Miðeind Icelandic Grammatical Error Detection
Models decide whether an Icelandic sentence contains a grammatical error. The test uses 100 correct sentences and 100 incorrect sentences from the Icelandic Error Corpus.
Passes test 2. Miðeind reports scores for 94 named models on its archived leaderboard.
- Made by
- Miðeind
- Released
- December 2023
- Kind
- Reading in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Icelandic
- Interaction
- Single turn
- Items from
- Another benchmark
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- Claude Fable 5 #12 on the capability index
- Last model added
- August 2026
- Scores refreshed
- November 20th, 2026
Claude Fable 5 leads with 91.5% among models released by August 2026 Claude Fable 5 leads with 91.5% among models released by August 2026
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. 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.
The newest model with a score here came out in August 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 13 more
- 91.5 Claude Fable 5
- 84.5 Claude Opus 4.7
- 84.0 Claude Opus 4.8
- 82.0
Gemini 3.7 Flash
- 81.0
Gemini 3 Pro
- 80.5
Gemini 3.1 Pro
- 78.0 GPT-5.4
- 77.5 Claude Sonnet 4.6
- 77.5 GPT-5.5
- 76.5 Claude Opus 4.6
- 76.5
Gemini 3.6 Flash
- 75.5 GPT-5.6 Sol
- 75.0 GPT-5.1
- 75.0
Gemini 3.5 Flash
- 74.5 o1-preview
- 74.5 Claude Opus 4.5
- 74.5 GPT-5.6 Luna
- 73.5
Gemini 3 Flash
- 72.5 Claude 3.5 Sonnet
- 72.5
Gemini 2.5 Flash
- 72.5
Gemini 3.1 Flash-Lite
- 71.5
Gemini 2.5 Pro
- 71.5 GPT-5
- 70.0 GPT-5.6 Terra
- 69.5 GPT-5.2
- 68.0 GPT-4o
- 67.0 Claude 3.7 Sonnet
- 66.5 GPT-4.1
- 66.0 Grok 4.3
- 65.0 GPT-4o
- 64.0 Kimi K2.5
- 64.0
Gemma 4 31B IT
- 63.5 Claude 3 Opus
- 63.5
Qwen3.5 397B-A17B
- 63.0
Gemini 2.5 Flash-Lite
- 62.5
Gemini 2.0 Flash
- 62.5 o4-mini
- 62.5
DeepSeek-V4-Pro
- 62.0 GLM-5.2
- 61.5 Claude 3.5 Haiku
- 60.5 GPT-4 Turbo
- 60.5 GPT-5 mini
- 60.5 Claude Sonnet 4.5
- 60.0
Gemini 2.0 Pro
- 59.5 GPT-5 nano
- 59.0 GPT-4.1 mini
- 59.0
DeepSeek-R1
- 59.0
MiniMax-M2.5
- 59.0
Gemma 4 26B A4B
- 58.5
Gemma 3 27B
- 58.5
Mistral Large 3
- 58.0 o3-mini
- 57.0 GPT-4o mini
- 57.0
DeepSeek-V3
- 57.0 GPT-4.1 nano
- 56.5 Claude Sonnet 4
- 56.5
Mistral Medium 3.1
- 56.0 cyboghostginx/gemma-3-4b-it-Adetayo
- 55.5 GPT-4
- 55.0
DeepSeek-R1-Distill-Llama-70B
- 54.5 cyboghostginx/gemma-3-27b-it-Adetayo
- 54.0
Gemma 3 12B
- 53.5 NousResearch/Hermes-3-Llama-3.1-405B-FP8
- 53.0 GPT-4
- 53.0
Mistral NeMo
- 53.0
Llama 3.1-70B
- 52.5 Claude 2.1
- 52.5
Llama-3.1-Nemotron-70B-Instruct
- 52.5
Llama 3.3 70B Instruct
- 52.0 GPT-3.5 Turbo
- 52.0
Llama 3-8B
- 52.0
Gemma 3 4B
- 51.5 AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct
- 51.5 LumiOpen/Viking-33B
- 51.0 AI-Sweden-Models/gpt-sw3-126m-instruct
- 51.0 cyboghostginx/gemma-4-31B-it-Adetayo
- 51.0
Qwen2-7B-Instruct
- 51.0
Gemma 2 9B
- 51.0 o1-mini
- 51.0
Ministral 3B
- 50.5 AI-Sweden-Models/gpt-sw3-1.3b-instruct
- 50.0 AI-Sweden-Models/gpt-sw3-20b-instruct
- 50.0
Llama 3.1-8B
- 50.0
Llama 3.2 1B
- 49.5 LumiOpen/Viking-13B
- 49.5
Gemma 3 1B
- 49.0
Llama 3-70B
- 49.0
