EuroEval Latvian Knowledge: leaderboard
EuroEval's Latvian knowledge task — multiple-choice general-knowledge questions in Latvian, from the EuroEval European language model benchmark suite.
Metric: Knowledge Average Score (%). Source: euroeval.com. Saturation forecast: Estimated already saturated. 212 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 87.47 | #142 (Claude Sonnet 4.5) |
| 2 | Gemini 2.5 Pro | 87.46 | #152 |
| 3 | GPT-5 | 86.7 | #98 |
| 4 | Gemini 3 Pro (Preview) | 84.63 | #66 |
| 5 | Grok 4.1 Fast (Reasoning) | 84.18 | #217 (Grok 4.1 Fast) |
| 6 | GPT-5.4 Mini (2026-03-17) (High) | 83.71 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 7 | Gemini 3 Flash (Preview) (Thinking) | 83.64 | #82 (Gemini 3 Flash (Preview)) |
| 8 | Gemini 2.5 Flash (Thinking) | 83.57 | #245 (Gemini 2.5 Flash) |
| 9 | Gemini 3 Flash (Preview) (Non-reasoning) | 83.02 | #82 (Gemini 3 Flash (Preview)) |
| 10 | GPT-5.2 | 82.23 | #110 |
| 11 | GPT-5 Mini (2025-08-07) | 82.15 | #172 |
| 12 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 80.72 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 13 | Gemini 3.1 Flash Lite (Preview) | 79.95 | #194 |
| 14 | Gemma 4 31B (IT) | 79.32 | #176 |
| 15 | Qwen 3.5 35B A3B Base | 77.62 | #310 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-latvian-knowledge · How It Works · Data refreshed daily, snapshot 2026-10-20.