Linguistic Knowledge Benchmark (Fab AI)
Models answer multiple-choice and short-answer questions about Kiswahili and English grammar, phonics, and spelling. Three model judges vote on short answers.
Fab AI scores 121 model configurations on 135 Kiswahili questions and 119 on 137 English questions. It shares 20 sample questions for each language.
- Made by
- Fab AI
- Released
- September 2026
- Kind
- Language reasoning
- Level
- University
- Scored
- Graded by a model
- Answers
- Multiple choice
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Languages and literature, Education
- Interaction
- Single turn
- Items from
- Exams and contests
- Refresh
- One fixed set
- Run by
- A host
- Strongest model tested
- Claude Opus 5 #11 on the capability index
- Last model added
- August 2026
- Scores refreshed
- November 20th, 2026
GPT-5.4 leads with 97.8% among models released by August 2026 GPT-5.4 leads with 97.8% 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. 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.
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 12 more
- 97.8 GPT-5.4
- 97.0
Gemini 3.7 Flash
- 96.3
Gemini 3 Flash
- 95.6 Claude Opus 4.7 Adaptive Thinking
- 95.6
Gemini 3.1 Pro
- 95.6 Claude Opus 4.7
- 95.6 GPT-5.5
- 95.6
DeepSeek-V4-Pro
- 95.6
Gemini 3.5 Flash
- 95.6 Claude Fable 5
- 95.6 Grok 4.5
- 95.6 GPT-5.6 Sol
- 95.5
DeepSeek-V4-Flash
- 94.8 Claude Opus 4.8
- 94.1 Kimi K3
- 94.1 Grok 4.6
- 93.3 GPT-5.6 Terra
- 92.6 o3
- 92.6 Claude Opus 4.6
- 92.6 Grok 4.20
- 92.6
Inkling
- 92.6 Claude Opus 5
- 91.8
Gemini 2.5 Pro
- 91.8 GPT-5
- 91.8
Qwen 3.6 Max (Preview)
- 91.8
Muse Spark 1.2
- 91.1 Claude Opus 4.5
- 91.1 GPT-5.2
- 91.1
Gemini 3.1 Flash-Lite
- 91.1 GPT-5.4 Mini
- 91.1 Grok 4.3
- 91.1 Claude Sonnet 5
- 91.1 GPT-5.6 Luna
- 91.1
Gemini 3.6 Flash
- 90.4
Gemini 2.5 Flash
- 90.4 Claude Sonnet 4.6
- 90.4 Kimi K2.6
- 90.4
Gemini 3.5 Flash-Lite
- 89.6 GPT-5.1
- 89.6
Qwen3.7-Max
- 88.9
Inkling-Small
- 88.5
Qwen3.5 397B-A17B
- 88.2
Qwen3.8-2.4T-A95B
- 87.4 Kimi K2.5
- 87.4
Qwen 3.8 Max
- 86.7
Qwen3.5-Plus
- 86.7 MiMo-V2.5-Pro
- 85.9
Qwen 3.6 Plus
- 85.9 GLM-5.1
- 85.8 GLM-5.2
- 85.2
Gemma 4 31B IT
- 85.2 GLM-5.3
- 81.5 Claude Sonnet 4.5
- 80.7 GPT-4.1
- 80.7 GPT-5 mini
- 80.7
Qwen3.5-122B-A10B
- 80.0
sonar
- 80.0
Llama 4 Maverick
- 80.0 o4-mini
- 80.0 GPT-5.4 Nano
- 79.5
MiniMax-M3
- 79.3
Muse Glimmer
- 77.8
Gemma 4 26B A4B
- 77.8 MiMo-V2.5
- 76.3
Mistral Large 3
- 76.3
MiniMax-M2.7
- 74.8
Qwen3.5-27B
- 74.1 o3-mini
- 74.1 GPT-5 nano
- 74.1
Qwen3.5-Flash
- 73.9
Qwen3-235B-A22B-Thinking
- 73.1
Qwen 3.6 35B-A3B
- 72.6
DeepSeek-V3
- 71.8 gpt-oss-120b
- 71.6
Qwen3.5-35B-A3B
- 69.6
Qwen3.7 Flash
- 68.2 GPT-4.1 mini
- 67.9
Qwen 3.8 27B
- 66.9
Qwen3.6 27B
- 65.9 Claude Haiku 4.5
- 65.7
Gemma 4 12B
- 63.9
Doubao-Seed-1.6
- 63.7
Mistral Medium 3
- 62.2
Mistral Medium 3.1
- 62.2
Qwen 3.6 Flash
- 61.5
Mistral Small 4
- 60.0
Mistral Medium 3.5
- 59.3 GLM-4.6V
- 55.6
Qwen3-235B-A22B
- 54.8
Gemma 3 27B
- 54.1
Llama 4 Scout
- 54.1 GPT-4.1 nano
- 51.9
Qwen3.5-9B
- 50.4 Command A
- 46.6 glm-4.7-flash
- 45.9
Gemma 2 27B
- 42.2 Command-R+ August
- 40.7
Gemma 4 E2B
- 40.3
Nemotron 3.5 Lightning 30B-A3B
- 40.0
Mistral Small 3
- 39.3
Gemma 3 12B