Llama 3.2 3B
- 48.5
Qwen2-72B
- 48.0 AI-Sweden-Models/gpt-sw3-356m-instruct
- 48.0 Sigurdur/icebreaker
- 40.0 LumiOpen/Viking-7B
- 1 Claude Fable 5 high 91.5%
- 2 Claude Opus 4.7 high 84.5%
- 3 Claude Opus 4.8 high 84%
- 4
Gemini 3.7 Flash high 82%
- 5
Gemini 3 Pro high 81%
- 6
Gemini 3.1 Pro high 80.5%
- 7 GPT-5.4 high 78%
- 8 Claude Sonnet 4.6 high 77.5%
- 9 GPT-5.5 high 77.5%
- 10 Claude Opus 4.6 high 76.5%
- 11
Gemini 3.6 Flash high 76.5%
- 12 GPT-5.6 Sol high 75.5%
- 13 GPT-5.1 high 75%
- 14
Gemini 3.5 Flash high 75%
- 15 o1-preview on 74.5%
- 16 Claude Opus 4.5 high 74.5%
- 17 GPT-5.6 Luna high 74.5%
- 18
Gemini 3 Flash high 73.5%
- 19 Claude 3.5 Sonnet 72.5%
- 20
Gemini 2.5 Flash Sep 2025, high 72.5%
- 21
Gemini 3.1 Flash-Lite high 72.5%
- 22
Gemini 2.5 Pro Jun 2025, on 71.5%
- 23 GPT-5 high 71.5%
- 24 GPT-5.6 Terra high 70%
- 25 GPT-5.2 high 69.5%
- 26 GPT-4o Aug 2024 68%
- 27 Claude 3.7 Sonnet 67%
- 28 GPT-4.1 66.5%
- 29 Grok 4.3 on 66%
- 30 GPT-4o May 2024 65%
- 31 Kimi K2.5 on 64%
- 32
Gemma 4 31B IT on 64%
- 33 Claude 3 Opus 63.5%
- 34
Qwen3.5 397B-A17B on 63.5%
- 35
Gemini 2.5 Flash-Lite Sep 2025, high 63%
- 36
Gemini 2.0 Flash Feb 2025 62.5%
- 37 o4-mini on 62.5%
- 38
DeepSeek-V4-Pro on 62.5%
- 39 GLM-5.2 on 62%
- 40 Claude 3.5 Haiku 61.5%
- 41 GPT-4 Turbo Apr 2024 60.5%
- 42 GPT-5 mini high 60.5%
- 43 Claude Sonnet 4.5 high 60.5%
- 44
Gemini 2.0 Pro on 60%
- 45 GPT-5 nano high 59.5%
- 46 GPT-4.1 mini 59%
- 47
DeepSeek-R1 May 2025, on 59%
- 48
MiniMax-M2.5 on 59%
- 49
Gemma 4 26B A4B on 59%
- 50
Gemma 3 27B 58.5%
- 51
Mistral Large 3 58.5%
- 52 o3-mini on 58%
- 53 GPT-4o mini 57%
- 54
DeepSeek-V3 Mar 2025 57%
- 55 GPT-4.1 nano 57%
- 56 Claude Sonnet 4 on 56.5%
- 57
Mistral Medium 3.1 56.5%
- 58 cyboghostginx/gemma-3-4b-it-Adetayo 56%
- 59 GPT-4 Mar 2023 55.5%
- 60
DeepSeek-R1-Distill-Llama-70B on 55%
- 61 cyboghostginx/gemma-3-27b-it-Adetayo 54.5%
- 62
Gemma 3 12B 54%
- 63 NousResearch/Hermes-3-Llama-3.1-405B-FP8 53.5%
- 64 GPT-4 Jun 2023 53%
- 65
Mistral NeMo 53%
- 66
Llama 3.1-70B 53%
- 67 Claude 2.1 52.5%
- 68
Llama-3.1-Nemotron-70B-Instruct 52.5%
- 69
Llama 3.3 70B Instruct 52.5%
- 70 GPT-3.5 Turbo Jan 2024 52%
- 71
Llama 3-8B 52%
- 72
Gemma 3 4B 52%
- 73 AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct 51.5%
- 74 LumiOpen/Viking-33B 51.5%
- 75 AI-Sweden-Models/gpt-sw3-126m-instruct 51%
- 76 cyboghostginx/gemma-4-31B-it-Adetayo 51%
- 77
Qwen2-7B-Instruct 51%
- 78
Gemma 2 9B 51%
- 79 o1-mini on 51%
- 80
Ministral 3B 51%
- 81 AI-Sweden-Models/gpt-sw3-1.3b-instruct 50.5%
- 82 AI-Sweden-Models/gpt-sw3-20b-instruct 50%
- 83
Llama 3.1-8B 50%
- 84
Llama 3.2 1B 50%
- 85 LumiOpen/Viking-13B 49.5%
- 86
Gemma 3 1B 49.5%
- 87
Llama 3-70B 49%
- 88
Llama 3.2 3B 49%
- 89
Qwen2-72B 48.5%
- 90 AI-Sweden-Models/gpt-sw3-356m-instruct 48%
- 91 Sigurdur/icebreaker 48%
- 92 LumiOpen/Viking-7B 40%
Source: Official Miðeind Icelandic Grammatical Error Detection leaderboard
- 91.5 Claude Fable 5
- 84.5 Claude Opus 4.7
- 84.0 Claude Opus 4.8
- 82.0
Gemini 3.7 Flash
- 81.0
Gemini 3 Pro
- 80.5
Gemini 3.1 Pro
