Miðeind Icelandic Generative Quality
Models write paragraphs in Icelandic. Málfríður checks for grammar errors, and a dictionary lookup counts words absent from the Database of Modern Icelandic Inflection.
Passes test 2. Miðeind reports scores for 60 named models on its current leaderboard. The quality score combines grammatical and vocabulary measures.
- Made by
- Miðeind
- Released
- September 2026
- Kind
- Chat and instructions in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- Kept private
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Icelandic
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Fable 5.2 #2 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
GPT-6.2 Sol leads with 87.7% GPT-6.2 Sol leads with 87.7%
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
- 87.7 GPT-6.2 Sol
- 84.3 GPT-6.1 Terra
- 83.8 GPT-6 Sol
- 82.9 Claude Fable 5.2
- 82.3 GPT-6 Luna
- 82.2 GPT-6 Astra
- 79.4
Gemini 4 Hydrogen
- 78.8 GPT-6.1 Sol
- 78.7 GPT-5.6 Luna
- 78.7 GPT-5.6 Sol
- 78.3
Gemini 4 Neon
- 77.8 Grok 4.7
- 75.6
Gemini 4 Carbon
- 75.6
DeepSeek-V4-Pro
- 74.9 Claude Sonnet 5.5
- 74.9
Gemini 4 Argon
- 74.6 GPT-5.6 Terra
- 74.5 Claude Opus 5.5
- 74.3
Gemini 3.1 Pro
- 73.7 Claude Fable 5.1
- 72.3 Claude Opus 5
- 71.4
Gemini 3.7 Flash
- 70.7 Claude Opus 4.8
- 70.2 Claude Sonnet 5
- 69.0 Claude Haiku 5.5
- 68.6 GPT-4o
- 67.8
Gemini 3.8 Flash
- 65.6
DeepSeek V4.1 Flash
- 64.8 GPT-5.2
- 64.0
Inkling 2 Small
- 63.9
Gemini 2.5 Pro
- 62.8
Qwen3.8-2.4T-A95B
- 62.6
Gemini 3.5 Flash
- 61.7
Muse Spark Open
- 61.0
Mistral Large 4
- 60.3 Bielik 11B v3.1 Instruct
- 57.9
Inkling
- 57.6 Kimi K3
- 57.5
Gemini 3.5 Flash-Lite
- 55.2
Mistral Large 3
- 55.0
Gemini 2.5 Flash-Lite
- 48.8
MiniMax-M3
- 48.7 GPT-4.1 nano
- 45.6
Mistral Small 4
- 43.4
Inkling-Small
- 42.6
Apertus 1.5 70B
- 37.5
Gemma 4 26B A4B
- 37.3 Llama 3.1 70B Instruct
- 36.1 GPT-3.5 Turbo
- 35.4 Claude Haiku 4.5
- 34.4
Mistral Medium 3.5
- 34.0
MiniMax-M3.1-Flash
- 33.3
Gemma 4 31B IT
- 31.4 Llama 3.1 8B Instruct
- 30.9
Qwen 3.8 27B
- 29.1
Apertus 8B Instruct
- 25.9
Gemma 4 12B
- 25.3
Apertus 1.5 8B
- 24.3
Gemma 4 E2B
- 24.1
Gemma 4 E4B
- 21.7 GLM-5.3-Flash
- 18.3 Ripple-65B Preview
- 1 GPT-6.2 Sol high 87.7%
- 2 GPT-6.1 Terra off 84.3%
- 3 GPT-6 Sol high 83.8%
- 4 Claude Fable 5.2 low 82.9%
- 5 GPT-6 Luna high 82.3%
- 6 GPT-6 Astra high 82.2%
- 7
Gemini 4 Hydrogen high 79.4%
- 8 GPT-6.1 Sol low 78.8%
- 9 GPT-5.6 Luna off 78.7%
- 10 GPT-5.6 Sol off 78.7%
- 11
Gemini 4 Neon low 78.3%
- 12 Grok 4.7 low 77.8%
- 13
Gemini 4 Carbon low 75.6%
- 14
DeepSeek-V4-Pro on 75.6%
- 15 Claude Sonnet 5.5 high 74.9%
- 16
Gemini 4 Argon high 74.9%
- 17 GPT-5.6 Terra off 74.6%
- 18 Claude Opus 5.5 high 74.5%
- 19
Gemini 3.1 Pro high 74.3%
- 20 Claude Fable 5.1 high 73.7%
- 21 Claude Opus 5 off 72.3%
- 22
Gemini 3.7 Flash low 71.4%
- 23 Claude Opus 4.8 high 70.7%
- 24 Claude Sonnet 5 high 70.2%
- 25 Claude Haiku 5.5 high 69%
- 26 GPT-4o Mar 2025, none 68.6%
- 27
Gemini 3.8 Flash low 67.8%
- 28
DeepSeek V4.1 Flash on 65.6%
- 29 GPT-5.2 off 64.8%
- 30
Inkling 2 Small minimal 64%
- 31
Gemini 2.5 Pro Jun 2025, minimal 63.9%
- 32
Qwen3.8-2.4T-A95B on 62.8%
- 33
Gemini 3.5 Flash high 62.6%
- 34
Muse Spark Open off 61.7%
- 35
Mistral Large 4 high 61%
- 36 Bielik 11B v3.1 Instruct off 60.3%
- 37
Inkling high 57.9%
- 38 Kimi K3 on 57.6%
- 39
Gemini 3.5 Flash-Lite high 57.5%
- 40
Mistral Large 3 none 55.2%
- 41
Gemini 2.5 Flash-Lite Sep 2025, high 55%
- 42
MiniMax-M3 on 48.8%
- 43 GPT-4.1 nano none 48.7%
- 44
Mistral Small 4 off 45.6%
