 | #4307 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=cast-bench-full-set · How It Works · Data refreshed daily, snapshot 2026-11-21.