- 78.0 GPT-5.4
- 77.5 Claude Sonnet 4.6
- 77.5 GPT-5.5
- 76.5 Claude Opus 4.6
- 76.5
Gemini 3.6 Flash
- 75.5 GPT-5.6 Sol
- 75.0 GPT-5.1
- 75.0
Gemini 3.5 Flash
- 74.5 o1-preview
- 74.5 Claude Opus 4.5
- 74.5 GPT-5.6 Luna
- 73.5
Gemini 3 Flash
- 72.5 Claude 3.5 Sonnet
- 72.5
Gemini 2.5 Flash
- 72.5
Gemini 3.1 Flash-Lite
- 71.5
Gemini 2.5 Pro
- 71.5 GPT-5
- 70.0 GPT-5.6 Terra
- 69.5 GPT-5.2
- 68.0 GPT-4o
- 67.0 Claude 3.7 Sonnet
- 66.5 GPT-4.1
- 66.0 Grok 4.3
- 65.0 GPT-4o
- 64.0 Kimi K2.5
- 64.0
Gemma 4 31B IT
- 63.5 Claude 3 Opus
- 63.5
Qwen3.5 397B-A17B
- 63.0
Gemini 2.5 Flash-Lite
- 62.5
Gemini 2.0 Flash
- 62.5 o4-mini
- 62.5
DeepSeek-V4-Pro
- 62.0 GLM-5.2
- 61.5 Claude 3.5 Haiku
- 60.5 GPT-4 Turbo
- 60.5 GPT-5 mini
- 60.5 Claude Sonnet 4.5
- 60.0
Gemini 2.0 Pro
- 59.5 GPT-5 nano
- 59.0 GPT-4.1 mini
- 59.0
DeepSeek-R1
- 59.0
MiniMax-M2.5
- 59.0
Gemma 4 26B A4B
- 58.5
Gemma 3 27B
- 58.5
Mistral Large 3
- 58.0 o3-mini
- 57.0 GPT-4o mini
- 57.0
DeepSeek-V3
- 57.0 GPT-4.1 nano
- 56.5 Claude Sonnet 4
- 56.5
Mistral Medium 3.1
- 55.5 GPT-4
- 55.0
DeepSeek-R1-Distill-Llama-70B
- 54.0
Gemma 3 12B
- 53.0 GPT-4
- 53.0
Mistral NeMo
- 53.0
Llama 3.1-70B
- 52.5 Claude 2.1
- 52.5
Llama-3.1-Nemotron-70B-Instruct
- 52.5
Llama 3.3 70B Instruct
- 52.0 GPT-3.5 Turbo
- 52.0
Llama 3-8B
- 52.0
Gemma 3 4B
- 51.0
Qwen2-7B-Instruct
- 51.0
Gemma 2 9B
- 51.0 o1-mini
- 51.0
Ministral 3B
- 50.0
Llama 3.1-8B
- 50.0
Llama 3.2 1B
- 49.5
Gemma 3 1B
- 49.0
Llama 3-70B
- 49.0
Llama 3.2 3B
- 48.5
Qwen2-72B
- 1 Claude Fable 5 high 91.5%
- 2 Claude Opus 4.7 high 84.5%
- 3 Claude Opus 4.8 high 84%
- 4
Gemini 3.7 Flash high 82%
- 5
Gemini 3 Pro high 81%
- 6
Gemini 3.1 Pro high 80.5%
- 7 GPT-5.4 high 78%
- 8 Claude Sonnet 4.6 high 77.5%
- 9 GPT-5.5 high 77.5%
- 10 Claude Opus 4.6 high 76.5%
- 11
Gemini 3.6 Flash high 76.5%
- 12 GPT-5.6 Sol high 75.5%
- 13 GPT-5.1 high 75%
- 14
Gemini 3.5 Flash high 75%
- 15 o1-preview on 74.5%
- 16 Claude Opus 4.5 high 74.5%
- 17 GPT-5.6 Luna high 74.5%
- 18
Gemini 3 Flash high 73.5%
- 19 Claude 3.5 Sonnet 72.5%
- 20
Gemini 2.5 Flash Sep 2025, high 72.5%
- 21
Gemini 3.1 Flash-Lite high 72.5%
- 22
Gemini 2.5 Pro Jun 2025, on 71.5%
- 23 GPT-5 high 71.5%
- 24 GPT-5.6 Terra high 70%
- 25 GPT-5.2 high 69.5%
- 26 GPT-4o Aug 2024 68%
- 27 Claude 3.7 Sonnet 67%
- 28 GPT-4.1 66.5%
- 29 Grok 4.3 on 66%
- 30 GPT-4o May 2024 65%
- 31 Kimi K2.5 on 64%
- 32
Gemma 4 31B IT on 64%
- 33 Claude 3 Opus 63.5%
- 34
Qwen3.5 397B-A17B on 63.5%
- 35
Gemini 2.5 Flash-Lite Sep 2025, high 63%
- 36
Gemini 2.0 Flash Feb 2025 62.5%
- 37 o4-mini on 62.5%
- 38
DeepSeek-V4-Pro on 62.5%
- 39 GLM-5.2 on 62%
- 40 Claude 3.5 Haiku 61.5%
- 41 GPT-4 Turbo Apr 2024 60.5%
- 42 GPT-5 mini high 60.5%
- 43 Claude Sonnet 4.5 high 60.5%
- 44
Gemini 2.0 Pro on 60%
- 45 GPT-5 nano high 59.5%
- 46 GPT-4.1 mini 59%
- 47
DeepSeek-R1 May 2025, on 59%
- 48
MiniMax-M2.5 on 59%
- 49
Gemma 4 26B A4B on 59%
- 50
Gemma 3 27B 58.5%
- 51
Mistral Large 3 58.5%
- 52 o3-mini on 58%
- 53 GPT-4o mini 57%
- 54
DeepSeek-V3 Mar 2025 57%
- 55 GPT-4.1 nano 57%
- 56 Claude Sonnet 4 on 56.5%
