Benchmarks · knowledge
UGI NatInt
A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics. Maintained by DontPlanToEnd. Score: NatInt 💡.
167 models · 168 results · data as of 2026-10-29 · huggingface.co ↗
Leaderboard
Gemini 4 Argon max
All results
168 rows| # | Model | Effort | UGI NatInt |
|---|---|---|---|
| 1 | Gemini 4 Argon | max | 81.3 |
| 2 | GPT-6 Astra | max | 78.5 |
| 3 | Gemini 3.1 Pro | high | 76.2 |
| 4 | Gemini 3.7 Flash | max | 76.1 |
| 5 | GPT-6 Sol | max | 74.0 |
| 6 | Gemini 3.5 Flash | xhigh | 72.3 |
| 7 | GPT-6.1 Sol | max | 71.1 |
| 8 | Gemini 3 Flash | high | 70.4 |
| 9 | Opus 5.5 | max | 70.4 |
| 10 | GPT-5.6 Sol | max | 70.1 |
| 11 | Gemini 3.8 Flash | max | 69.7 |
| 12 | Fable 5 | max | 67.5 |
| 13 | Gemini 3 Pro | high | 67.2 |
| 14 | GPT-5.2025 | high | 67.2 |
| 15 | Gemini 3.6 Flash | xhigh | 66.5 |
| 16 | o3 | high | 65.5 |
| 17 | Grok 4.0709 | 65.2 | |
| 18 | Fable 5.1 | max | 64.9 |
| 19 | o1 | high | 64.2 |
| 20 | Gemini 2.5 Pro | high | 64.0 |
| 21 | Opus 4.5 | high | 63.8 |
| 22 | GPT-5.3 | xhigh | 63.5 |
| 23 | Opus 4.6 | max | 62.9 |
| 24 | GPT-5.5 | xhigh | 62.6 |
| 25 | Grok 4.6 | max | 60.8 |
| 26 | Opus 4.8 | max | 60.7 |
| 27 | Kimi K2.5 | max | 60.3 |
| 28 | Grok 4.5 | max | 60.2 |
| 29 | GPT-4.1 | high | 59.9 |
| 30 | Kimi K2.6 | max | 59.5 |