EuroEval Serbian: leaderboard
Serbian-language EuroEval all-task suite spanning NLU, knowledge, common-sense reasoning, reading comprehension, summarization, and related tasks.
Metric: Average Score (%). Source: euroeval.com. Saturation forecast: Around May 2027. 209 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 72.24 | #98 |
| 2 | Gemini 2.5 Flash (Thinking) | 70 | #245 (Gemini 2.5 Flash) |
| 3 | Gemini 2.5 Pro | 69.52 | #152 |
| 4 | Gemini 3 Pro (Preview) | 67.08 | #66 |
| 5 | Claude Sonnet 4.5 (Thinking) | 66.08 | #142 (Claude Sonnet 4.5) |
| 6 | Gemini 3 Flash (Preview) (Thinking) | 63.65 | #82 (Gemini 3 Flash (Preview)) |
| 7 | Gemini 3 Flash (Preview) (Non-reasoning) | 62.41 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Gemini 2.5 Flash (Non-reasoning) | 61.96 | #245 (Gemini 2.5 Flash) |
| 9 | GPT-5 Mini (2025-08-07) | 61.23 | #172 |
| 10 | Gemini 3.1 Flash Lite (Preview) | 60.99 | #194 |
| 11 | Claude Sonnet 4.6 | 60.48 | #90 |
| 12 | Grok 4.1 Fast (Reasoning) | 60.04 | #217 (Grok 4.1 Fast) |
| 13 | GPT-5.4 Mini (2026-03-17) (High) | 58.2 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 14 | GPT-5.2 | 58 | #110 |
| 15 | Gemini 2.5 Flash Lite (Thinking) | 57.43 | #422 (Gemini 2.5 Flash Lite) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-serbian · How It Works · Data refreshed daily, snapshot 2026-10-20.