- 57
Mistral Medium 3.1 56.5%
- 58 GPT-4 Mar 2023 55.5%
- 59
DeepSeek-R1-Distill-Llama-70B on 55%
- 60
Gemma 3 12B 54%
- 61 GPT-4 Jun 2023 53%
- 62
Mistral NeMo 53%
- 63
Llama 3.1-70B 53%
- 64 Claude 2.1 52.5%
- 65
Llama-3.1-Nemotron-70B-Instruct 52.5%
- 66
Llama 3.3 70B Instruct 52.5%
- 67 GPT-3.5 Turbo Jan 2024 52%
- 68
Llama 3-8B 52%
- 69
Gemma 3 4B 52%
- 70
Qwen2-7B-Instruct 51%
- 71
Gemma 2 9B 51%
- 72 o1-mini on 51%
- 73
Ministral 3B 51%
- 74
Llama 3.1-8B 50%
- 75
Llama 3.2 1B 50%
- 76
Gemma 3 1B 49.5%
- 77
Llama 3-70B 49%
- 78
Llama 3.2 3B 49%
- 79
Qwen2-72B 48.5%
Source: Official Miðeind Icelandic Grammatical Error Detection leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5 | 91.5% | high | Jun 2026 | anthropic.com | Official leaderboard |
| 2 | Claude Opus 4.7 | 84.5% | high | Apr 2026 | anthropic.com | Official leaderboard |
| 3 | Claude Opus 4.8 | 84% | high | May 2026 | anthropic.com | Official leaderboard |
| 4 | | 82% | high | Aug 2026 | ai.google.dev | Official leaderboard |
| 5 | | 81% | high | Nov 2025 | ai.google.dev | Official leaderboard |
| 6 | | 80.5% | high | Feb 2026 | ai.google.dev | Official leaderboard |
| 7 | GPT-5.4 | 78% | high | Mar 2026 | huggingface.co | Official leaderboard |
| 8 | Claude Sonnet 4.6 | 77.5% | high | Feb 2026 | anthropic.com | Official leaderboard |
| 9 | GPT-5.5 | 77.5% | high | Apr 2026 | developers.openai.com | Official leaderboard |
| 10 | Claude Opus 4.6 | 76.5% | high | Feb 2026 | anthropic.com | Official leaderboard |
| 11 | | 76.5% | high | Jul 2026 | ai.google.dev | Official leaderboard |
| 12 | GPT-5.6 Sol | 75.5% | high | Jul 2026 | developers.openai.com | Official leaderboard |
| 13 | GPT-5.1 | 75% | high | Nov 2025 | huggingface.co | Official leaderboard |
| 14 | | 75% | high | May 2026 | ai.google.dev | Official leaderboard |
| 15 | o1-preview | 74.5% | on | Sep 2024 | huggingface.co | Official leaderboard |
| 16 | Claude Opus 4.5 | 74.5% | high | Nov 2025 | huggingface.co | Official leaderboard |
| 17 | GPT-5.6 Luna | 74.5% | high | Jul 2026 | developers.openai.com | Official leaderboard |
| 18 | | 73.5% | high | Dec 2025 | ai.google.dev | Official leaderboard |
| 19 | Claude 3.5 Sonnet | 72.5% | Jun 2024 | huggingface.co | Official leaderboard | |
| 20 | | 72.5% | high | Sep 2025 | huggingface.co | Official leaderboard |
| 21 | | 72.5% | high | Mar 2026 | ai.google.dev | Official leaderboard |
| 22 | | 71.5% | on | Jun 2025 | huggingface.co | Official leaderboard |
| 23 | GPT-5 | 71.5% | high | Aug 2025 | huggingface.co | Official leaderboard |
| 24 | GPT-5.6 Terra | 70% | high | Jul 2026 | developers.openai.com | Official leaderboard |
| 25 | GPT-5.2 | 69.5% | high | Dec 2025 | huggingface.co | Official leaderboard |
| 26 | GPT-4o Aug 2024 | 68% | Aug 2024 | huggingface.co | Official leaderboard | |
| 27 | Claude 3.7 Sonnet | 67% | Feb 2025 | huggingface.co | Official leaderboard | |
| 28 | GPT-4.1 | 66.5% | Apr 2025 | huggingface.co | Official leaderboard | |
| 29 | Grok 4.3 | 66% | on | Apr 2026 | docs.x.ai | Official leaderboard |
