Miðeind Icelandic Grammar Correction
Models correct an Icelandic sentence or return it unchanged. Half the sentences contain one error. The score measures exact agreement with the expected sentence.
Passes test 2. Miðeind reports scores for 60 named models on its current leaderboard. The board reports separate scores for sentences with and without errors.
- 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
- Items from
- Written by experts
- 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
Claude Fable 5.2 leads with 83.9% Claude Fable 5.2 leads with 83.9%
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.
- 83.9 Claude Fable 5.2
- 83.0 Claude Opus 5
- 81.7 Claude Fable 5.1
- 81.2 GPT-6 Astra
- 80.7 Claude Opus 5.5
- 80.7
Gemini 4 Argon
- 80.7
Gemini 4 Neon
- 79.4 GPT-6.1 Terra
- 78.4 GPT-6.2 Sol
- 78.0
Gemini 4 Hydrogen
- 74.8 GPT-6 Sol
- 74.3 GPT-6.1 Sol
- 73.4
Gemini 3.1 Pro
- 72.9 Claude Opus 4.8
- 71.1
Gemini 4 Carbon
- 70.6 GPT-5.6 Sol
- 67.4 Claude Sonnet 5.5
- 67.0
Gemini 3.5 Flash
- 66.5
Gemini 3.7 Flash
- 64.2 Claude Haiku 5.5
- 63.3
Gemini 3.8 Flash
- 59.6 Claude Sonnet 5
- 58.3 GPT-5.6 Terra
- 57.8 GPT-5.6 Luna
- 56.9
Inkling 2 Small
- 56.4 Grok 4.7
- 56.0 GPT-6 Luna
- 54.6
DeepSeek V4.1 Flash
- 51.4
DeepSeek-V4-Pro
- 49.5 Bielik 11B v3.1 Instruct
- 49.1
Gemini 3.5 Flash-Lite
- 49.1
Muse Spark Open
- 46.3 Kimi K3
- 45.0
Qwen3.8-2.4T-A95B
- 44.5
MiniMax-M3.1-Flash
- 44.0
Gemma 4 E2B
- 42.7
Gemini 2.5 Flash-Lite
- 41.3
Gemini 2.5 Pro
- 40.8
Inkling
- 37.2
MiniMax-M3
- 36.7
Gemma 4 12B
- 36.2
Gemma 4 26B A4B
- 35.8 GPT-5.2
- 35.3 GLM-5.3-Flash
- 34.4 GPT-4.1 nano
- 33.9 GPT-4o
- 33.9
Mistral Small 4
- 33.5
Apertus 1.5 70B
- 30.7
Inkling-Small
- 29.8
Gemma 4 E4B
- 27.1
Qwen 3.8 27B
- 25.7
Mistral Large 4
- 21.6
Apertus 1.5 8B
- 20.2
Mistral Medium 3.5
- 19.7
Gemma 4 31B IT
- 18.8
Mistral Large 3
- 17.4 GPT-3.5 Turbo
- 17.0
Llama 3.1-70B
- 14.7 Claude Haiku 4.5
- 10.6 Ripple-65B Preview
- 8.26
Llama 3.1-8B
- 2.29
Apertus 8B Instruct
- 1 Claude Fable 5.2 high 83.9%
- 2 Claude Opus 5 high 83%
- 3 Claude Fable 5.1 high 81.7%
- 4 GPT-6 Astra high 81.2%
- 5 Claude Opus 5.5 high 80.7%
- 6
Gemini 4 Argon high 80.7%
- 7
Gemini 4 Neon low 80.7%
- 8 GPT-6.1 Terra high 79.4%
- 9 GPT-6.2 Sol high 78.4%
- 10
Gemini 4 Hydrogen high 78%
- 11 GPT-6 Sol high 74.8%
- 12 GPT-6.1 Sol high 74.3%
- 13
Gemini 3.1 Pro low 73.4%
- 14 Claude Opus 4.8 high 72.9%
- 15
Gemini 4 Carbon low 71.1%
- 16 GPT-5.6 Sol high 70.6%
- 17 Claude Sonnet 5.5 high 67.4%
- 18
Gemini 3.5 Flash high 67%
- 19
Gemini 3.7 Flash high 66.5%
- 20 Claude Haiku 5.5 high 64.2%
- 21
Gemini 3.8 Flash high 63.3%
- 22 Claude Sonnet 5 off 59.6%
- 23 GPT-5.6 Terra high 58.3%
- 24 GPT-5.6 Luna high 57.8%
- 25
Inkling 2 Small high 56.9%
- 26 Grok 4.7 high 56.4%
- 27 GPT-6 Luna high 56%
- 28
DeepSeek V4.1 Flash on 54.6%
- 29
DeepSeek-V4-Pro off 51.4%
- 30 Bielik 11B v3.1 Instruct off 49.5%
- 31
Gemini 3.5 Flash-Lite off 49.1%
- 32
Muse Spark Open high 49.1%
- 33 Kimi K3 off 46.3%
- 34
Qwen3.8-2.4T-A95B on 45%
- 35
MiniMax-M3.1-Flash off 44.5%
- 36
Gemma 4 E2B off 44%
- 37
Gemini 2.5 Flash-Lite Sep 2025, off 42.7%
- 38
Gemini 2.5 Pro Jun 2025, high 41.3%
- 39
Inkling off 40.8%
- 40
MiniMax-M3 on 37.2%
- 41
Gemma 4 12B off 36.7%
- 42
