IKP - T6: leaderboard
IKP's sixth obscurity tier tests very rare entity facts and researcher knowledge. Accuracy on all 187 cleaned T6 questions; tier difficulty was calibrated using reference models, and no retrieval or supplied evidence is allowed.
Metric: Accuracy (%). Source: 01.me. Saturation forecast: Around February 2027. 141 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 93.58 | #64 |
| 2 | Gemini 3 Flash (Preview) (Medium) | 82.35 | #90 (Gemini 3 Flash (Preview)) |
| 3 | Gemini 3 Flash (Preview) | 79.68 | #90 |
| 4 | GPT-5.5 (Medium) | 69.52 | #33 (GPT-5.5) |
| 5 | GPT-5.5 | 67.38 | #33 |
| 6 | Claude Fable 5 | 59.89 | #20 |
| 7 | Gemini 2.5 Pro (Preview) | 57.75 | #136 |
| 8 | Gemini 2.5 Pro (Medium) | 55.08 | #159 (Gemini 2.5 Pro) |
| 9 | Gemini 3.1 Flash Lite (Preview) | 49.73 | #201 |
| 10 | GPT-5.4 Pro (xHigh) | 48.66 | #38 (GPT-5.4 Pro) |
| 11 | O3 | 48.13 | #132 |
| 12 | GPT-5 Pro | 48.13 | #89 |
| 13 | GPT-4.1 | 47.06 | #258 |
| 14 | GPT-5 (Medium) | 45.99 | #105 (GPT-5) |
| 15 | DeepSeek V4 Flash | 44.39 | #155 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ikp-t6 · How It Works · Data refreshed daily, snapshot 2026-11-05.