| 30 | GPT-4o May 2024 | 65% | May 2024 | huggingface.co | Official leaderboard | |
| 31 | Kimi K2.5 | 64% | on | Jan 2026 | kimi.com | Official leaderboard |
| 32 | | 64% | on | Apr 2026 | huggingface.co | Official leaderboard |
| 33 | Claude 3 Opus | 63.5% | Feb 2024 | huggingface.co | Official leaderboard | |
| 34 | | 63.5% | on | Feb 2026 | huggingface.co | Official leaderboard |
| 35 | | 63% | high | Sep 2025 | huggingface.co | Official leaderboard |
| 36 | | 62.5% | Feb 2025 | huggingface.co | Official leaderboard | |
| 37 | o4-mini | 62.5% | on | Apr 2025 | huggingface.co | Official leaderboard |
| 38 | | 62.5% | on | Apr 2026 | huggingface.co | Official leaderboard |
| 39 | GLM-5.2 | 62% | on | Jun 2026 | huggingface.co | Official leaderboard |
| 40 | Claude 3.5 Haiku | 61.5% | Oct 2024 | huggingface.co | Official leaderboard | |
| 41 | GPT-4 Turbo Apr 2024 | 60.5% | Apr 2024 | huggingface.co | Official leaderboard | |
| 42 | GPT-5 mini | 60.5% | high | Aug 2025 | huggingface.co | Official leaderboard |
| 43 | Claude Sonnet 4.5 | 60.5% | high | Sep 2025 | huggingface.co | Official leaderboard |
| 44 | | 60% | on | Feb 2025 | huggingface.co | Official leaderboard |
| 45 | GPT-5 nano | 59.5% | high | Aug 2025 | huggingface.co | Official leaderboard |
| 46 | GPT-4.1 mini | 59% | Apr 2025 | huggingface.co | Official leaderboard | |
| 47 | | 59% | on | May 2025 | huggingface.co | Official leaderboard |
| 48 | | 59% | on | Feb 2026 | minimax.io | Official leaderboard |
| 49 | | 59% | on | Apr 2026 | huggingface.co | Official leaderboard |
| 50 | | 58.5% | Mar 2025 | huggingface.co | Official leaderboard | |
| 51 | | 58.5% | Dec 2025 | huggingface.co | Official leaderboard | |
| 52 | o3-mini | 58% | on | Jan 2025 | huggingface.co | Official leaderboard |
| 53 | GPT-4o mini | 57% | Jul 2024 | huggingface.co | Official leaderboard | |
| 54 | | 57% | Mar 2025 | huggingface.co | Official leaderboard | |
| 55 | GPT-4.1 nano | 57% | Apr 2025 | huggingface.co | Official leaderboard | |
| 56 | Claude Sonnet 4 | 56.5% | on | May 2025 | huggingface.co | Official leaderboard |
| 57 | | 56.5% | Aug 2025 | huggingface.co | Official leaderboard | |
| 58 | cyboghostginx/gemma-3-4b-it-Adetayo 4B | 56% | huggingface.co | Official leaderboard | ||
| 59 | GPT-4 Mar 2023 | 55.5% | Mar 2023 | huggingface.co | Official leaderboard | |
| 60 | | 55% | on | Jan 2025 | huggingface.co | Official leaderboard |
| 61 | cyboghostginx/gemma-3-27b-it-Adetayo 27B | 54.5% | huggingface.co | Official leaderboard | ||
| 62 | | 54% | Mar 2025 | huggingface.co | Official leaderboard | |
| 63 | NousResearch/Hermes-3-Llama-3.1-405B-FP8 405.9B | 53.5% | huggingface.co | Official leaderboard | ||
| 64 | GPT-4 Jun 2023 | 53% | Jun 2023 | huggingface.co | Official leaderboard | |
| 65 | | 53% | Jul 2024 | huggingface.co | Official leaderboard | |
| 66 | | 53% | Jul 2024 | huggingface.co | Official leaderboard | |
| 67 | Claude 2.1 | 52.5% | Nov 2023 | huggingface.co | Official leaderboard | |
| 68 | | 52.5% | Oct 2024 | huggingface.co | Official leaderboard | |