- 45
Inkling-Small high 43.4%
- 46
Apertus 1.5 70B on 42.6%
- 47
Gemma 4 26B A4B on 37.5%
- 48 Llama 3.1 70B Instruct none 37.3%
- 49 GPT-3.5 Turbo Jan 2024, none 36.1%
- 50 Claude Haiku 4.5 off 35.4%
- 51
Mistral Medium 3.5 high 34.4%
- 52
MiniMax-M3.1-Flash high 34%
- 53
Gemma 4 31B IT on 33.3%
- 54 Llama 3.1 8B Instruct none 31.4%
- 55
Qwen 3.8 27B off 30.9%
- 56
Apertus 8B Instruct none 29.1%
- 57
Gemma 4 12B on 25.9%
- 58
Apertus 1.5 8B on 25.3%
- 59
Gemma 4 E2B off 24.3%
- 60
Gemma 4 E4B off 24.1%
- 61 GLM-5.3-Flash on 21.7%
- 62 Ripple-65B Preview on 18.3%
Source: Official Miðeind Icelandic Generative Quality leaderboard
- 87.7 GPT-6.2 Sol
- 84.3 GPT-6.1 Terra
- 83.8 GPT-6 Sol
- 82.9 Claude Fable 5.2
- 82.3 GPT-6 Luna
- 82.2 GPT-6 Astra
- 79.4
Gemini 4 Hydrogen
- 78.8 GPT-6.1 Sol
- 78.7 GPT-5.6 Luna
- 78.7 GPT-5.6 Sol
- 78.3
Gemini 4 Neon
- 77.8 Grok 4.7
- 75.6
Gemini 4 Carbon
- 75.6
DeepSeek-V4-Pro
- 74.9 Claude Sonnet 5.5
- 74.9
Gemini 4 Argon
- 74.6 GPT-5.6 Terra
- 74.5 Claude Opus 5.5
- 74.3
Gemini 3.1 Pro
- 73.7 Claude Fable 5.1
- 72.3 Claude Opus 5
- 71.4
Gemini 3.7 Flash
- 70.7 Claude Opus 4.8
- 70.2 Claude Sonnet 5
- 69.0 Claude Haiku 5.5
- 68.6 GPT-4o
- 67.8
Gemini 3.8 Flash
- 65.6
DeepSeek V4.1 Flash
- 64.8 GPT-5.2
- 64.0
Inkling 2 Small
- 63.9
Gemini 2.5 Pro
- 62.8
Qwen3.8-2.4T-A95B
- 62.6
Gemini 3.5 Flash
- 61.7
Muse Spark Open
- 61.0
Mistral Large 4
- 57.9
Inkling
- 57.6 Kimi K3
- 57.5
Gemini 3.5 Flash-Lite
- 55.2
Mistral Large 3
- 55.0
Gemini 2.5 Flash-Lite
- 48.8
MiniMax-M3
- 48.7 GPT-4.1 nano
- 45.6
Mistral Small 4
- 43.4
Inkling-Small
- 42.6
Apertus 1.5 70B
- 37.5
Gemma 4 26B A4B
- 36.1 GPT-3.5 Turbo
- 35.4 Claude Haiku 4.5
- 34.4
Mistral Medium 3.5
- 34.0
MiniMax-M3.1-Flash
- 33.3
Gemma 4 31B IT
- 30.9
Qwen 3.8 27B
- 29.1
Apertus 8B Instruct
- 25.9
Gemma 4 12B
- 25.3
Apertus 1.5 8B
- 24.3
Gemma 4 E2B
- 24.1
Gemma 4 E4B
- 21.7 GLM-5.3-Flash
- 18.3 Ripple-65B Preview
- 1 GPT-6.2 Sol high 87.7%
- 2 GPT-6.1 Terra off 84.3%
- 3 GPT-6 Sol high 83.8%
- 4 Claude Fable 5.2 low 82.9%
- 5 GPT-6 Luna high 82.3%
- 6 GPT-6 Astra high 82.2%
- 7
Gemini 4 Hydrogen high 79.4%
- 8 GPT-6.1 Sol low 78.8%
- 9 GPT-5.6 Luna off 78.7%
- 10 GPT-5.6 Sol off 78.7%
- 11
Gemini 4 Neon low 78.3%
- 12 Grok 4.7 low 77.8%
- 13
Gemini 4 Carbon low 75.6%
- 14
DeepSeek-V4-Pro on 75.6%
- 15 Claude Sonnet 5.5 high 74.9%
- 16
Gemini 4 Argon high 74.9%
- 17 GPT-5.6 Terra off 74.6%
- 18 Claude Opus 5.5 high 74.5%
- 19
Gemini 3.1 Pro high 74.3%
- 20 Claude Fable 5.1 high 73.7%
- 21 Claude Opus 5 off 72.3%
- 22
Gemini 3.7 Flash low 71.4%
- 23 Claude Opus 4.8 high 70.7%
- 24 Claude Sonnet 5 high 70.2%
- 25 Claude Haiku 5.5 high 69%
- 26 GPT-4o Mar 2025, none 68.6%
- 27
Gemini 3.8 Flash low 67.8%
- 28
DeepSeek V4.1 Flash on 65.6%
- 29 GPT-5.2 off 64.8%
- 30
Inkling 2 Small minimal 64%
- 31
Gemini 2.5 Pro Jun 2025, minimal 63.9%
- 32
Qwen3.8-2.4T-A95B on 62.8%
- 33
Gemini 3.5 Flash high 62.6%
- 34
Muse Spark Open off 61.7%
- 35
Mistral Large 4 high 61%
- 36
Inkling high 57.9%
- 37 Kimi K3 on 57.6%
- 38
Gemini 3.5 Flash-Lite high 57.5%
- 39
Mistral Large 3 none 55.2%
- 40
Gemini 2.5 Flash-Lite Sep 2025, high 55%
- 41
MiniMax-M3 on 48.8%
- 42 GPT-4.1 nano none 48.7%
- 43
Mistral Small 4 off 45.6%
- 44
Inkling-Small high 43.4%
- 45
Apertus 1.5 70B on 42.6%
- 46
Gemma 4 26B A4B on 37.5%
- 47 GPT-3.5 Turbo Jan 2024, none 36.1%
- 48 Claude Haiku 4.5 off 35.4%
- 49
Mistral Medium 3.5 high 34.4%
- 50
MiniMax-M3.1-Flash high 34%
- 51
Gemma 4 31B IT on 33.3%
- 52
Qwen 3.8 27B off 30.9%
