Kuaishou
Kling 4.0
Kling 4.0 from Kuaishou scores 4.76 out of 5 on our full 40-prompt battery, level with Sora 2 for eighth of 16 and below Kling 3.0 Turbo, with a full 360-degree orbit in one take and perfect multi-shot sequences, but it cuts to new angles in half of the prompts that ask for a single take.
- Best category
- Multi-shot 5.00
- Weakest category
- Liquids 4.29
- Clips scored
- 40
At a glance
Strengths
- A full 360-degree orbit in one take: front, profile, back, the other profile and front again, with the subject unchanged. Half the board stops short on this test.
- Multi-shot at 5.00: the cafe in three shots, the man in the yellow jacket, the watch and the bench from midday to dusk keep the same subject and place.
- Image-to-video at 5.00 on all four tests, including a product turn of about 180 degrees as asked.
- Every clip comes with audio, and three of the four lip-sync lines are word for word.
Watch-outs
- It edits when nobody asked: 16 of the 32 one-shot text-to-video prompts cut to other angles, from a single cut to five shots in 8 seconds.
- The direct-to-camera line comes out as "We test the flop", heard that way by two separate transcriptions.
- The ice cube does not melt, the crane starts at rooftop height, and the cat jumps from a worktop instead of the floor.
- No public price yet: Kuaishou has not published a rate for Kling 4.0.
Sequences of shots, orbit and other complex camera moves, and animating a still image. For one continuous take, check that it did not cut.
Capabilities
- Native audio
- Yes
- Multi-shot sequences
- No
- Image to video
- Yes
- Public API
- No
- Max resolution
- 1080p
- Max duration
- 30s
Benchmark scores
How we test →| Dimension | Score | |
|---|---|---|
| Overall | 4.76 / 5 | |
| Prompt fidelity | 4.60 | |
| Visual quality | 4.86 | |
| Physics & motion | 4.59 | |
| Subject consistency | 5.00 | |
| Audio & sync | 4.75 |
- Scored runs
- 40
| Prompt category | Score | Runs | |
|---|---|---|---|
| Multi-shot | 5.00 | 4 | |
| Image to video | 5.00 | 4 | |
| Faces | 4.92 | 4 | |
| Style | 4.88 | 4 | |
| On-screen text | 4.83 | 4 | |
| Camera | 4.75 | 4 | |
| Lip-sync | 4.75 | 4 | |
| Animals | 4.58 | 4 | |
| Hands | 4.58 | 4 | |
| Animation | 4.53 | 4 | |
| Liquids | 4.29 | 4 |
Scores out of 5, judged blind. Bars start at 3.0 so the gaps are visible.
Cite this
Free to cite and reuse with a link back. Data is updated as new runs and prices come in, so include the date.
SlopTV. (2026). Kling 4.0 benchmark results. Retrieved October 23, 2026, from https://sloptv.co/model/kling-4-0<a href="https://sloptv.co/model/kling-4-0">Kling 4.0 benchmark results</a> (SlopTV)The clips
Every score above links to the actual generation it came from. Nothing here is a mockup.
Hands avg 4.58/5
Chopping a pepper
Clean slices that stay where they fall, with two hands and five fingers each; a cut at about 5.5 seconds moves to a wider view. Checked frame by frame.
Counting fingers
Five digits throughout, checked frame by frame, but the four fingers straighten together once the fist loosens instead of rising one by one.
Fretting a guitar chord
Fingertips press the strings with five fingers throughout, but the clip cuts to a new angle about every 2 seconds. Checked frame by frame.
Tying shoelaces
Five fingers on both hands and a finished bow at the end, but the clip cuts to a closer angle at about 5 seconds. Checked frame by frame.
Faces avg 4.92/5
Face in a crowd
The man stays still and sharp, but the crowd behind him is in focus rather than blurred. Checked frame by frame.
Elderly portrait, slow blink
Deep wrinkles under hard side light and one slow, complete blink.
Glasses reflection
Round glasses carry a bright window reflection that moves with the slight head motion.
Turn and smile
Turns from profile to camera and breaks into a smile, with the same face through the turn.
Liquids avg 4.29/5
Pouring coffee
Continuous pour with a rising level and backlit steam, shown as three shots (side, top-down, steam) rather than one take. Cuts measured with ffmpeg.
Honey drizzle
Viscous coiling honey that pools and spreads over the pancakes, cut into five short shots. Cuts measured with ffmpeg.
Ice melting in whisky
Condensation builds and a drop runs down the glass, but the cube keeps its size across four shots, the last from above. Verified frame by frame.
Wave on rocks
Heavy spray and foam on dark rocks with runoff in the crevices, split into three shots. Cuts measured with ffmpeg.