| 69 | | 52.5% | Dec 2024 | huggingface.co | Official leaderboard | |
| 70 | GPT-3.5 Turbo Jan 2024 | 52% | Jan 2024 | huggingface.co | Official leaderboard | |
| 71 | | 52% | Apr 2024 | huggingface.co | Official leaderboard | |
| 72 | | 52% | Mar 2025 | huggingface.co | Official leaderboard | |
| 73 | AI-Sweden-Models/gpt-sw3-6.7b-v2-instruct 7.1B | 51.5% | huggingface.co | Official leaderboard | ||
| 74 | LumiOpen/Viking-33B 33.1B | 51.5% | huggingface.co | Official leaderboard | ||
| 75 | AI-Sweden-Models/gpt-sw3-126m-instruct 0.2B | 51% | huggingface.co | Official leaderboard | ||
| 76 | cyboghostginx/gemma-4-31B-it-Adetayo 31B | 51% | huggingface.co | Official leaderboard | ||
| 77 | | 51% | Jun 2024 | huggingface.co | Official leaderboard | |
| 78 | | 51% | Jun 2024 | huggingface.co | Official leaderboard | |
| 79 | o1-mini | 51% | on | Sep 2024 | huggingface.co | Official leaderboard |
| 80 | | 51% | Oct 2024 | huggingface.co | Official leaderboard | |
| 81 | AI-Sweden-Models/gpt-sw3-1.3b-instruct 1.4B | 50.5% | huggingface.co | Official leaderboard | ||
| 82 | AI-Sweden-Models/gpt-sw3-20b-instruct 20.9B | 50% | huggingface.co | Official leaderboard | ||
| 83 | | 50% | Jul 2024 | huggingface.co | Official leaderboard | |
| 84 | | 50% | Sep 2024 | huggingface.co | Official leaderboard | |
| 85 | LumiOpen/Viking-13B 14B | 49.5% | huggingface.co | Official leaderboard | ||
| 86 | | 49.5% | Mar 2025 | huggingface.co | Official leaderboard | |
| 87 | | 49% | Apr 2024 | huggingface.co | Official leaderboard | |
| 88 | | 49% | Sep 2024 | huggingface.co | Official leaderboard | |
| 89 | | 48.5% | Jun 2024 | huggingface.co | Official leaderboard | |
| 90 | AI-Sweden-Models/gpt-sw3-356m-instruct 0.5B | 48% | huggingface.co | Official leaderboard | ||
| 91 | Sigurdur/icebreaker 0.1B | 48% | huggingface.co | Official leaderboard | ||
| 92 | LumiOpen/Viking-7B 7.6B | 40% | huggingface.co | Official leaderboard |
| # | Model | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5 | 91.5% | high | Jun 2026 | anthropic.com | Official leaderboard |
| 2 | Claude Opus 4.7 | 84.5% | high | Apr 2026 | anthropic.com | Official leaderboard |
| 3 | Claude Opus 4.8 | 84% | high | May 2026 | anthropic.com | Official leaderboard |
| 4 | | 82% | high | Aug 2026 | ai.google.dev | Official leaderboard |
| 5 | | 81% | high | Nov 2025 | ai.google.dev | Official leaderboard |
| 6 | | 80.5% | high | Feb 2026 | ai.google.dev | Official leaderboard |
| 7 | GPT-5.4 | 78% | high | Mar 2026 | huggingface.co | Official leaderboard |
| 8 | Claude Sonnet 4.6 | 77.5% | high | Feb 2026 | anthropic.com | Official leaderboard |
| 9 | GPT-5.5 | 77.5% | high | Apr 2026 | developers.openai.com | Official leaderboard |
| 10 | Claude Opus 4.6 | 76.5% | high | Feb 2026 | anthropic.com | Official leaderboard |
| 11 | | 76.5% | high | Jul 2026 | ai.google.dev | Official leaderboard |
| 12 | GPT-5.6 Sol | 75.5% | high | Jul 2026 | developers.openai.com | Official leaderboard |
| 13 | GPT-5.1 | 75% | high | Nov 2025 | huggingface.co | Official leaderboard |
