The creative model reference

AI video editing model comparison

Compare the editing board before testing changes to an existing video.

September 2026 benchmark snapshot · Curated by Oakgen. Data source and limits.

video / Video Editing

The scores, in perspective.

6 models · 95% intervals

Swipe to compare all models →

Oakgen Arena · v1.0

11,080

Wan 3.0

21,079

Seedance 2.5

31,068

Google Omni Flash

41,046

Seedance 2.0

51,008

Seedance 2.0 Mini

61,000

MiniMax H3Anchor

↥ 95% confidence interval · Anchor interval not reported.6 ranked models

Relative scores on a zero-based display scale. Compare within this board only. Values are rounded for display.

September 2026 benchmark snapshot · Curated by Oakgen. Data source and limits.

Published reference / v1.0

Video Editing leaderboard

Video Editing video rankings · Benchmark index 1.0
Rank	Model	Overall score	95% confidence interval	Vote appearances	Distinct judges
01	Wan 3.0Alibaba Criterion scores Audio quality1,059.695% CI 1,022.9 to 1,100.1Reused fit from master-video Consistency1,121.595% CI 1,080.6 to 1,165.8Reused fit from master-video Physics & motion1,026.795% CI 993 to 1,058.4Reused fit from master-video Precise editing1,066.495% CI 1,007.6 to 1,130 Prompt adherence989.595% CI 923.3 to 1,054.3 Prompt adherence980.895% CI 940.2 to 1,021.2Reused fit from master-video Style adaptation1,227.295% CI 1,130.5 to 1,341 Subjective aesthetics1,044.395% CI 1,006.5 to 1,083.1Reused fit from master-video	1,080LEAD	1,047.5 to 1,112.2	4,263	Not reported
02	Seedance 2.5ByteDance Criterion scores Audio quality1,178.195% CI 1,128.4 to 1,228.7Reused fit from master-video Consistency1,194.795% CI 1,151.8 to 1,243.3Reused fit from master-video Physics & motion1,103.695% CI 1,068.6 to 1,137.4Reused fit from master-video Precise editing1,001.295% CI 941.7 to 1,065.6 Prompt adherence1,091.295% CI 1,035.3 to 1,163.9 Prompt adherence1,052.695% CI 1,014.6 to 1,088.4Reused fit from master-video Style adaptation1,085.395% CI 1,004.8 to 1,187.8 Subjective aesthetics1,096.495% CI 1,061.3 to 1,131.1Reused fit from master-video	1,079#2	1,052.6 to 1,113.8	4,269	Not reported
03	Google Omni FlashGoogle Criterion scores Audio quality1,108.895% CI 1,065.6 to 1,152.5Reused fit from master-video Consistency995.495% CI 956 to 1,033.9Reused fit from master-video Physics & motion98395% CI 949.1 to 1,020.3Reused fit from master-video Precise editing992.395% CI 917 to 1,075.1 Prompt adherence978.195% CI 903.8 to 1,056.5 Prompt adherence977.295% CI 942.3 to 1,010.9Reused fit from master-video Style adaptation1,283.995% CI 1,181.6 to 1,417.9 Subjective aesthetics1,081.695% CI 1,041.6 to 1,123.6Reused fit from master-video	1,068.1#3	1,034.4 to 1,106.1	4,279	Not reported
04	Seedance 2.0ByteDance Criterion scores Audio quality1,102.895% CI 1,063.5 to 1,140.8Reused fit from master-video Consistency1,060.895% CI 1,022.7 to 1,099Reused fit from master-video Physics & motion1,036.195% CI 1,002.3 to 1,069.3Reused fit from master-video Precise editing960.795% CI 899 to 1,021.2 Prompt adherence1,054.695% CI 978.1 to 1,140.6 Prompt adherence1,050.595% CI 1,017.4 to 1,084.1Reused fit from master-video Style adaptation1,125.895% CI 1,038.6 to 1,227.9 Subjective aesthetics971.895% CI 935.7 to 1,010.3Reused fit from master-video	1,046.2	1,012 to 1,081.5	4,304	Not reported
05	Seedance 2.0 MiniByteDance Criterion scores Audio quality1,127.895% CI 1,085.5 to 1,172.8Reused fit from master-video Consistency1,03495% CI 997.3 to 1,069.8Reused fit from master-video Physics & motion1,024.495% CI 991.6 to 1,059.6Reused fit from master-video Precise editing952.595% CI 884.3 to 1,028.9 Prompt adherence1,017.495% CI 964.3 to 1,072.6 Prompt adherence971.495% CI 937.1 to 1,002.7Reused fit from master-video Style adaptation1,022.495% CI 935 to 1,118 Subjective aesthetics1,008.595% CI 972.9 to 1,048.3Reused fit from master-video	1,008.2	979.5 to 1,040.9	4,310	Not reported
06	MiniMax H3MiniMax Criterion scores Audio quality1,00095% CI Anchor · interval not reportedReused fit from master-video Consistency1,00095% CI Anchor · interval not reportedReused fit from master-video Physics & motion1,00095% CI Anchor · interval not reportedReused fit from master-video Precise editing1,00095% CI Anchor · interval not reported Prompt adherence1,00095% CI Anchor · interval not reported Prompt adherence1,00095% CI Anchor · interval not reportedReused fit from master-video Style adaptation1,00095% CI Anchor · interval not reported Subjective aesthetics1,00095% CI Anchor · interval not reportedReused fit from master-video	1,000Anchor	Anchor · interval not reported	4,297	Not reported

Ranks are the source’s published positions. Vote appearances are not unique people and must not be added across boards. Scores are rounded for display.

September 2026 benchmark snapshot · Curated by Oakgen. Data source and limits.

From comparison to creation

Choose for your brief.

Keep an untouched copy of your clip and compare the edited region with the rest of the frame. Check identity, lighting and motion continuity. Judge how well the requested change works and how much unrelated content moves.

Explore Oakgen's model directory

A source listing does not confirm current availability in Oakgen.

How this board is composed

Criteria and weights

Physics & motion6%
Audio quality6%
Precise editing23.3%
Prompt adherence23.3%
Prompt adherence6%
Style adaptation23.3%
Consistency6%
Subjective aesthetics6%

Read the methodology