VPCT
Rank #25 of 51 · 26 models scored · top score 86.5
unknown
Strongest on discrimination, weakest on contamination resistance. Caveat: the public test set leaves contamination on the table.
Weighted composite. Each signal is computed from the source-backed leaderboard below.
Does it still separate models?
How far from ceiling / clustered at the top?
Public vs held-out; training-leak risk.
Apples-to-apples, or mixed / vendor-optimized?
How old is the benchmark?
| # | Model | Score | Evidence | Measured |
|---|---|---|---|---|
| 1 | Gemini 3 Pro | 86.5 | unverified | 2025-11-18 |
| 2 | GPT-5.2 | 76 | unverified | 2025-12-11 |
| 3 | Gemini 3 Flash | 58.9 | unverified | 2025-12-17 |
| 4 | GPT-5 | 49 | unverified | 2025-08-07 |
| 5 | GPT-5.1 | 38.05 | unverified | 2025-11-13 |
| 6 | o4-mini | 36.25 | unverified | 2025-04-16 |
| 7 | o3 | 28 | unverified | 2024-12-20 |
| 8 | Gemini 2.5 Pro (Mar 2025) | 22 | unverified | 2025-03-25 |
| 9 | Gemini 2.5 Pro (Jun 2025) | 19.6 | unverified | 2025-06-05 |
| 10 | Gemini 2.5 Flash (Sep 2025) | 19.3 | unverified | 2025-09-25 |
| 11 | GPT-4.5 | 17.5 | unverified | 2025-02-27 |
| 12 | Gemini 2.5 Pro (May 2025) | 10.75 | unverified | 2025-05-06 |
| 13 | GPT-5 mini | 10.3 | unverified | 2025-08-07 |
| 14 | Claude Opus 4.5 | 10 | unverified | 2025-11-24 |
| 15 | GPT-4o (Nov 2024) | 10 | unverified | 2024-05-13 |
| 16 | Claude Sonnet 4.5 | 9.7 | unverified | 2025-09-29 |
| 17 | Claude 3.7 Sonnet | 8.5 | unverified | 2025-02-24 |
| 18 | Claude Opus 4 | 7 | unverified | 2025-05-22 |
| 19 | Gemini 2.5 Flash (Apr 2025) | 7 | unverified | 2025-04-17 |
| 20 | GPT-5 nano | 5.8 | unverified | 2025-08-07 |
| 21 | o1 | 5.5 | unverified | 2024-12-05 |
| 22 | Claude Opus 4.1 | 2.5 | unverified | 2025-08-05 |
| 23 | Claude Sonnet 4 | 1 | unverified | 2025-05-22 |
| 24 | GPT-4o mini | 1 | unverified | 2024-07-18 |
| 25 | Claude 3.5 Sonnet | 0 | unverified | 2024-06-20 |
| 26 | Claude 3.5 Sonnet (October 2024) | 0 | unverified | 2024-10-22 |