| 14 | | 75% | high | May 2026 | ai.google.dev | Official leaderboard |
| 15 | o1-preview | 74.5% | on | Sep 2024 | huggingface.co | Official leaderboard |
| 16 | Claude Opus 4.5 | 74.5% | high | Nov 2025 | huggingface.co | Official leaderboard |
| 17 | GPT-5.6 Luna | 74.5% | high | Jul 2026 | developers.openai.com | Official leaderboard |
| 18 | | 73.5% | high | Dec 2025 | ai.google.dev | Official leaderboard |
| 19 | Claude 3.5 Sonnet | 72.5% | Jun 2024 | huggingface.co | Official leaderboard | |
| 20 | | 72.5% | high | Sep 2025 | huggingface.co | Official leaderboard |
| 21 | | 72.5% | high | Mar 2026 | ai.google.dev | Official leaderboard |
| 22 | | 71.5% | on | Jun 2025 | huggingface.co | Official leaderboard |
| 23 | GPT-5 | 71.5% | high | Aug 2025 | huggingface.co | Official leaderboard |
| 24 | GPT-5.6 Terra | 70% | high | Jul 2026 | developers.openai.com | Official leaderboard |
| 25 | GPT-5.2 | 69.5% | high | Dec 2025 | huggingface.co | Official leaderboard |
| 26 | GPT-4o Aug 2024 | 68% | Aug 2024 | huggingface.co | Official leaderboard | |
| 27 | Claude 3.7 Sonnet | 67% | Feb 2025 | huggingface.co | Official leaderboard | |
| 28 | GPT-4.1 | 66.5% | Apr 2025 | huggingface.co | Official leaderboard | |
| 29 | Grok 4.3 | 66% | on | Apr 2026 | docs.x.ai | Official leaderboard |
| 30 | GPT-4o May 2024 | 65% | May 2024 | huggingface.co | Official leaderboard | |
| 31 | Kimi K2.5 | 64% | on | Jan 2026 | kimi.com | Official leaderboard |
| 32 | | 64% | on | Apr 2026 | huggingface.co | Official leaderboard |
| 33 | Claude 3 Opus | 63.5% | Feb 2024 | huggingface.co | Official leaderboard | |
| 34 | | 63.5% | on | Feb 2026 | huggingface.co | Official leaderboard |
| 35 | | 63% | high | Sep 2025 | huggingface.co | Official leaderboard |
| 36 | | 62.5% | Feb 2025 | huggingface.co | Official leaderboard | |
| 37 | o4-mini | 62.5% | on | Apr 2025 | huggingface.co | Official leaderboard |
| 38 | | 62.5% | on | Apr 2026 | huggingface.co | Official leaderboard |
| 39 | GLM-5.2 | 62% | on | Jun 2026 | huggingface.co | Official leaderboard |
| 40 | Claude 3.5 Haiku | 61.5% | Oct 2024 | huggingface.co | Official leaderboard | |
| 41 | GPT-4 Turbo Apr 2024 | 60.5% | Apr 2024 | huggingface.co | Official leaderboard | |
| 42 | GPT-5 mini | 60.5% | high | Aug 2025 | huggingface.co | Official leaderboard |
| 43 | Claude Sonnet 4.5 | 60.5% | high | Sep 2025 | huggingface.co | Official leaderboard |
| 44 | | 60% | on | Feb 2025 | huggingface.co | Official leaderboard |
| 45 | GPT-5 nano | 59.5% | high | Aug 2025 | huggingface.co | Official leaderboard |
| 46 | GPT-4.1 mini | 59% | Apr 2025 | huggingface.co | Official leaderboard | |
| 47 | | 59% | on | May 2025 | huggingface.co | Official leaderboard |
| 48 | | 59% | on | Feb 2026 | minimax.io | Official leaderboard |
| 49 | | 59% | on | Apr 2026 | huggingface.co | Official leaderboard |
| 50 | | 58.5% | Mar 2025 | huggingface.co | Official leaderboard | |
| 51 | | 58.5% | Dec 2025 | huggingface.co | Official leaderboard | |
| 52 | o3-mini | 58% | on | Jan 2025 | huggingface.co | Official leaderboard |