Gemma 4 26B A4B off 36.2%
- 43 GPT-5.2 off 35.8%
- 44 GLM-5.3-Flash on 35.3%
- 45 GPT-4.1 nano none 34.4%
- 46 GPT-4o Mar 2025, none 33.9%
- 47
Mistral Small 4 off 33.9%
- 48
Apertus 1.5 70B on 33.5%
- 49
Inkling-Small high 30.7%
- 50
Gemma 4 E4B off 29.8%
- 51
Qwen 3.8 27B off 27.1%
- 52
Mistral Large 4 low 25.7%
- 53
Apertus 1.5 8B on 21.6%
- 54
Mistral Medium 3.5 off 20.2%
- 55
Gemma 4 31B IT on 19.7%
- 56
Mistral Large 3 none 18.8%
- 57 GPT-3.5 Turbo Jan 2024, none 17.4%
- 58
Llama 3.1-70B none 17%
- 59 Claude Haiku 4.5 off 14.7%
- 60 Ripple-65B Preview on 10.6%
- 61
Llama 3.1-8B none 8.26%
- 62
Apertus 8B Instruct none 2.29%
Source: Official Miðeind Icelandic Grammar Correction leaderboard
- 83.9 Claude Fable 5.2
- 83.0 Claude Opus 5
- 81.7 Claude Fable 5.1
- 81.2 GPT-6 Astra
- 80.7 Claude Opus 5.5
- 80.7
Gemini 4 Argon
- 80.7
Gemini 4 Neon
- 79.4 GPT-6.1 Terra
- 78.4 GPT-6.2 Sol
- 78.0
Gemini 4 Hydrogen
- 74.8 GPT-6 Sol
- 74.3 GPT-6.1 Sol
- 73.4
Gemini 3.1 Pro
- 72.9 Claude Opus 4.8
- 71.1
Gemini 4 Carbon
- 70.6 GPT-5.6 Sol
- 67.4 Claude Sonnet 5.5
- 67.0
Gemini 3.5 Flash
- 66.5
Gemini 3.7 Flash
- 64.2 Claude Haiku 5.5
- 63.3
Gemini 3.8 Flash
- 59.6 Claude Sonnet 5
- 58.3 GPT-5.6 Terra
- 57.8 GPT-5.6 Luna
- 56.9
Inkling 2 Small
- 56.4 Grok 4.7
- 56.0 GPT-6 Luna
- 54.6
DeepSeek V4.1 Flash
- 51.4
DeepSeek-V4-Pro
- 49.1
Gemini 3.5 Flash-Lite
- 49.1
Muse Spark Open
- 46.3 Kimi K3
- 45.0
Qwen3.8-2.4T-A95B
- 44.5
MiniMax-M3.1-Flash
- 44.0
Gemma 4 E2B
- 42.7
Gemini 2.5 Flash-Lite
- 41.3
Gemini 2.5 Pro
- 40.8
Inkling
- 37.2
MiniMax-M3
- 36.7
Gemma 4 12B
- 36.2
Gemma 4 26B A4B
- 35.8 GPT-5.2
- 35.3 GLM-5.3-Flash
- 34.4 GPT-4.1 nano
- 33.9 GPT-4o
- 33.9
Mistral Small 4
- 33.5
Apertus 1.5 70B
- 30.7
Inkling-Small
- 29.8
Gemma 4 E4B
- 27.1
Qwen 3.8 27B
- 25.7
Mistral Large 4
- 21.6
Apertus 1.5 8B
- 20.2
Mistral Medium 3.5
- 19.7
Gemma 4 31B IT
- 18.8
Mistral Large 3
- 17.4 GPT-3.5 Turbo
- 17.0
Llama 3.1-70B
- 14.7 Claude Haiku 4.5
- 10.6 Ripple-65B Preview
- 8.26
Llama 3.1-8B
- 2.29
Apertus 8B Instruct
- 1 Claude Fable 5.2 high 83.9%
- 2 Claude Opus 5 high 83%
- 3 Claude Fable 5.1 high 81.7%
- 4 GPT-6 Astra high 81.2%
- 5 Claude Opus 5.5 high 80.7%
- 6
Gemini 4 Argon high 80.7%
- 7
Gemini 4 Neon low 80.7%
- 8 GPT-6.1 Terra high 79.4%
- 9 GPT-6.2 Sol high 78.4%
- 10
Gemini 4 Hydrogen high 78%
- 11 GPT-6 Sol high 74.8%
- 12 GPT-6.1 Sol high 74.3%
- 13
Gemini 3.1 Pro low 73.4%
- 14 Claude Opus 4.8 high 72.9%
- 15
Gemini 4 Carbon low 71.1%
- 16 GPT-5.6 Sol high 70.6%
- 17 Claude Sonnet 5.5 high 67.4%
- 18
Gemini 3.5 Flash high 67%
- 19
Gemini 3.7 Flash high 66.5%
- 20 Claude Haiku 5.5 high 64.2%
- 21
Gemini 3.8 Flash high 63.3%
- 22 Claude Sonnet 5 off 59.6%
- 23 GPT-5.6 Terra high 58.3%
- 24 GPT-5.6 Luna high 57.8%
- 25
Inkling 2 Small high 56.9%
- 26 Grok 4.7 high 56.4%
- 27 GPT-6 Luna high 56%
- 28
DeepSeek V4.1 Flash on 54.6%
- 29
DeepSeek-V4-Pro off 51.4%
- 30
Gemini 3.5 Flash-Lite off 49.1%
- 31
Muse Spark Open high 49.1%
- 32 Kimi K3 off 46.3%
- 33
Qwen3.8-2.4T-A95B on 45%
- 34
MiniMax-M3.1-Flash off 44.5%
- 35
Gemma 4 E2B off 44%
- 36
Gemini 2.5 Flash-Lite Sep 2025, off 42.7%
- 37
Gemini 2.5 Pro Jun 2025, high 41.3%
- 38
Inkling off 40.8%
- 39
MiniMax-M3 on 37.2%
- 40
Gemma 4 12B off 36.7%
