SPACE Personality Study - Base - FOMC - Accuracy: leaderboard
SPACE v1 Table11,FOMC unmodified Instruct Base only, nativeAccuracy. Base/T/F triple retained inprimary; takeBasefirstonly. Greedy and exactstudyextraction. CommitmentBankstrictmajority858/1009records,151distributiononly,notoriginal3classgold. No DPOrow substitution.
Metric: Accuracy (native). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 2.5 7B Instruct | 63.07 | #2583 |
| 2 | Llama 3.1 8B Instruct | 59.48 | #4277 |
| 3 | Qwen 2.5 3B Instruct | 56.67 | #5206 |
| 4 | Llama 3.2 3B Instruct | 51.8 | #7185 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=space-personality-study-base-fomc-accuracy · How It Works · Data refreshed daily, snapshot 2026-11-12.