On-screen text avg 4.83/5
Book chapter heading
"CHAPTER ONE" is spelled correctly and stays stable during the push-in. The body text on the page is pseudo-text.
Neon sign OPEN 24H
"OPEN 24H" reads correctly in every shot and the sign flickers on a wet street, but the clip cuts to a puddle reflection and back.
Bakery sign
"FRESH BREAD DAILY" reads correctly from every angle, but the shopfront is shown in four shots instead of one. Cuts measured with ffmpeg.
Printed t-shirt
"SLOP" stays legible on the t-shirt as the person walks toward the camera. Shop awnings behind carry pseudo-text.
Multi-shot avg 5/5
Cafe, three shots
Three shots in the asked order, wide, medium, then hands around the cup, with cuts at about 2.9 and 5.8 seconds and the same woman, red coat and cafe. Checked frame by frame.
Same bench, day and dusk
The light moves from midday sun to dusk on the same bench with identical framing. Checked frame by frame.
Watch, wide then macro
Wide on the stand, then a macro of the same watch after a cut at about 4 seconds, with matching dial, hands and date window.
Alley, two angles
From behind down the alley, then front-on after a cut at 3 seconds, same man, same yellow jacket. Checked frame by frame.
Lip-sync avg 4.75/5
Bearded man, long line
Audio says the exact line, transcribed word for word, and the bearded jaw moves with it without warping.
Direct address to camera
The lips follow the audio, but the line comes out as "We test the flop", heard that way by two separate transcriptions; the clip also cuts from a medium shot to a close-up at 1.25 seconds.
Sung line
Sings "hold on to me" twice, confirmed in the audio, with sustained vowels; the clip cuts to a close-up of the mouth and back. Checked frame by frame.
Two-person exchange
The man asks and the woman answers, both lines transcribed word for word, with shot and reverse shot and the listener silent.
Camera avg 4.75/5
Crane to skyline
Golden-hour skyline, but the camera starts at rooftop height and mostly pushes forward instead of rising from the street. Verified frame by frame.
Dolly in to a door
Steady push-in down a dim hallway toward a door that stays closed.
Handheld follow
Handheld camera tracks alongside and then behind the running child through tall grass.
360 orbit
A full turn in one take: front, profile, back, the other profile and front again, with the woman and her book unchanged. Verified frame by frame.
Animals avg 4.58/5
Pigeon takeoff
Clean take-off with wings fully extended, followed by a cut at about 4 seconds to a wider shot of the bird in flight. Checked frame by frame.
Cat jumping to a counter
One leap onto the white counter, but the cat takes off from a wooden worktop, not the floor. Verified frame by frame.
Dog shaking off water
Whole-body shake with droplets flying outward, after a cut at about 2.5 seconds from a close shot to a wider one. Checked frame by frame.
Galloping horse
Four legs and a full gallop, but the first 3 seconds are a blurred close tracking shot before a cut to the wide side profile. Checked frame by frame.
Style avg 4.88/5
Anime walk cycle
Clean anime style with face and outfit unchanged, but the camera follows the walk, so the character moves only a little across the frame. Checked frame by frame.
Claymation wave
The figure waves and the palm carries a large fingerprint, but the clip cuts to a close-up of the hand and back. Checked frame by frame.
1970s film look
1970s car on a coastal road with film grain and strong halation and flare.
Rotating mug
Plain white mug turns continuously and the handle travels all the way around without jumping or duplicating.
Image to video avg 5/5
Animate a landscape
Clouds drift and the grass moves while the hills stay fixed, with no camera move. Compared with the reference image.
Animate a vintage photo
Stays sepia with the original grain and adds only subtle motion to the family and the trees. Compared with the reference image.
Animate a portrait
Same face from first to last frame, with a blink, a slight head tilt and hair motion. Compared with the reference image.
Product photo to spin
Turns about 180 degrees, handle from the right round the back to the left, with rigid geometry. Output keeps the square format of the reference. Verified frame by frame.
Animation avg 4.53/5
3D feature film look
Cuts between close-ups and medium shots three times. The robot smiles and the butterfly lands on its open palm at about 6.5 seconds, but then shrinks to half its size over the last second.
Anime sword draw
She stands still for the first 3.5 seconds, then draws and the clip cuts to a wide stance against speed lines, sword raised and sheath in the other hand. Little forward lunge.
Squash and stretch
Every principle asked for: a squash in anticipation, a stretched hop, a flat splat on landing, a tall rebound and a wide-eyed surprised face, all on a static camera.
2D walk cycle
The fox walks in place in side view, but the tail snaps between different poses every half second and the legs tangle into each other at the contact frames.