- 38.9
Nemotron 3 Nano 30B-A3B
- 35.6
Nova 2 Lite
- 33.8 Seed 1.6 Flash
- 29.6
Mistral NeMo
- 28.9
Phi-4
- 26.7
Gemma 3 4B
- 23.7 Ministral 3 3B
- 23.0 Ministral 3 8B
- 22.2
Command R7B
- 21.5
Llama 3.2 3B
- 20.7
Qwen3-4B
- 14.1
Llama 3.2 1B
- 11.1
Qwen3-1.7B
- 10.4
Qwen3-0.6B
- 1 GPT-5.4 medium 97.8%
- 2
Gemini 3.7 Flash 97%
- 3
Gemini 3 Flash 96.3%
- 4 Claude Opus 4.7 Adaptive Thinking 95.6%
- 5
Gemini 3.1 Pro 95.6%
- 6 Claude Opus 4.7 95.6%
- 7 GPT-5.5 95.6%
- 8
DeepSeek-V4-Pro 95.6%
- 9
Gemini 3.5 Flash 95.6%
- 10 Claude Fable 5 95.6%
- 11 Grok 4.5 95.6%
- 12 GPT-5.6 Sol 95.6%
- 13
DeepSeek-V4-Flash 95.5%
- 14 Claude Opus 4.8 94.8%
- 15 Kimi K3 94.1%
- 16 Grok 4.6 94.1%
- 17 GPT-5.6 Terra 93.3%
- 18 o3 92.6%
- 19 Claude Opus 4.6 92.6%
- 20 Grok 4.20 reasoning 92.6%
- 21
Inkling 92.6%
- 22 Claude Opus 5 92.6%
- 23
Gemini 2.5 Pro Jun 2025 91.8%
- 24 GPT-5 medium 91.8%
- 25
Qwen 3.6 Max (Preview) 91.8%
- 26
Muse Spark 1.2 91.8%
- 27 Claude Opus 4.5 91.1%
- 28 GPT-5.2 medium 91.1%
- 29
Gemini 3.1 Flash-Lite 91.1%
- 30 GPT-5.4 Mini medium 91.1%
- 31 Grok 4.3 91.1%
- 32 Claude Sonnet 5 91.1%
- 33 GPT-5.6 Luna 91.1%
- 34
Gemini 3.6 Flash 91.1%
- 35
Gemini 2.5 Flash Sep 2025 90.4%
- 36 Claude Sonnet 4.6 90.4%
- 37 Kimi K2.6 90.4%
- 38
Gemini 3.5 Flash-Lite 90.4%
- 39 GPT-5.1 medium 89.6%
- 40
Qwen3.7-Max 89.6%
- 41
Inkling-Small 88.9%
- 42
Qwen3.5 397B-A17B 88.5%
- 43
Qwen3.8-2.4T-A95B 88.2%
- 44 Kimi K2.5 87.4%
- 45
Qwen 3.8 Max 87.4%
- 46
Qwen3.5-Plus 86.7%
- 47 MiMo-V2.5-Pro 86.7%
- 48
Qwen 3.6 Plus 85.9%
- 49 GLM-5.1 85.9%
- 50 GLM-5.2 85.8%
- 51
Gemma 4 31B IT 85.2%
- 52 GLM-5.3 85.2%
- 53 Claude Sonnet 4.5 81.5%
- 54 GPT-4.1 80.7%
- 55 GPT-5 mini medium 80.7%
- 56
Qwen3.5-122B-A10B 80.7%
- 57
sonar 80%
- 58
Llama 4 Maverick 80%
- 59 o4-mini 80%
- 60 GPT-5.4 Nano medium 80%
- 61
MiniMax-M3 79.5%
- 62
Muse Glimmer 79.3%
- 63
Gemma 4 26B A4B 77.8%
- 64 MiMo-V2.5 77.8%
- 65
Mistral Large 3 76.3%
- 66
MiniMax-M2.7 76.3%
- 67
Qwen3.5-27B 74.8%
- 68 o3-mini 74.1%
- 69 GPT-5 nano medium 74.1%
- 70
Qwen3.5-Flash 74.1%
- 71
Qwen3-235B-A22B-Thinking Jul 2025 73.9%
- 72
Qwen 3.6 35B-A3B 73.1%
- 73
DeepSeek-V3 Mar 2025 72.6%
- 74 gpt-oss-120b 71.8%
- 75
Qwen3.5-35B-A3B 71.6%
- 76
Qwen3.7 Flash 69.6%
- 77 GPT-4.1 mini 68.2%
- 78
Qwen 3.8 27B 67.9%
- 79
Qwen3.6 27B 66.9%
- 80 Claude Haiku 4.5 65.9%
- 81
Gemma 4 12B 65.7%
- 82
Doubao-Seed-1.6 63.9%
- 83
Mistral Medium 3 63.7%
- 84
Mistral Medium 3.1 62.2%
- 85
Qwen 3.6 Flash 62.2%
- 86
Mistral Small 4 61.5%
- 87
Mistral Medium 3.5 60%
- 88 GLM-4.6V 59.3%
- 89
Qwen3-235B-A22B 55.6%
- 90
Gemma 3 27B 54.8%
- 91
Llama 4 Scout 54.1%
- 92 GPT-4.1 nano 54.1%
- 93
Qwen3.5-9B 51.9%
- 94 Command A 50.4%
- 95 glm-4.7-flash 46.6%
- 96
Gemma 2 27B 45.9%
- 97 Command-R+ August 42.2%
- 98
Gemma 4 E2B 40.7%
- 99
Nemotron 3.5 Lightning 30B-A3B 40.3%
- 100
Mistral Small 3 40%
- 101
Gemma 3 12B 39.3%
- 102
Nemotron 3 Nano 30B-A3B 38.9%
- 103
Nova 2 Lite 35.6%
- 104 Seed 1.6 Flash 33.8%
- 105
Mistral NeMo 29.6%
- 106
Phi-4 28.9%
- 107
Gemma 3 4B 26.7%
- 108 Ministral 3 3B 23.7%
- 109 Ministral 3 8B 23%
- 110
Command R7B 22.2%
- 111
Llama 3.2 3B 21.5%
- 112
Qwen3-4B 20.7%
- 113
Llama 3.2 1B 14.1%
- 114
Qwen3-1.7B 11.1%
