KoNeoBench - Semantic Category - Open without Examples: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around 2029. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 53.28 |
| 2 | GPT-4.1 | 47 |
| 3 | Qwen 3.5 9B | 37.76 |
| 4 | Solar Pro 3 | 36.13 |
| 5 | Qwen 2.5 7B Instruct | 34.62 |
| 6 | EXAONE 3.5 7.8B Instruct | 33.45 |
| 7 | Llama 3.1 8B Instruct | 32.94 |
Interactive version: theaggregate.ai/benchmark?slug=koneobench-semantic-category-open-without-examples · How It Works · Data refreshed daily, snapshot 2026-09-24.