EuroEval Greek NLU - MultiWikiQA EL: leaderboard
The "MultiWikiQA EL" subtask of EuroEval Greek NLU. Greek-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Character F1 (%). Source: euroeval.com. Saturation forecast: Around January 2027. 204 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 3.1 70B | 76.53 | #592 |
| 2 | gemma-3-27B-pt | 74.2 | #502 |
| 3 | Ministral-3-14B-Reasoning-2512 | 73.81 | #540 |
| 4 | gemma-3-12B-pt | 73.15 | #686 |
| 5 | Llama 3.1 8B | 72.93 | #1151 |
| 6 | Qwen3.5-4B-Base | 72.82 | #798 |
| 7 | Mistral Small 3.2 | 72.45 | #605 |
| 8 | Gemma 4 31B | 70.17 | #200 |
| 9 | Qwen 3 14B (Non-reasoning) | 70.12 | #537 (Qwen 3 14B) |
| 10 | Voxtral-Small-24B-2507 | 69.77 | #581 |
| 11 | Qwen3.5-2B-Base | 68.96 | #1309 |
| 12 | Ministral-3-14B-Instruct-2512 | 68.79 | #615 |
| 13 | Mistral Small 3.1 | 68.73 | #610 |
| 14 | Qwen 3 32B (Non-reasoning) | 68.46 | #443 (Qwen 3 32B) |
| 15 | EuroLLM-9B | 68.1 | #1254 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-greek-nlu-multiwikiqa-el · How It Works · Data refreshed daily, snapshot 2026-10-20.