- 115
Qwen3-0.6B 10.4%
Source: Official Linguistic Knowledge Benchmark (Fab AI) leaderboard
- 97.8 GPT-5.4
- 97.0
Gemini 3.7 Flash
- 96.3
Gemini 3 Flash
- 95.6
Gemini 3.1 Pro
- 95.6 Claude Opus 4.7
- 95.6 GPT-5.5
- 95.6
DeepSeek-V4-Pro
- 95.6
Gemini 3.5 Flash
- 95.6 Claude Fable 5
- 95.6 Grok 4.5
- 95.6 GPT-5.6 Sol
- 95.5
DeepSeek-V4-Flash
- 94.8 Claude Opus 4.8
- 94.1 Kimi K3
- 94.1 Grok 4.6
- 93.3 GPT-5.6 Terra
- 92.6 o3
- 92.6 Claude Opus 4.6
- 92.6 Grok 4.20
- 92.6
Inkling
- 92.6 Claude Opus 5
- 91.8
Gemini 2.5 Pro
- 91.8 GPT-5
- 91.8
Qwen 3.6 Max (Preview)
- 91.8
Muse Spark 1.2
- 91.1 Claude Opus 4.5
- 91.1 GPT-5.2
- 91.1
Gemini 3.1 Flash-Lite
- 91.1 GPT-5.4 Mini
- 91.1 Grok 4.3
- 91.1 Claude Sonnet 5
- 91.1 GPT-5.6 Luna
- 91.1
Gemini 3.6 Flash
- 90.4
Gemini 2.5 Flash
- 90.4 Claude Sonnet 4.6
- 90.4 Kimi K2.6
- 90.4
Gemini 3.5 Flash-Lite
- 89.6 GPT-5.1
- 89.6
Qwen3.7-Max
- 88.9
Inkling-Small
- 88.5
Qwen3.5 397B-A17B
- 88.2
Qwen3.8-2.4T-A95B
- 87.4 Kimi K2.5
- 87.4
Qwen 3.8 Max
- 86.7
Qwen3.5-Plus
- 86.7 MiMo-V2.5-Pro
- 85.9
Qwen 3.6 Plus
- 85.9 GLM-5.1
- 85.8 GLM-5.2
- 85.2
Gemma 4 31B IT
- 85.2 GLM-5.3
- 81.5 Claude Sonnet 4.5
- 80.7 GPT-4.1
- 80.7 GPT-5 mini
- 80.7
Qwen3.5-122B-A10B
- 80.0
sonar
- 80.0
Llama 4 Maverick
- 80.0 o4-mini
- 80.0 GPT-5.4 Nano
- 79.5
MiniMax-M3
- 79.3
Muse Glimmer
- 77.8
Gemma 4 26B A4B
- 77.8 MiMo-V2.5
- 76.3
Mistral Large 3
- 76.3
MiniMax-M2.7
- 74.8
Qwen3.5-27B
- 74.1 o3-mini
- 74.1 GPT-5 nano
- 74.1
Qwen3.5-Flash
- 73.9
Qwen3-235B-A22B-Thinking
- 73.1
Qwen 3.6 35B-A3B
- 72.6
DeepSeek-V3
- 71.8 gpt-oss-120b
- 71.6
Qwen3.5-35B-A3B
- 69.6
Qwen3.7 Flash
- 68.2 GPT-4.1 mini
- 67.9
Qwen 3.8 27B
- 66.9
Qwen3.6 27B
- 65.9 Claude Haiku 4.5
- 65.7
Gemma 4 12B
- 63.9
Doubao-Seed-1.6
- 63.7
Mistral Medium 3
- 62.2
Mistral Medium 3.1
- 62.2
Qwen 3.6 Flash
- 61.5
Mistral Small 4
- 60.0
Mistral Medium 3.5
- 59.3 GLM-4.6V
- 55.6
Qwen3-235B-A22B
- 54.8
Gemma 3 27B
- 54.1
Llama 4 Scout
- 54.1 GPT-4.1 nano
- 51.9
Qwen3.5-9B
- 46.6 glm-4.7-flash
- 45.9
Gemma 2 27B
- 40.7
Gemma 4 E2B
- 40.3
Nemotron 3.5 Lightning 30B-A3B
- 40.0
Mistral Small 3
- 39.3
Gemma 3 12B
- 38.9
Nemotron 3 Nano 30B-A3B
- 35.6
Nova 2 Lite
- 29.6
Mistral NeMo
- 28.9
Phi-4
- 26.7
Gemma 3 4B
- 22.2
Command R7B
- 21.5
Llama 3.2 3B
- 20.7
Qwen3-4B
- 14.1
Llama 3.2 1B
- 11.1
Qwen3-1.7B
- 10.4
Qwen3-0.6B
- 1 GPT-5.4 medium 97.8%
- 2
Gemini 3.7 Flash 97%
- 3
Gemini 3 Flash 96.3%
- 4
Gemini 3.1 Pro 95.6%
- 5 Claude Opus 4.7 95.6%
- 6 GPT-5.5 95.6%
- 7
DeepSeek-V4-Pro 95.6%
- 8
Gemini 3.5 Flash 95.6%
- 9 Claude Fable 5 95.6%
- 10 Grok 4.5 95.6%
- 11 GPT-5.6 Sol 95.6%
- 12
DeepSeek-V4-Flash 95.5%
- 13 Claude Opus 4.8 94.8%
- 14 Kimi K3 94.1%
- 15 Grok 4.6 94.1%
- 16 GPT-5.6 Terra 93.3%
- 17 o3 92.6%
- 18 Claude Opus 4.6 92.6%
- 19 Grok 4.20 reasoning 92.6%
- 20
Inkling 92.6%
- 21 Claude Opus 5 92.6%
- 22
Gemini 2.5 Pro Jun 2025 91.8%
- 23 GPT-5 medium 91.8%
- 24
Qwen 3.6 Max (Preview) 91.8%
- 25
Muse Spark 1.2 91.8%
- 26 Claude Opus 4.5 91.1%
- 27 GPT-5.2 medium 91.1%
- 28
Gemini 3.1 Flash-Lite 91.1%
- 29 GPT-5.4 Mini medium 91.1%
- 30 Grok 4.3 91.1%
- 31 Claude Sonnet 5 91.1%
- 32 GPT-5.6 Luna 91.1%
- 33
Gemini 3.6 Flash 91.1%
- 34
Gemini 2.5 Flash Sep 2025 90.4%