- 53
Apertus 8B Instruct none 29.1%
- 54
Gemma 4 12B on 25.9%
- 55
Apertus 1.5 8B on 25.3%
- 56
Gemma 4 E2B off 24.3%
- 57
Gemma 4 E4B off 24.1%
- 58 GLM-5.3-Flash on 21.7%
- 59 Ripple-65B Preview on 18.3%
Source: Official Miðeind Icelandic Generative Quality leaderboard
| # | Entry | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | GPT-6.2 Sol | 87.7% | high | Nov 2026 | Nov 2026 | developers.openai.com | Official leaderboard |
| 2 | GPT-6.1 Terra | 84.3% | off | Oct 2026 | Oct 2026 | developers.openai.com | Official leaderboard |
| 3 | GPT-6 Sol | 83.8% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 4 | Claude Fable 5.2 | 82.9% | low | Nov 2026 | Nov 2026 | anthropic.com | Official leaderboard |
| 5 | GPT-6 Luna | 82.3% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 6 | GPT-6 Astra | 82.2% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 7 | | 79.4% | high | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 8 | GPT-6.1 Sol | 78.8% | low | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 9 | GPT-5.6 Luna | 78.7% | off | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 10 | GPT-5.6 Sol | 78.7% | off | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 11 | | 78.3% | low | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 12 | Grok 4.7 | 77.8% | low | Sep 2026 | Nov 2026 | docs.x.ai | Official leaderboard |
| 13 | | 75.6% | low | Oct 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 14 | | 75.6% | on | Apr 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 15 | Claude Sonnet 5.5 | 74.9% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 16 | | 74.9% | high | Sep 2026 | Oct 2026 | ai.google.dev | Official leaderboard |
| 17 | GPT-5.6 Terra | 74.6% | off | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 18 | Claude Opus 5.5 | 74.5% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 19 | | 74.3% | high | Feb 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 20 | Claude Fable 5.1 | 73.7% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 21 | Claude Opus 5 | 72.3% | off | Jul 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 22 | | 71.4% | low | Aug 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 23 | Claude Opus 4.8 | 70.7% | high | May 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 24 | Claude Sonnet 5 | 70.2% | high | Jun 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 25 | Claude Haiku 5.5 | 69% | high | Oct 2026 | Oct 2026 | anthropic.com | Official leaderboard |
| 26 | GPT-4o Mar 2025 | 68.6% | none | Mar 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 27 | | 67.8% | low | Sep 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 28 | | 65.6% | on | Sep 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 29 | GPT-5.2 | 64.8% | off | Dec 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 30 | | 64% | minimal | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 31 | | 63.9% | minimal | Jun 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 32 | | 62.8% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 33 | | 62.6% | high | May 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 34 | | 61.7% | off | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 35 | | 61% | high | Oct 2026 | Oct 2026 | mistral.ai | Official leaderboard |
| 36 | Bielik 11B v3.1 Instruct 11.2B | 60.3% | off | Nov 2026 | huggingface.co | Official leaderboard | |
