EuroEval Latvian Common Sense Reasoning: leaderboard
Metric: Common Sense Reasoning Average Score (%). Source: euroeval.com. 212 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 97.25 |
| 2 | Claude Sonnet 4.6 | 94.71 |
| 3 | Gemini 3 Pro (Preview) | 94.71 |
| 4 | Gemini 2.5 Pro | 94.34 |
| 5 | Gemini 3.1 Flash Lite (Preview) | 92.24 |
| 6 | GPT-5.4 Mini (Medium) | 92.24 |
| 7 | Gemma 3 27B (IT) | 92.21 |
| 8 | GPT-5.4 Mini (High) | 91.59 |
| 9 | GPT-5 | 91.51 |
| 10 | GPT-5.2 | 91.23 |
| 11 | gemma-3-27B-pt | 91.19 |
| 12 | Claude Sonnet 4.5 (Thinking) | 90.43 |
| 13 | Qwen 3 235B A22B 2507 Instruct | 89.67 |
| 14 | Gemma 4 31B (IT) | 89.04 |
| 15 | Gemini 2.5 Flash (Thinking) | 88.62 |
Interactive version: theaggregate.ai/benchmark?slug=euroeval-latvian-common-sense-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.