EuroEval Serbian Knowledge: leaderboard
Metric: Knowledge Average Score (%). Source: euroeval.com. 188 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 91.4 |
| 2 | GPT-5 | 90.17 |
| 3 | Gemini 2.5 Pro | 88.2 |
| 4 | Gemini 3 Pro (Preview) | 87.86 |
| 5 | Gemini 2.5 Flash (Thinking) | 86.15 |
| 6 | GPT-5 Mini | 84.32 |
| 7 | GPT-5.4 Mini (High) | 83.73 |
| 8 | GPT-5.4 Mini (Medium) | 83.26 |
| 9 | Grok 4.1 Fast (Reasoning) | 82.4 |
| 10 | Gemini 3.1 Flash Lite (Preview) | 81.11 |
| 11 | Claude Sonnet 4.6 | 79.68 |
| 12 | GPT-5.4 Nano (High) | 78.99 |
| 13 | GPT-5.2 | 78.4 |
| 14 | GPT-5.4 Nano (Medium) | 78.22 |
| 15 | Qwen 3.5 9B | 75.93 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-serbian-knowledge · How It Works · Data refreshed daily, snapshot 2026-09-05.