| 37 | | 57.9% | high | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 38 | Kimi K3 | 57.6% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 39 | | 57.5% | high | Jul 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 40 | | 55.2% | none | Dec 2025 | Sep 2026 | mistral.ai | Official leaderboard |
| 41 | | 55% | high | Sep 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 42 | | 48.8% | on | Jun 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 43 | GPT-4.1 nano | 48.7% | none | Apr 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 44 | | 45.6% | off | Mar 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 45 | | 43.4% | high | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 46 | | 42.6% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 47 | | 37.5% | on | Apr 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 48 | Llama 3.1 70B Instruct 70B | 37.3% | none | Oct 2026 | huggingface.co | Official leaderboard | |
| 49 | GPT-3.5 Turbo Jan 2024 | 36.1% | none | Jan 2024 | Sep 2026 | platform.openai.com | Official leaderboard |
| 50 | Claude Haiku 4.5 | 35.4% | off | Oct 2025 | Sep 2026 | anthropic.com | Official leaderboard |
| 51 | | 34.4% | high | Apr 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 52 | | 34% | high | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 53 | | 33.3% | on | Apr 2026 | Sep 2026 | deepmind.google | Official leaderboard |
| 54 | Llama 3.1 8B Instruct 8B | 31.4% | none | Oct 2026 | huggingface.co | Official leaderboard | |
| 55 | | 30.9% | off | Aug 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 56 | | 29.1% | none | Sep 2025 | Sep 2026 | huggingface.co | Official leaderboard |
| 57 | | 25.9% | on | Jun 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 58 | | 25.3% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 59 | | 24.3% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 60 | | 24.1% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 61 | GLM-5.3-Flash | 21.7% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 62 | Ripple-65B Preview | 18.3% | on | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | GPT-6.2 Sol | 87.7% | high | Nov 2026 | Nov 2026 | developers.openai.com | Official leaderboard |
| 2 | GPT-6.1 Terra | 84.3% | off | Oct 2026 | Oct 2026 | developers.openai.com | Official leaderboard |
| 3 | GPT-6 Sol | 83.8% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 4 | Claude Fable 5.2 | 82.9% | low | Nov 2026 | Nov 2026 | anthropic.com | Official leaderboard |
| 5 | GPT-6 Luna | 82.3% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 6 | GPT-6 Astra | 82.2% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 7 | | 79.4% | high | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 8 | GPT-6.1 Sol | 78.8% | low | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 9 | GPT-5.6 Luna | 78.7% | off | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 10 | GPT-5.6 Sol | 78.7% | off | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 11 | | 78.3% | low | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 12 | Grok 4.7 | 77.8% | low | Sep 2026 | Nov 2026 | docs.x.ai | Official leaderboard |
| 13 | | 75.6% | low | Oct 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 14 | | 75.6% | on | Apr 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 15 | Claude Sonnet 5.5 | 74.9% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 16 | | 74.9% | high | Sep 2026 | Oct 2026 | ai.google.dev | Official leaderboard |