- 41
Gemma 4 26B A4B off 36.2%
- 42 GPT-5.2 off 35.8%
- 43 GLM-5.3-Flash on 35.3%
- 44 GPT-4.1 nano none 34.4%
- 45 GPT-4o Mar 2025, none 33.9%
- 46
Mistral Small 4 off 33.9%
- 47
Apertus 1.5 70B on 33.5%
- 48
Inkling-Small high 30.7%
- 49
Gemma 4 E4B off 29.8%
- 50
Qwen 3.8 27B off 27.1%
- 51
Mistral Large 4 low 25.7%
- 52
Apertus 1.5 8B on 21.6%
- 53
Mistral Medium 3.5 off 20.2%
- 54
Gemma 4 31B IT on 19.7%
- 55
Mistral Large 3 none 18.8%
- 56 GPT-3.5 Turbo Jan 2024, none 17.4%
- 57
Llama 3.1-70B none 17%
- 58 Claude Haiku 4.5 off 14.7%
- 59 Ripple-65B Preview on 10.6%
- 60
Llama 3.1-8B none 8.26%
- 61
Apertus 8B Instruct none 2.29%
Source: Official Miðeind Icelandic Grammar Correction leaderboard
| # | Entry | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 83.9% | high | Nov 2026 | Nov 2026 | anthropic.com | Official leaderboard |
| 2 | Claude Opus 5 | 83% | high | Jul 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 3 | Claude Fable 5.1 | 81.7% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 4 | GPT-6 Astra | 81.2% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 5 | Claude Opus 5.5 | 80.7% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 6 | | 80.7% | high | Sep 2026 | Oct 2026 | ai.google.dev | Official leaderboard |
| 7 | | 80.7% | low | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 8 | GPT-6.1 Terra | 79.4% | high | Oct 2026 | Oct 2026 | developers.openai.com | Official leaderboard |
| 9 | GPT-6.2 Sol | 78.4% | high | Nov 2026 | Nov 2026 | developers.openai.com | Official leaderboard |
| 10 | | 78% | high | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 11 | GPT-6 Sol | 74.8% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 12 | GPT-6.1 Sol | 74.3% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 13 | | 73.4% | low | Feb 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 14 | Claude Opus 4.8 | 72.9% | high | May 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 15 | | 71.1% | low | Oct 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 16 | GPT-5.6 Sol | 70.6% | high | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 17 | Claude Sonnet 5.5 | 67.4% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 18 | | 67% | high | May 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 19 | | 66.5% | high | Aug 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 20 | Claude Haiku 5.5 | 64.2% | high | Oct 2026 | Oct 2026 | anthropic.com | Official leaderboard |
| 21 | | 63.3% | high | Sep 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 22 | Claude Sonnet 5 | 59.6% | off | Jun 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 23 | GPT-5.6 Terra | 58.3% | high | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 24 | GPT-5.6 Luna | 57.8% | high | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 25 | | 56.9% | high | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 26 | Grok 4.7 | 56.4% | high | Sep 2026 | Nov 2026 | docs.x.ai | Official leaderboard |
| 27 | GPT-6 Luna | 56% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 28 | | 54.6% | on | Sep 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 29 | | 51.4% | off | Apr 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 30 | Bielik 11B v3.1 Instruct 11.2B | 49.5% | off | Nov 2026 | huggingface.co | Official leaderboard | |
