V-Benchmark v2.0 comparison

LTX 2.3 22B vs P-Video 2

By Megaton TeamSeptember 14, 2026

P-Video 2 leads this comparison on the published overall score.

Share
LTX 2.3 22B evaluation example
LTX 2.3 22B
P-Video 2 evaluation example
P-Video 2
Our verdict

P-Video 2 leads

P-Video 2 leads this comparison on the published overall score.

Lightricks

Lightricks

LTX 2.3 22B

51.8Overall score
Rank
#16
Price per minute
$2.13/min
Pruna AI

Pruna AI

P-Video 2

65.9Overall score
Rank
#13
Price per minute
$1.50/min

Best for

Highest overall score

P-Video 2

P-Video 2 leads the overall score by 14.1 points.

The overall score does not measure file reliability.

Best for

More readable text

P-Video 2

P-Video 2 leads by 9.0 points.

Long or moving text still needs manual review.

Best for

Lower generation cost

P-Video 2

P-Video 2 runs $1.50/min, against $2.13/min for LTX 2.3 22B.

Provider prices can change.

Best for

Built-in audio

LTX 2.3 22B

LTX 2.3 22B generates audio with the video; P-Video 2 does not.

This comparison does not score audio quality.

0
videos rated
0
measurements
0
ratings
September 14, 2026
last updated

Reviewer scores

Scores by category

P-Video 2 wins 12 of 13 categories head-to-head. Each bar is the reviewer score out of 100.

Biggest gapHuman: P-Video 2 ahead by 30.4 points.
Closest categoryPrompt Adherence: LTX 2.3 22B ahead by 0.1 points.

Head-to-head scores

13 categories rated head-to-head

LTX 2.3 22BP-Video 2
Physics
40.0
58.2
Prompt Adherence
73.1
73.0
Logic Consistency
46.4
62.7
Scene Consistency
64.0
80.2
Cinematography
58.6
78.6
Taste
42.0
62.2
2D Animation
33.3
38.3
3D Animation
42.5
62.5
Human
50.7
81.1
Actor Performance
41.0
71.0
Objects
48.3
59.8
Animals
44.3
67.1
Text Fidelity
11.6
20.6

Capabilities

Inputs and outputs

CapabilityLTX 2.3 22BP-Video 2
Text inputYesUnlisted
Image inputYesUnlisted
Video inputYesUnlisted
Audio inputYesUnlisted
Image outputNoUnlisted
Audio outputYesUnlisted

FAQ

Common questions

Is LTX 2.3 22B better than P-Video 2?

Not on our scores — P-Video 2 edges ahead overall, 65.9 to 51.8, winning 12 of 13 rated categories. LTX 2.3 22B still leads in a few areas the category scores make clear.

Is LTX 2.3 22B cheaper than P-Video 2?

No — P-Video 2 is the cheaper option at $1.50/min, versus $2.13/min for LTX 2.3 22B.

Does LTX 2.3 22B generate audio?

Yes — LTX 2.3 22B generates audio together with the video, in the same file.

Does P-Video 2 generate audio?

We haven't confirmed native audio output for P-Video 2 yet.

Is LTX 2.3 22B or P-Video 2 better for human?

P-Video 2 leads human, by 30.4 points.

Is LTX 2.3 22B or P-Video 2 better for actor performance?

P-Video 2 leads actor performance, by 30.0 points.

Is LTX 2.3 22B or P-Video 2 better for animals?

P-Video 2 leads animals, by 22.9 points.

Is LTX 2.3 22B or P-Video 2 better for taste?

P-Video 2 leads taste, by 20.2 points.

Is LTX 2.3 22B or P-Video 2 better for 3d animation?

P-Video 2 leads 3d animation, by 20.0 points.

Is LTX 2.3 22B or P-Video 2 better for cinematography?

P-Video 2 leads cinematography, by 20.0 points.

Is LTX 2.3 22B or P-Video 2 better for physics?

P-Video 2 leads physics, by 18.2 points.

Is LTX 2.3 22B or P-Video 2 better for logic consistency?

P-Video 2 leads logic consistency, by 16.4 points.

Is LTX 2.3 22B or P-Video 2 better for scene consistency?

P-Video 2 leads scene consistency, by 16.2 points.

Is LTX 2.3 22B or P-Video 2 better for objects?

P-Video 2 leads objects, by 11.5 points.

How are LTX 2.3 22B and P-Video 2 tested?

