IKP - T2: leaderboard
IKP's second factual-recall tier, covering common knowledge beyond its easiest questions. Accuracy on all 200 cleaned T2 questions; no retrieval, supplied evidence or hallucination penalty.
Metric: Accuracy (%). Source: 01.me. Saturation forecast: Estimated already saturated. 197 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 100 | #148 |
| 2 | Claude Sonnet 4.6 | 100 | #94 |
| 3 | GPT-5.5 | 100 | #33 |
| 4 | DeepSeek V3.2 | 100 | #210 |
| 5 | Claude Opus 4.8 | 100 | #39 |
| 6 | DeepSeek V4 Flash | 100 | #155 |
| 7 | Claude 3.7 Sonnet | 100 | #259 |
| 8 | Gemini 3 Flash (Preview) | 100 | #90 |
| 9 | GPT-4 Turbo | 100 | #417 |
| 10 | Mixtral 8x22B Instruct | 100 | #738 |
| 11 | GLM-5.2 | 100 | #80 |
| 12 | Grok 3 | 100 | #313 |
| 13 | Qwen 3.7 Max | 100 | #85 |
| 14 | Qwen 3.7 Plus | 100 | #98 |
| 15 | Nemotron 3 Ultra | 100 | #245 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=ikp-t2 · How It Works · Data refreshed daily, snapshot 2026-11-05.