- 35 Claude Sonnet 4.6 90.4%
- 36 Kimi K2.6 90.4%
- 37
Gemini 3.5 Flash-Lite 90.4%
- 38 GPT-5.1 medium 89.6%
- 39
Qwen3.7-Max 89.6%
- 40
Inkling-Small 88.9%
- 41
Qwen3.5 397B-A17B 88.5%
- 42
Qwen3.8-2.4T-A95B 88.2%
- 43 Kimi K2.5 87.4%
- 44
Qwen 3.8 Max 87.4%
- 45
Qwen3.5-Plus 86.7%
- 46 MiMo-V2.5-Pro 86.7%
- 47
Qwen 3.6 Plus 85.9%
- 48 GLM-5.1 85.9%
- 49 GLM-5.2 85.8%
- 50
Gemma 4 31B IT 85.2%
- 51 GLM-5.3 85.2%
- 52 Claude Sonnet 4.5 81.5%
- 53 GPT-4.1 80.7%
- 54 GPT-5 mini medium 80.7%
- 55
Qwen3.5-122B-A10B 80.7%
- 56
sonar 80%
- 57
Llama 4 Maverick 80%
- 58 o4-mini 80%
- 59 GPT-5.4 Nano medium 80%
- 60
MiniMax-M3 79.5%
- 61
Muse Glimmer 79.3%
- 62
Gemma 4 26B A4B 77.8%
- 63 MiMo-V2.5 77.8%
- 64
Mistral Large 3 76.3%
- 65
MiniMax-M2.7 76.3%
- 66
Qwen3.5-27B 74.8%
- 67 o3-mini 74.1%
- 68 GPT-5 nano medium 74.1%
- 69
Qwen3.5-Flash 74.1%
- 70
Qwen3-235B-A22B-Thinking Jul 2025 73.9%
- 71
Qwen 3.6 35B-A3B 73.1%
- 72
DeepSeek-V3 Mar 2025 72.6%
- 73 gpt-oss-120b 71.8%
- 74
Qwen3.5-35B-A3B 71.6%
- 75
Qwen3.7 Flash 69.6%
- 76 GPT-4.1 mini 68.2%
- 77
Qwen 3.8 27B 67.9%
- 78
Qwen3.6 27B 66.9%
- 79 Claude Haiku 4.5 65.9%
- 80
Gemma 4 12B 65.7%
- 81
Doubao-Seed-1.6 63.9%
- 82
Mistral Medium 3 63.7%
- 83
Mistral Medium 3.1 62.2%
- 84
Qwen 3.6 Flash 62.2%
- 85
Mistral Small 4 61.5%
- 86
Mistral Medium 3.5 60%
- 87 GLM-4.6V 59.3%
- 88
Qwen3-235B-A22B 55.6%
- 89
Gemma 3 27B 54.8%
- 90
Llama 4 Scout 54.1%
- 91 GPT-4.1 nano 54.1%
- 92
Qwen3.5-9B 51.9%
- 93 glm-4.7-flash 46.6%
- 94
Gemma 2 27B 45.9%
- 95
Gemma 4 E2B 40.7%
- 96
Nemotron 3.5 Lightning 30B-A3B 40.3%
- 97
Mistral Small 3 40%
- 98
Gemma 3 12B 39.3%
- 99
Nemotron 3 Nano 30B-A3B 38.9%
- 100
Nova 2 Lite 35.6%
- 101
Mistral NeMo 29.6%
- 102
Phi-4 28.9%
- 103
Gemma 3 4B 26.7%
- 104
Command R7B 22.2%
- 105
Llama 3.2 3B 21.5%
- 106
Qwen3-4B 20.7%
- 107
Llama 3.2 1B 14.1%
- 108
Qwen3-1.7B 11.1%
- 109
Qwen3-0.6B 10.4%
Source: Official Linguistic Knowledge Benchmark (Fab AI) leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 | 97.8% | medium | Mar 2026 | Official leaderboard |
| 2 | | 97% | Aug 2026 | Official leaderboard | |
| 3 | | 96.3% | Dec 2025 | Official leaderboard | |
| 4 | Claude Opus 4.7 Adaptive Thinking | 95.6% | Official leaderboard | ||
| 5 | | 95.6% | Feb 2026 | Official leaderboard | |
| 6 | Claude Opus 4.7 | 95.6% | Apr 2026 | Official leaderboard | |
| 7 | GPT-5.5 | 95.6% | Apr 2026 | Official leaderboard | |
| 8 | | 95.6% | Apr 2026 | Official leaderboard | |
| 9 | | 95.6% | May 2026 | Official leaderboard | |
| 10 | Claude Fable 5 | 95.6% | Jun 2026 | Official leaderboard | |
| 11 | Grok 4.5 | 95.6% | Jul 2026 | Official leaderboard | |
| 12 | GPT-5.6 Sol | 95.6% | Jul 2026 | Official leaderboard | |
| 13 | | 95.5% | Apr 2026 | Official leaderboard | |
| 14 | Claude Opus 4.8 | 94.8% | May 2026 | Official leaderboard | |
| 15 | Kimi K3 | 94.1% | Jul 2026 | Official leaderboard | |
| 16 | Grok 4.6 | 94.1% | Aug 2026 | Official leaderboard | |
| 17 | GPT-5.6 Terra | 93.3% | Jul 2026 | Official leaderboard | |
| 18 | o3 | 92.6% | Apr 2025 | Official leaderboard | |
| 19 | Claude Opus 4.6 | 92.6% | Feb 2026 | Official leaderboard | |
| 20 | Grok 4.20 | 92.6% | reasoning | Feb 2026 | Official leaderboard |