| 17 | GPT-5.6 Terra | 74.6% | off | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 18 | Claude Opus 5.5 | 74.5% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 19 | | 74.3% | high | Feb 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 20 | Claude Fable 5.1 | 73.7% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 21 | Claude Opus 5 | 72.3% | off | Jul 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 22 | | 71.4% | low | Aug 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 23 | Claude Opus 4.8 | 70.7% | high | May 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 24 | Claude Sonnet 5 | 70.2% | high | Jun 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 25 | Claude Haiku 5.5 | 69% | high | Oct 2026 | Oct 2026 | anthropic.com | Official leaderboard |
| 26 | GPT-4o Mar 2025 | 68.6% | none | Mar 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 27 | | 67.8% | low | Sep 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 28 | | 65.6% | on | Sep 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 29 | GPT-5.2 | 64.8% | off | Dec 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 30 | | 64% | minimal | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 31 | | 63.9% | minimal | Jun 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 32 | | 62.8% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 33 | | 62.6% | high | May 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 34 | | 61.7% | off | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 35 | | 61% | high | Oct 2026 | Oct 2026 | mistral.ai | Official leaderboard |
| 36 | | 57.9% | high | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 37 | Kimi K3 | 57.6% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 38 | | 57.5% | high | Jul 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 39 | | 55.2% | none | Dec 2025 | Sep 2026 | mistral.ai | Official leaderboard |
| 40 | | 55% | high | Sep 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 41 | | 48.8% | on | Jun 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 42 | GPT-4.1 nano | 48.7% | none | Apr 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 43 | | 45.6% | off | Mar 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 44 | | 43.4% | high | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 45 | | 42.6% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 46 | | 37.5% | on | Apr 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 47 | GPT-3.5 Turbo Jan 2024 | 36.1% | none | Jan 2024 | Sep 2026 | platform.openai.com | Official leaderboard |
| 48 | Claude Haiku 4.5 | 35.4% | off | Oct 2025 | Sep 2026 | anthropic.com | Official leaderboard |
| 49 | | 34.4% | high | Apr 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 50 | | 34% | high | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 51 | | 33.3% | on | Apr 2026 | Sep 2026 | deepmind.google | Official leaderboard |
| 52 | | 30.9% | off | Aug 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 53 | | 29.1% | none | Sep 2025 | Sep 2026 | huggingface.co | Official leaderboard |
| 54 | | 25.9% | on | Jun 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 55 | | 25.3% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 56 | | 24.3% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 57 | | 24.1% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 58 | GLM-5.3-Flash | 21.7% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 59 | Ripple-65B Preview | 18.3% | on | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: Grammar and Vocabulary. Each ranks models on one part of the test. GPT-6.2 Sol leads both. Arrows show how far a model moved from its overall rank among the models we track.
