KoNeoBench - Specialist Domain - Multiple Choice: leaderboard
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Around December 2026. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 84.12 |
| 2 | GPT-4.1 | 80 |
| 3 | Qwen 3.5 9B | 57.13 |
| 4 | Solar Pro 3 | 52.12 |
| 5 | Qwen 2.5 7B Instruct | 48 |
| 6 | EXAONE 3.5 7.8B Instruct | 40.12 |
| 7 | Llama 3.1 8B Instruct | 32.75 |
Interactive version: theaggregate.ai/benchmark?slug=koneobench-specialist-domain-multiple-choice · How It Works · Data refreshed daily, snapshot 2026-09-24.