| 21 | | 92.6% | Jul 2026 | Official leaderboard | |
| 22 | Claude Opus 5 | 92.6% | Jul 2026 | Official leaderboard | |
| 23 | | 91.8% | Jun 2025 | Official leaderboard | |
| 24 | GPT-5 | 91.8% | medium | Aug 2025 | Official leaderboard |
| 25 | | 91.8% | Apr 2026 | Official leaderboard | |
| 26 | | 91.8% | Aug 2026 | Official leaderboard | |
| 27 | Claude Opus 4.5 | 91.1% | Nov 2025 | Official leaderboard | |
| 28 | GPT-5.2 | 91.1% | medium | Dec 2025 | Official leaderboard |
| 29 | | 91.1% | Mar 2026 | Official leaderboard | |
| 30 | GPT-5.4 Mini | 91.1% | medium | Mar 2026 | Official leaderboard |
| 31 | Grok 4.3 | 91.1% | Apr 2026 | Official leaderboard | |
| 32 | Claude Sonnet 5 | 91.1% | Jun 2026 | Official leaderboard | |
| 33 | GPT-5.6 Luna | 91.1% | Jul 2026 | Official leaderboard | |
| 34 | | 91.1% | Jul 2026 | Official leaderboard | |
| 35 | | 90.4% | Sep 2025 | Official leaderboard | |
| 36 | Claude Sonnet 4.6 | 90.4% | Feb 2026 | Official leaderboard | |
| 37 | Kimi K2.6 | 90.4% | Apr 2026 | Official leaderboard | |
| 38 | | 90.4% | Jul 2026 | Official leaderboard | |
| 39 | GPT-5.1 | 89.6% | medium | Nov 2025 | Official leaderboard |
| 40 | | 89.6% | May 2026 | Official leaderboard | |
| 41 | | 88.9% | Jul 2026 | Official leaderboard | |
| 42 | | 88.5% | Feb 2026 | Official leaderboard | |
| 43 | | 88.2% | Aug 2026 | Official leaderboard | |
| 44 | Kimi K2.5 | 87.4% | Jan 2026 | Official leaderboard | |
| 45 | | 87.4% | Aug 2026 | Official leaderboard | |
| 46 | | 86.7% | Feb 2026 | Official leaderboard | |
| 47 | MiMo-V2.5-Pro | 86.7% | Apr 2026 | Official leaderboard | |
| 48 | | 85.9% | Mar 2026 | Official leaderboard | |
| 49 | GLM-5.1 | 85.9% | Apr 2026 | Official leaderboard | |
| 50 | GLM-5.2 | 85.8% | Jun 2026 | Official leaderboard | |
| 51 | | 85.2% | Apr 2026 | Official leaderboard | |
| 52 | GLM-5.3 | 85.2% | Aug 2026 | Official leaderboard | |
| 53 | Claude Sonnet 4.5 | 81.5% | Sep 2025 | Official leaderboard | |
| 54 | GPT-4.1 | 80.7% | Apr 2025 | Official leaderboard | |
| 55 | GPT-5 mini | 80.7% | medium | Aug 2025 | Official leaderboard |
| 56 | | 80.7% | Feb 2026 | Official leaderboard | |
| 57 | | 80% | Jan 2025 | Official leaderboard | |
| 58 | | 80% | Apr 2025 | Official leaderboard | |
| 59 | o4-mini | 80% | Apr 2025 | Official leaderboard | |
| 60 | GPT-5.4 Nano | 80% | medium | Mar 2026 | Official leaderboard |
| 61 | | 79.5% | Jun 2026 | Official leaderboard | |
| 62 | | 79.3% | Aug 2026 | Official leaderboard | |
| 63 | | 77.8% | Apr 2026 | Official leaderboard | |
| 64 | MiMo-V2.5 | 77.8% | Apr 2026 | Official leaderboard | |
| 65 | | 76.3% | Dec 2025 | Official leaderboard | |
| 66 | | 76.3% | Mar 2026 | Official leaderboard | |
| 67 | | 74.8% | Feb 2026 | Official leaderboard | |
| 68 | o3-mini | 74.1% | Jan 2025 | Official leaderboard | |
| 69 | GPT-5 nano | 74.1% | medium | Aug 2025 | Official leaderboard |
| 70 | | 74.1% | Feb 2026 | Official leaderboard | |
| 71 | | 73.9% | Jul 2025 | Official leaderboard | |
| 72 | | 73.1% | Apr 2026 | Official leaderboard | |
| 73 | | 72.6% | Mar 2025 | Official leaderboard | |
| 74 | gpt-oss-120b | 71.8% | Aug 2025 | Official leaderboard | |
