EuroEval Icelandic NLU - MIM-GOLD NER: leaderboard
The "MIM-GOLD NER" subtask of EuroEval Icelandic NLU. Icelandic-language EuroEval natural-language-understanding suite, separating NLU task performance from the broader all-task EuroEval aggregate.
Metric: Micro F1 excluding MISC (%). Source: euroeval.com. Saturation forecast: Around January 2027. 392 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 (Thinking) | 86.91 | #142 (Claude Sonnet 4.5) |
| 2 | GPT-5 (2025-08-07) (High) | 85.47 | |
| 3 | GPT-5 | 84.43 | #98 |
| 4 | GPT-5.4 Mini (2026-03-17) (High) | 84.04 | #169 (GPT-5.4 Mini (2026-03-17)) |
| 5 | Qwen 3.5 35B A3B Base | 82.51 | #310 |
| 6 | Qwen 3 235B A22B 2507 FP8 (Thinking) | 82.42 | #246 (Qwen 3 235B A22B 2507 FP8) |
| 7 | Gemma 4 31B (IT) | 79.94 | #176 |
| 8 | O3 (2025-04-16) | 78.07 | #121 |
| 9 | Gemini 3 Flash (Preview) (Thinking) | 77.08 | #82 (Gemini 3 Flash (Preview)) |
| 10 | GLM 4.5 Air (Thinking) | 75.93 | #392 (GLM 4.5 Air) |
| 11 | Gemma 4 26B A4B (IT) | 75.89 | #297 |
| 12 | Gemini 3 Pro (Preview) | 75.87 | #66 |
| 13 | Qwen 3 Next 80B A3B (Thinking) | 75.24 | #320 (Qwen 3 Next 80B A3B) |
| 14 | Gemini 2.5 Flash (Thinking) | 74.9 | #245 (Gemini 2.5 Flash) |
| 15 | Gemini 3.1 Flash Lite (Preview) | 74.85 | #194 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=euroeval-icelandic-nlu-mim-gold-ner · How It Works · Data refreshed daily, snapshot 2026-10-20.