Benchmark

On-screen text leaderboard

Every model runs the same 40 prompts. A vision model scores each clip blind against the original prompt in a single pass, across visual fidelity, physics and motion, subject consistency, prompt adherence and audio sync. Scores are out of 5, and the 95% CI column shows how much a score could plausibly move on a re-run with this few samples. Full methodology.

Board: Overall · Hands · Faces · Liquids · On-screen text · Multi-shot · Lip-sync · Camera · Animals · Style · Image to video

Clip shown: every model here on the same prompt, “text-neon-sign”, so the preview is a fair comparison, not a cherry-picked best clip.

#	Model	Overall	95% CI	Fidelity	Visual	Physics	Consistency	Audio	Attempts	Gen (s)	$/run	Runs
1	OpenAI Sora 2 discontinued OpenAI	5.00	±0	5.00	5.00	—	5.00	—	1.00	217	—	4
2	Grok Video xAI	5.00	±0	5.00	5.00	—	5.00	—	1.00	85	—	4
3	Seedance 2.0 ByteDance	5.00	±0	5.00	5.00	—	5.00	—	—	248	—	4
4	MiniMax H3 MiniMax	5.00	±0	5.00	5.00	—	5.00	—	—	448	—	4
5	PixVerse v5.5 PixVerse	4.93	±0.21	4.83	4.95	5.00	4.95	—	—	—	—	4
6	Runway Gen-4.5 Runway	4.81	±0.2	4.53	4.85	5.00	4.85	—	—	—	—	4
7	Kling 3.0 Turbo Kuaishou	4.78	±0.61	4.38	4.88	4.75	4.88	5.00	—	—	—	4
8	Kling 3.0 Kuaishou	4.67	±1.06	4.25	4.88	—	4.88	—	1.00	190	—	4
9	Seedance 2.5 ByteDance	4.67	±1.06	4.25	4.88	—	4.88	—	—	233	—	4
10	Google Veo 3.1 Google	4.29	±2.25	4.13	4.50	—	4.25	—	—	131	—	4
11	MiniMax Hailuo 02 MiniMax	3.88	±2.07	3.38	4.25	—	4.00	—	—	300	—	4

Attempts is the average number of generations needed before one was usable, the number that actually decides what a model costs you. 95% CI is computed from that model's own runs on this board, not assumed. On a category board with only 4 runs per model, a wide CI is the honest reflection of a small sample, not a bug. Two models whose CIs overlap are not meaningfully different at this sample size.

Frequently asked

Which AI video model is best at On-screen text right now?

As of 23 September 2026, OpenAI Sora 2 by OpenAI ranks #1 on On-screen text on SlopTV's benchmark, scoring 5.00/5 across 4 scored runs (±0 at 95% confidence).