| 31 | | 49.1% | off | Jul 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 32 | | 49.1% | high | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 33 | Kimi K3 | 46.3% | off | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 34 | | 45% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 35 | | 44.5% | off | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 36 | | 44% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 37 | | 42.7% | off | Sep 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 38 | | 41.3% | high | Jun 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 39 | | 40.8% | off | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 40 | | 37.2% | on | Jun 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 41 | | 36.7% | off | Jun 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 42 | | 36.2% | off | Apr 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 43 | GPT-5.2 | 35.8% | off | Dec 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 44 | GLM-5.3-Flash | 35.3% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 45 | GPT-4.1 nano | 34.4% | none | Apr 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 46 | GPT-4o Mar 2025 | 33.9% | none | Mar 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 47 | | 33.9% | off | Mar 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 48 | | 33.5% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 49 | | 30.7% | high | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 50 | | 29.8% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 51 | | 27.1% | off | Aug 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 52 | | 25.7% | low | Oct 2026 | Oct 2026 | mistral.ai | Official leaderboard |
| 53 | | 21.6% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 54 | | 20.2% | off | Apr 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 55 | | 19.7% | on | Apr 2026 | Sep 2026 | deepmind.google | Official leaderboard |
| 56 | | 18.8% | none | Dec 2025 | Sep 2026 | mistral.ai | Official leaderboard |
| 57 | GPT-3.5 Turbo Jan 2024 | 17.4% | none | Jan 2024 | Sep 2026 | platform.openai.com | Official leaderboard |
| 58 | | 17% | none | Jul 2024 | Oct 2026 | huggingface.co | Official leaderboard |
| 59 | Claude Haiku 4.5 | 14.7% | off | Oct 2025 | Sep 2026 | anthropic.com | Official leaderboard |
| 60 | Ripple-65B Preview | 10.6% | on | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 61 | | 8.26% | none | Jul 2024 | Oct 2026 | huggingface.co | Official leaderboard |
| 62 | | 2.29% | none | Sep 2025 | Sep 2026 | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.2 | 83.9% | high | Nov 2026 | Nov 2026 | anthropic.com | Official leaderboard |
| 2 | Claude Opus 5 | 83% | high | Jul 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 3 | Claude Fable 5.1 | 81.7% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 4 | GPT-6 Astra | 81.2% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 5 | Claude Opus 5.5 | 80.7% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 6 | | 80.7% | high | Sep 2026 | Oct 2026 | ai.google.dev | Official leaderboard |