Grammar
59 models we track have a score here.
- 1 GPT-6.2 Sol 93.3%
- 2 GPT-6 Astra ↑4 92.1%
- 3 Claude Fable 5.2 ↑1 91.4%
- 4 GPT-6 Sol ↓1 90%
- 5 GPT-5.6 Sol ↑5 89.9%
- 6 GPT-6.1 Sol ↑2 89.8%
- 7 GPT-5.6 Luna ↑2 88.1%
- 8 GPT-6.1 Terra ↓6 87.9%
- 9 Claude Opus 5.5 ↑9 86.6%
- 10
Gemini 4 Hydrogen ↓3 86.6%
Vocabulary
59 models we track have a score here.
- 1 GPT-6.2 Sol 82.1%
- 2 GPT-6 Sol ↑1 81.2%
- 3 GPT-6.1 Terra ↓1 80.8%
- 4 GPT-4o Mar 2025 ↑22 78.4%
- 5 GPT-6 Luna 78%
- 6 Grok 4.7 ↑6 77%
- 7 GPT-5.6 Luna ↑2 75.1%
- 8 Claude Fable 5.2 ↓4 74.4%
- 9
DeepSeek-V4-Pro ↑5 73.6%
- 10 GPT-6 Astra ↓4 73.3%
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official Miðeind Icelandic Generative Quality leaderboard
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official Miðeind Icelandic Generative Quality leaderboard
5 models have held number one on the official leaderboard since its release in September 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Miðeind Icelandic Generative Quality leaderboard
GPT-6.2 Sol on the official leaderboard passed 85% in November 2026
That was 2 months after its release. By the same age, 21% of the benchmarks from 2026 had passed 85%. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Miðeind Icelandic Generative Quality leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Multilingual
- MMMLU In use MMLU professionally translated into 14 languages. Multiple-choice accuracy. Claude Mythos Preview 92.7%
- WMT24++ In use English-to-55-language translation of WMT24 test data. Scored with automatic metrics such as MetricX or xCOMET.
K-EXAONE 90.5%
- MMLU-ProX In use MMLU-Pro translated into up to 29 languages with expert review. Multiple-choice accuracy per language.
Qwen3.7-Max 87%
- CLIcK In use Models answer 1,995 multiple-choice questions on Korean language and culture. Questions come from official Korean exams and textbooks in eleven categories.
Solar Open 2 90.7%
- Global MMLU Lite 3.0 In use Models answer 400 human-translated MMLU questions per language in 23 languages. Version 3.0 adds Czech, Hungarian, Oriya, Slovak and Tajik and updates Italian. Accuracy. Claude Opus 5 95.7%
- MMMB In use Models answer multiple-choice questions about images in six languages across 15 categories. The set has about 12,000 questions. LFM2.5-VL-3B 83%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (62 entries).
- Pass Models scored 59 models we track, plus 3 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
- Pass Frontier models 9 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Note Headroom Saturated. The best is 87.7%, past 85% since November 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on mideind-icelandic-llm-leaderboard.static.hf.space: 101 rows for models we track and 3 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.