| 53 | GPT-4o mini | 57% | Jul 2024 | huggingface.co | Official leaderboard | |
| 54 | | 57% | Mar 2025 | huggingface.co | Official leaderboard | |
| 55 | GPT-4.1 nano | 57% | Apr 2025 | huggingface.co | Official leaderboard | |
| 56 | Claude Sonnet 4 | 56.5% | on | May 2025 | huggingface.co | Official leaderboard |
| 57 | | 56.5% | Aug 2025 | huggingface.co | Official leaderboard | |
| 58 | GPT-4 Mar 2023 | 55.5% | Mar 2023 | huggingface.co | Official leaderboard | |
| 59 | | 55% | on | Jan 2025 | huggingface.co | Official leaderboard |
| 60 | | 54% | Mar 2025 | huggingface.co | Official leaderboard | |
| 61 | GPT-4 Jun 2023 | 53% | Jun 2023 | huggingface.co | Official leaderboard | |
| 62 | | 53% | Jul 2024 | huggingface.co | Official leaderboard | |
| 63 | | 53% | Jul 2024 | huggingface.co | Official leaderboard | |
| 64 | Claude 2.1 | 52.5% | Nov 2023 | huggingface.co | Official leaderboard | |
| 65 | | 52.5% | Oct 2024 | huggingface.co | Official leaderboard | |
| 66 | | 52.5% | Dec 2024 | huggingface.co | Official leaderboard | |
| 67 | GPT-3.5 Turbo Jan 2024 | 52% | Jan 2024 | huggingface.co | Official leaderboard | |
| 68 | | 52% | Apr 2024 | huggingface.co | Official leaderboard | |
| 69 | | 52% | Mar 2025 | huggingface.co | Official leaderboard | |
| 70 | | 51% | Jun 2024 | huggingface.co | Official leaderboard | |
| 71 | | 51% | Jun 2024 | huggingface.co | Official leaderboard | |
| 72 | o1-mini | 51% | on | Sep 2024 | huggingface.co | Official leaderboard |
| 73 | | 51% | Oct 2024 | huggingface.co | Official leaderboard | |
| 74 | | 50% | Jul 2024 | huggingface.co | Official leaderboard | |
| 75 | | 50% | Sep 2024 | huggingface.co | Official leaderboard | |
| 76 | | 49.5% | Mar 2025 | huggingface.co | Official leaderboard | |
| 77 | | 49% | Apr 2024 | huggingface.co | Official leaderboard | |
| 78 | | 49% | Sep 2024 | huggingface.co | Official leaderboard | |
| 79 | | 48.5% | Jun 2024 | huggingface.co | Official leaderboard |
9 models have held number one on the official leaderboard since its release in December 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Miðeind Icelandic Grammatical Error Detection leaderboard
Claude Fable 5 on the official leaderboard passed 85% in June 2026
That was 30 months after its release. By the same age, 51% of the benchmarks from 2023 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 Grammatical Error Detection 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 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (92 entries).
- Pass Models scored 79 models we track, plus 13 other entries on its leaderboard.
- Pass Newest score The newest is from August 2026, for Gemini 3.7 Flash.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Fable 5 (#12).
- Note Headroom Saturated. The best is 91.5%, past 85% since June 2026.
Leaderboard import 3 pass
- Pass Importer We read the board on mideind-icelandic-llm-leaderboard.static.hf.space: 81 rows for models we track and 13 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.