| 7 | | 80.7% | low | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 8 | GPT-6.1 Terra | 79.4% | high | Oct 2026 | Oct 2026 | developers.openai.com | Official leaderboard |
| 9 | GPT-6.2 Sol | 78.4% | high | Nov 2026 | Nov 2026 | developers.openai.com | Official leaderboard |
| 10 | | 78% | high | Nov 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 11 | GPT-6 Sol | 74.8% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 12 | GPT-6.1 Sol | 74.3% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 13 | | 73.4% | low | Feb 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 14 | Claude Opus 4.8 | 72.9% | high | May 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 15 | | 71.1% | low | Oct 2026 | Nov 2026 | ai.google.dev | Official leaderboard |
| 16 | GPT-5.6 Sol | 70.6% | high | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 17 | Claude Sonnet 5.5 | 67.4% | high | Sep 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 18 | | 67% | high | May 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 19 | | 66.5% | high | Aug 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 20 | Claude Haiku 5.5 | 64.2% | high | Oct 2026 | Oct 2026 | anthropic.com | Official leaderboard |
| 21 | | 63.3% | high | Sep 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 22 | Claude Sonnet 5 | 59.6% | off | Jun 2026 | Sep 2026 | anthropic.com | Official leaderboard |
| 23 | GPT-5.6 Terra | 58.3% | high | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 24 | GPT-5.6 Luna | 57.8% | high | Jul 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 25 | | 56.9% | high | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 26 | Grok 4.7 | 56.4% | high | Sep 2026 | Nov 2026 | docs.x.ai | Official leaderboard |
| 27 | GPT-6 Luna | 56% | high | Sep 2026 | Sep 2026 | developers.openai.com | Official leaderboard |
| 28 | | 54.6% | on | Sep 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 29 | | 51.4% | off | Apr 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 30 | | 49.1% | off | Jul 2026 | Sep 2026 | ai.google.dev | Official leaderboard |
| 31 | | 49.1% | high | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 32 | Kimi K3 | 46.3% | off | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 33 | | 45% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 34 | | 44.5% | off | Oct 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 35 | | 44% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 36 | | 42.7% | off | Sep 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 37 | | 41.3% | high | Jun 2025 | Sep 2026 | ai.google.dev | Official leaderboard |
| 38 | | 40.8% | off | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 39 | | 37.2% | on | Jun 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 40 | | 36.7% | off | Jun 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 41 | | 36.2% | off | Apr 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 42 | GPT-5.2 | 35.8% | off | Dec 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 43 | GLM-5.3-Flash | 35.3% | on | Aug 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 44 | GPT-4.1 nano | 34.4% | none | Apr 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 45 | GPT-4o Mar 2025 | 33.9% | none | Mar 2025 | Sep 2026 | platform.openai.com | Official leaderboard |