| 75 | | 71.6% | Feb 2026 | Official leaderboard | |
| 76 | | 69.6% | Jul 2026 | Official leaderboard | |
| 77 | GPT-4.1 mini | 68.2% | Apr 2025 | Official leaderboard | |
| 78 | | 67.9% | Aug 2026 | Official leaderboard | |
| 79 | | 66.9% | Apr 2026 | Official leaderboard | |
| 80 | Claude Haiku 4.5 | 65.9% | Oct 2025 | Official leaderboard | |
| 81 | | 65.7% | Jun 2026 | Official leaderboard | |
| 82 | | 63.9% | Jun 2025 | Official leaderboard | |
| 83 | | 63.7% | May 2025 | Official leaderboard | |
| 84 | | 62.2% | Aug 2025 | Official leaderboard | |
| 85 | | 62.2% | Apr 2026 | Official leaderboard | |
| 86 | | 61.5% | Mar 2026 | Official leaderboard | |
| 87 | | 60% | Apr 2026 | Official leaderboard | |
| 88 | GLM-4.6V | 59.3% | Dec 2025 | Official leaderboard | |
| 89 | | 55.6% | Apr 2025 | Official leaderboard | |
| 90 | | 54.8% | Mar 2025 | Official leaderboard | |
| 91 | | 54.1% | Apr 2025 | Official leaderboard | |
| 92 | GPT-4.1 nano | 54.1% | Apr 2025 | Official leaderboard | |
| 93 | | 51.9% | Feb 2026 | Official leaderboard | |
| 94 | Command A | 50.4% | Official leaderboard | ||
| 95 | glm-4.7-flash | 46.6% | Jan 2026 | Official leaderboard | |
| 96 | | 45.9% | Jun 2024 | Official leaderboard | |
| 97 | Command-R+ August | 42.2% | Official leaderboard | ||
| 98 | | 40.7% | Mar 2026 | Official leaderboard | |
| 99 | | 40.3% | Aug 2026 | Official leaderboard | |
| 100 | | 40% | Jan 2025 | Official leaderboard | |
| 101 | | 39.3% | Mar 2025 | Official leaderboard | |
| 102 | | 38.9% | Dec 2025 | Official leaderboard | |
| 103 | | 35.6% | Dec 2025 | Official leaderboard | |
| 104 | Seed 1.6 Flash | 33.8% | Official leaderboard | ||
| 105 | | 29.6% | Jul 2024 | Official leaderboard | |
| 106 | | 28.9% | Dec 2024 | Official leaderboard | |
| 107 | | 26.7% | Mar 2025 | Official leaderboard | |
| 108 | Ministral 3 3B | 23.7% | Official leaderboard | ||
| 109 | Ministral 3 8B | 23% | Official leaderboard | ||
| 110 | | 22.2% | Dec 2024 | Official leaderboard | |
| 111 | | 21.5% | Sep 2024 | Official leaderboard | |
| 112 | | 20.7% | Apr 2025 | Official leaderboard | |
| 113 | | 14.1% | Sep 2024 | Official leaderboard | |
| 114 | | 11.1% | Apr 2025 | Official leaderboard | |
| 115 | | 10.4% | Apr 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5.4 | 97.8% | medium | Mar 2026 | Official leaderboard |
| 2 | | 97% | Aug 2026 | Official leaderboard | |
| 3 | | 96.3% | Dec 2025 | Official leaderboard | |
| 4 | | 95.6% | Feb 2026 | Official leaderboard | |
| 5 | Claude Opus 4.7 | 95.6% | Apr 2026 | Official leaderboard | |
| 6 | GPT-5.5 | 95.6% | Apr 2026 | Official leaderboard | |
| 7 | | 95.6% | Apr 2026 | Official leaderboard | |
| 8 | | 95.6% | May 2026 | Official leaderboard | |
| 9 | Claude Fable 5 | 95.6% | Jun 2026 | Official leaderboard | |
| 10 | Grok 4.5 | 95.6% | Jul 2026 | Official leaderboard | |
| 11 | GPT-5.6 Sol | 95.6% | Jul 2026 | Official leaderboard | |
| 12 | | 95.5% | Apr 2026 | Official leaderboard | |
| 13 | Claude Opus 4.8 | 94.8% | May 2026 | Official leaderboard | |
| 14 | Kimi K3 | 94.1% | Jul 2026 | Official leaderboard | |
| 15 | Grok 4.6 | 94.1% | Aug 2026 | Official leaderboard | |