Both models run the same prompts. Professional reviewers score each video 0–100 on how well it follows the prompt and handles motion, people, objects, animation, and text, while automated checks flag freezes, bad framing, and unstable motion. This matchup draws on 0 rated videos and 0 reviewer ratings.

More comparisons

More AI video model comparisons

Browse more head-to-head results, including scores, prices, and side-by-side video tests.

Other AI video model comparison pages
ComparisonProvidersOverall scores
P-Video 2 vs Seedance 2.5Pruna AIByteDance66.0 / 87.0
P-Video 2 vs Wan 3.0Pruna AIAlibaba66.0 / 82.0
P-Video 2 vs Seedance 2.0Pruna AIByteDance66.0 / 78.0
FLUX 3 vs P-Video 2Black Forest LabsPruna AI77.0 / 66.0
LTX 2.3 22B vs Seedance 2.5LightricksByteDance52.0 / 87.0
Gemini Omni 1.1 Flash vs P-Video 2GooglePruna AI76.0 / 66.0
LTX 2.3 22B vs Wan 3.0LightricksAlibaba52.0 / 82.0
Kling 3 Pro vs P-Video 2Kling AI (Kuaishou)Pruna AI76.0 / 66.0
LTX 2.3 22B vs Seedance 2.0LightricksByteDance52.0 / 78.0
FLUX 3 vs LTX 2.3 22BBlack Forest LabsLightricks77.0 / 52.0
MiniMax Hailuo 03 vs P-Video 2MiniMaxPruna AI75.0 / 66.0
Gemini Omni 1.1 Flash vs LTX 2.3 22BGoogleLightricks76.0 / 52.0
MiniMax H3 Max vs P-Video 2fal.aiPruna AI75.0 / 66.0
H3 Max Turbo vs P-Video 2MiniMaxPruna AI73.0 / 66.0
Kling 3 Pro vs LTX 2.3 22BKling AI (Kuaishou)Lightricks76.0 / 52.0
Gemini Omni Flash vs P-Video 2GooglePruna AI70.0 / 66.0
LTX 2.3 22B vs MiniMax Hailuo 03LightricksMiniMax52.0 / 75.0
Kling 3 Standard vs P-Video 2Kling AI (Kuaishou)Pruna AI69.0 / 66.0
MiniMax H3 Max vs LTX 2.3 22Bfal.aiLightricks75.0 / 52.0
H3 Max Turbo vs LTX 2.3 22BMiniMaxLightricks73.0 / 52.0
P-Video 2 vs Seedance 2.0 MiniPruna AIByteDance66.0 / 69.0
Gemini Omni Flash vs LTX 2.3 22BGoogleLightricks70.0 / 52.0
Kling 3 Standard vs LTX 2.3 22BKling AI (Kuaishou)Lightricks69.0 / 52.0
P-Video 2 vs Veo 3.1Pruna AIGoogle66.0 / 62.0
LTX 2.3 22B vs Seedance 2.0 MiniLightricksByteDance52.0 / 69.0
P-Video 2 vs Gen-4.5Pruna AIRunway66.0 / 61.0
LTX 2.3 22B vs Veo 3.1LightricksGoogle52.0 / 62.0
LTX 2.3 22B vs Gen-4.5LightricksRunway52.0 / 61.0
Seedance 2.5 vs Wan 3.0ByteDanceAlibaba87.0 / 82.0
Seedance 2.0 vs Seedance 2.5ByteDanceByteDance78.0 / 87.0
FLUX 3 vs Seedance 2.5Black Forest LabsByteDance77.0 / 87.0
Seedance 2.0 vs Wan 3.0ByteDanceAlibaba78.0 / 82.0

Methodology

How we tested LTX 2.3 22B and P-Video 2

We score two things separately: how good the video looks to a reviewer, and how reliably the file itself holds up. A model can make great-looking footage and still deliver clips with freezes, bad framing, or unstable motion.

We test every model with v-benchmark v2.0, our benchmark for AI video models — the same prompts, professional reviewers, and automated reliability checks behind every score here.

Reviewer scores
Both models receive the same prompts. Professional reviewers score how well each video follows the prompt and handles motion, composition, people, objects, animals, animation, and on-screen text. Scores use a 0-100 scale.
File reliability
Automated checks review 0 clips for freezes, bad framing, compression problems, unstable motion, distorted geometry, exposure problems, and invalid file properties.
Missing scores
Categories with a score for only one model are shown but excluded from the head-to-head win count. Price and generation speed stay separate because they use different units.
Last updated
Reviewer scores and rankings use results from September 14, 2026. Reliability results use the latest completed test for each model. Provider prices and rankings can change.