EuroEval Latvian: leaderboard
Latvian-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: Estimated already saturated. 238 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 | 70.85 | #98 |
| 2 | Gemini 3 Pro (Preview) | 69.58 | #66 |
| 3 | GPT-5.4 Mini (2026-03-17) (High) | 68.78 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 4 | Claude Sonnet 4.5 (Thinking) | 67.91 | #142 (Claude Sonnet 4.5) |
| 5 | Gemini 2.5 Flash (Thinking) | 67.61 | #245 (Gemini 2.5 Flash) |
| 6 | Gemini 3.1 Flash Lite (Preview) | 67.43 | #194 |
| 7 | GPT-5.2 | 66.83 | #110 |
| 8 | Gemini 2.5 Pro | 66.13 | #152 |
| 9 | Gemma 4 31B (IT) | 65.96 | #176 |
| 10 | Claude Sonnet 4.6 | 65.86 | #90 |
| 11 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 65.49 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 12 | GPT-5 Mini (2025-08-07) | 65.38 | #172 |
| 13 | Gemini 3 Flash (Preview) (Thinking) | 65.27 | #82 (Gemini 3 Flash (Preview)) |
| 14 | Gemini 3 Flash (Preview) (Non-reasoning) | 65.13 | #82 (Gemini 3 Flash (Preview)) |
| 15 | Qwen 3 235B A22B 2507 Instruct | 63.81 | #300 |
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 · How It Works · Data refreshed daily, snapshot 2026-10-20.