IKP - T1: leaderboard
The easiest IKP factual-recall tier: universal knowledge such as capitals and familiar geographical facts. Accuracy on all 200 cleaned T1 questions, answered without retrieval or supplied evidence.
Metric: Accuracy (%). Source: 01.me. Saturation forecast: Estimated already saturated. 195 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 100 | #64 |
| 2 | Claude Sonnet 4.6 | 100 | #94 |
| 3 | GPT-5.4 | 100 | #83 |
| 4 | GPT-4.1 | 100 | #258 |
| 5 | GPT-5.5 | 100 | #33 |
| 6 | Qwen 2.5 72B Instruct | 100 | #469 |
| 7 | Claude Opus 4.6 | 100 | #67 |
| 8 | GPT-4.1 Nano | 100 | #730 |
| 9 | Claude Opus 4.7 | 100 | #51 |
| 10 | Grok 4 | 100 | #189 |
| 11 | GPT-5.4 Mini | 100 | #228 |
| 12 | Gemini 3 Flash (Preview) | 100 | #90 |
| 13 | GLM-5.1 | 100 | #109 |
| 14 | MiniMax-M3 | 100 | #151 |
| 15 | GLM-5.2 | 100 | #80 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ikp-t1 · How It Works · Data refreshed daily, snapshot 2026-11-05.