| 46 | | 33.9% | off | Mar 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 47 | | 33.5% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 48 | | 30.7% | high | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 49 | | 29.8% | off | Mar 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 50 | | 27.1% | off | Aug 2026 | Oct 2026 | huggingface.co | Official leaderboard |
| 51 | | 25.7% | low | Oct 2026 | Oct 2026 | mistral.ai | Official leaderboard |
| 52 | | 21.6% | on | Jul 2026 | Sep 2026 | huggingface.co | Official leaderboard |
| 53 | | 20.2% | off | Apr 2026 | Sep 2026 | mistral.ai | Official leaderboard |
| 54 | | 19.7% | on | Apr 2026 | Sep 2026 | deepmind.google | Official leaderboard |
| 55 | | 18.8% | none | Dec 2025 | Sep 2026 | mistral.ai | Official leaderboard |
| 56 | GPT-3.5 Turbo Jan 2024 | 17.4% | none | Jan 2024 | Sep 2026 | platform.openai.com | Official leaderboard |
| 57 | | 17% | none | Jul 2024 | Oct 2026 | huggingface.co | Official leaderboard |
| 58 | Claude Haiku 4.5 | 14.7% | off | Oct 2025 | Sep 2026 | anthropic.com | Official leaderboard |
| 59 | Ripple-65B Preview | 10.6% | on | Nov 2026 | Nov 2026 | huggingface.co | Official leaderboard |
| 60 | | 8.26% | none | Jul 2024 | Oct 2026 | huggingface.co | Official leaderboard |
| 61 | | 2.29% | none | Sep 2025 | Sep 2026 | huggingface.co | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s own leaderboard: With error and Error free. Each ranks models on one part of the test. Gemini 3.1 Pro leads With error and Claude Fable 5.1 leads Error free. Arrows show how far a model moved from its overall rank among the models we track.
With error
61 models we track have a score here.
- 1
Gemini 3.1 Pro ↑12 79.8%
- 2 Claude Opus 5 79.8%
- 3 Claude Fable 5.2 ↓2 79.8%
- 4 GPT-6 Astra 78.9%
- 5 GPT-6.2 Sol ↑4 78%
- 6
Gemini 3.8 Flash ↑15 77.1%
- 7
Gemini 4 Argon ↓1 77.1%
- 8 Claude Opus 5.5 ↓3 75.2%
- 9 GPT-6.1 Sol ↑3 75.2%
- 10
Gemini 4 Carbon ↑5 75.2%
Error free
61 models we track have a score here.
- 1 Claude Fable 5.1 ↑2 93.6%
- 2
Gemini 4 Neon ↑5 89.9%
- 3
Gemma 4 E2B ↑32 88.1%
- 4 Claude Haiku 5.5 ↑16 88.1%
- 5 Claude Fable 5.2 ↓4 88.1%
- 6
Gemini 4 Hydrogen ↑4 87.2%
- 7 Claude Opus 5 ↓5 86.2%
- 8 Claude Opus 5.5 ↓3 86.2%
- 9
MiniMax-M3.1-Flash ↑25 86.2%
- 10 GPT-6.1 Terra ↓2 86.2%
More effort adds a median 5 points
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 Grammar Correction leaderboard
More effort adds a median 5 points
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 Grammar Correction leaderboard
2 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 Grammar Correction leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Miðeind Icelandic Grammar Correction 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 11 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access The tasks are private.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (62 entries).
- Pass Models scored 61 models we track, plus 1 other entry 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).
- Pass Headroom The best is 83.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on mideind-icelandic-llm-leaderboard.static.hf.space: 103 rows for models we track and 1 other entry 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.