D-02 · Largest score gapsarchive-recorded · snapshot 2026-09-17
Largest Score Gaps: Top 20
The 20 head-to-head dossiers with the widest recorded overall-score gaps, out of 170 pair dossiers (of 195 total dossiers). The widest recorded gap is 9.2 points (midjourney-vs-sora).
Key numbers
Pair dossiers
170
data/comparisons.json (mode=pair) · N=195
Widest gap
9.2 pts
delta · N=170
Widest matchup
midjourney-vs-sora
delta · N=170
Pairs at 5 pts or more
20
delta · N=170
Median pair gap
2.5 pts
delta · N=170
Largest gaps — top 20 of 170 pairs
descending delta; scores from archives (score.overall)
| # | Matchup | Winner (overall) | Runner-up (overall) | Gap (pts) | Winner |
|---|---|---|---|---|---|
| 1 | Midjourney vs Sora | Midjourney · 85.7 | Sora · 76.5 | 9.2 | Midjourney |
| 2 | Murf vs PlayHT | Murf · 80.2 | PlayHT · 89.2 | 9 | PlayHT |
| 3 | Retool vs Superblocks | Retool · 83.3 | Superblocks · 76.1 | 7.2 | Retool |
| 4 | Consensus vs Elicit | Consensus · 77.8 | Elicit · 84.8 | 7 | Elicit |
| 5 | DeepSeek vs ChatGPT | DeepSeek · 84.7 | ChatGPT · 90.9 | 6.2 | ChatGPT |
| 6 | Sora vs Kling AI | Sora · 76.5 | Kling AI · 82.7 | 6.2 | Kling AI |
| 7 | Sora vs Kling AI | Sora · 76.5 | Kling AI · 82.7 | 6.2 | Kling AI |
| 8 | FLUX vs Figma Make | FLUX · 88.3 | Figma Make · 82.3 | 6 | FLUX |
| 9 | Fathom vs Granola | Fathom · 86.1 | Granola · 80.2 | 5.9 | Fathom |
| 10 | FLUX vs Ideogram | FLUX · 88.3 | Ideogram · 82.4 | 5.9 | FLUX |
| 11 | ElevenLabs vs Suno | ElevenLabs · 87.8 | Suno · 82 | 5.8 | ElevenLabs |
| 12 | Krea AI vs Magnific AI | Krea AI · 83.1 | Magnific AI · 77.4 | 5.7 | Krea AI |
| 13 | Cursor vs Cline | Cursor · 89.2 | Cline · 83.7 | 5.5 | Cursor |
| 14 | FLUX vs Adobe Firefly | FLUX · 88.3 | Adobe Firefly · 82.8 | 5.5 | FLUX |
| 15 | FLUX vs Recraft | FLUX · 88.3 | Recraft · 82.9 | 5.4 | FLUX |
| 16 | Cursor vs Windsurf | Cursor · 89.2 | Windsurf · 83.9 | 5.3 | Cursor |
| 17 | Cursor vs Kilo | Cursor · 89.2 | Kilo · 84 | 5.2 | Cursor |
| 18 | FLUX vs Krea AI | FLUX · 88.3 | Krea AI · 83.1 | 5.2 | FLUX |
| 19 | FLUX vs Leonardo AI | FLUX · 88.3 | Leonardo AI · 83.2 | 5.1 | FLUX |
| 20 | Cursor vs Trae | Cursor · 89.2 | Trae · 84.2 | 5 | Cursor |
Ten widest pairs
Overall-score gap in points for the ten most one-sided recorded matchups.
Method
- Source: data/comparisons.json, pair dossiers only (mode=pair, N=170 of 195 dossiers).
- Gap = the numeric value in each dossier's delta field; participant overall scores come from the tool archives.
- Ordering: gap descending, ties broken by dossier slug.
- All values are archive-recorded or dossier-recorded; nothing is re-scored.