| 16 | GPT-5.6 Terra | 93.3% | Jul 2026 | Official leaderboard | |
| 17 | o3 | 92.6% | Apr 2025 | Official leaderboard | |
| 18 | Claude Opus 4.6 | 92.6% | Feb 2026 | Official leaderboard | |
| 19 | Grok 4.20 | 92.6% | reasoning | Feb 2026 | Official leaderboard |
| 20 | | 92.6% | Jul 2026 | Official leaderboard | |
| 21 | Claude Opus 5 | 92.6% | Jul 2026 | Official leaderboard | |
| 22 | | 91.8% | Jun 2025 | Official leaderboard | |
| 23 | GPT-5 | 91.8% | medium | Aug 2025 | Official leaderboard |
| 24 | | 91.8% | Apr 2026 | Official leaderboard | |
| 25 | | 91.8% | Aug 2026 | Official leaderboard | |
| 26 | Claude Opus 4.5 | 91.1% | Nov 2025 | Official leaderboard | |
| 27 | GPT-5.2 | 91.1% | medium | Dec 2025 | Official leaderboard |
| 28 | | 91.1% | Mar 2026 | Official leaderboard | |
| 29 | GPT-5.4 Mini | 91.1% | medium | Mar 2026 | Official leaderboard |
| 30 | Grok 4.3 | 91.1% | Apr 2026 | Official leaderboard | |
| 31 | Claude Sonnet 5 | 91.1% | Jun 2026 | Official leaderboard | |
| 32 | GPT-5.6 Luna | 91.1% | Jul 2026 | Official leaderboard | |
| 33 | | 91.1% | Jul 2026 | Official leaderboard | |
| 34 | | 90.4% | Sep 2025 | Official leaderboard | |
| 35 | Claude Sonnet 4.6 | 90.4% | Feb 2026 | Official leaderboard | |
| 36 | Kimi K2.6 | 90.4% | Apr 2026 | Official leaderboard | |
| 37 | | 90.4% | Jul 2026 | Official leaderboard | |
| 38 | GPT-5.1 | 89.6% | medium | Nov 2025 | Official leaderboard |
| 39 | | 89.6% | May 2026 | Official leaderboard | |
| 40 | | 88.9% | Jul 2026 | Official leaderboard | |
| 41 | | 88.5% | Feb 2026 | Official leaderboard | |
| 42 | | 88.2% | Aug 2026 | Official leaderboard | |
| 43 | Kimi K2.5 | 87.4% | Jan 2026 | Official leaderboard | |
| 44 | | 87.4% | Aug 2026 | Official leaderboard | |
| 45 | | 86.7% | Feb 2026 | Official leaderboard | |
| 46 | MiMo-V2.5-Pro | 86.7% | Apr 2026 | Official leaderboard | |
| 47 | | 85.9% | Mar 2026 | Official leaderboard | |
| 48 | GLM-5.1 | 85.9% | Apr 2026 | Official leaderboard | |
| 49 | GLM-5.2 | 85.8% | Jun 2026 | Official leaderboard | |
| 50 | | 85.2% | Apr 2026 | Official leaderboard | |
| 51 | GLM-5.3 | 85.2% | Aug 2026 | Official leaderboard | |
| 52 | Claude Sonnet 4.5 | 81.5% | Sep 2025 | Official leaderboard | |
| 53 | GPT-4.1 | 80.7% | Apr 2025 | Official leaderboard | |
| 54 | GPT-5 mini | 80.7% | medium | Aug 2025 | Official leaderboard |
| 55 | | 80.7% | Feb 2026 | Official leaderboard | |
| 56 | | 80% | Jan 2025 | Official leaderboard | |
| 57 | | 80% | Apr 2025 | Official leaderboard | |
| 58 | o4-mini | 80% | Apr 2025 | Official leaderboard | |
| 59 | GPT-5.4 Nano | 80% | medium | Mar 2026 | Official leaderboard |
| 60 | | 79.5% | Jun 2026 | Official leaderboard | |
| 61 | | 79.3% | Aug 2026 | Official leaderboard | |
| 62 | | 77.8% | Apr 2026 | Official leaderboard | |
| 63 | MiMo-V2.5 | 77.8% | Apr 2026 | Official leaderboard | |
| 64 | | 76.3% | Dec 2025 | Official leaderboard | |
| 65 | | 76.3% | Mar 2026 | Official leaderboard | |
| 66 | | 74.8% | Feb 2026 | Official leaderboard | |
| 67 | o3-mini | 74.1% | Jan 2025 | Official leaderboard | |
| 68 | GPT-5 nano | 74.1% | medium | Aug 2025 | Official leaderboard |
| 69 | | 74.1% | Feb 2026 | Official leaderboard | |
| 70 | | 73.9% | Jul 2025 | Official leaderboard | |
| 71 | | 73.1% | Apr 2026 | Official leaderboard | |
| 72 | | 72.6% | Mar 2025 | Official leaderboard | |
| 73 | gpt-oss-120b | 71.8% | Aug 2025 | Official leaderboard | |
| 74 | | 71.6% | Feb 2026 | Official leaderboard | |
| 75 | | 69.6% | Jul 2026 | Official leaderboard | |
| 76 | GPT-4.1 mini | 68.2% | Apr 2025 | Official leaderboard | |
| 77 | | 67.9% | Aug 2026 | Official leaderboard | |
| 78 | | 66.9% | Apr 2026 | Official leaderboard | |
| 79 | Claude Haiku 4.5 | 65.9% | Oct 2025 | Official leaderboard | |
| 80 | | 65.7% | Jun 2026 | Official leaderboard | |
| 81 | | 63.9% | Jun 2025 | Official leaderboard | |
| 82 | | 63.7% | May 2025 | Official leaderboard | |
| 83 | | 62.2% | Aug 2025 | Official leaderboard | |
| 84 | | 62.2% | Apr 2026 | Official leaderboard | |
| 85 | | 61.5% | Mar 2026 | Official leaderboard | |
| 86 | | 60% | Apr 2026 | Official leaderboard | |
| 87 | GLM-4.6V | 59.3% | Dec 2025 | Official leaderboard | |
| 88 | | 55.6% | Apr 2025 | Official leaderboard | |
| 89 | | 54.8% | Mar 2025 | Official leaderboard | |
| 90 | | 54.1% | Apr 2025 | Official leaderboard | |
| 91 | GPT-4.1 nano | 54.1% | Apr 2025 | Official leaderboard | |
| 92 | | 51.9% | Feb 2026 | Official leaderboard | |
| 93 | glm-4.7-flash | 46.6% | Jan 2026 | Official leaderboard | |
| 94 | | 45.9% | Jun 2024 | Official leaderboard | |
| 95 | | 40.7% | Mar 2026 | Official leaderboard | |
| 96 | | 40.3% | Aug 2026 | Official leaderboard | |
| 97 | | 40% | Jan 2025 | Official leaderboard | |
| 98 | | 39.3% | Mar 2025 | Official leaderboard | |
| 99 | | 38.9% | Dec 2025 | Official leaderboard | |
| 100 | | 35.6% | Dec 2025 | Official leaderboard | |
| 101 | | 29.6% | Jul 2024 | Official leaderboard | |
| 102 | | 28.9% | Dec 2024 | Official leaderboard | |
| 103 | | 26.7% | Mar 2025 | Official leaderboard | |
| 104 | | 22.2% | Dec 2024 | Official leaderboard | |
| 105 | | 21.5% | Sep 2024 | Official leaderboard | |
| 106 | | 20.7% | Apr 2025 | Official leaderboard | |
| 107 | | 14.1% | Sep 2024 | Official leaderboard | |
| 108 | | 11.1% | Apr 2025 | Official leaderboard | |
| 109 | | 10.4% | Apr 2025 | Official 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 Linguistic Knowledge Benchmark (Fab AI) 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 Linguistic Knowledge Benchmark (Fab AI) leaderboard
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Linguistic Knowledge Benchmark (Fab AI) leaderboard
O3 on the official leaderboard passed 85% in April 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Linguistic Knowledge Benchmark (Fab AI) 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 Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (115 entries).
- Pass Models scored 109 models we track, plus 6 other entries on its leaderboard.
- Pass Newest score The newest is from August 2026, for GLM-5.3.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Claude Opus 5 (#11).
- Note Headroom Saturated. The best is 97.8%, past 85% since April 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on fab-ai.org: 115 rows for models we track and 6 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.