EKI Mälumäng
Models answer 800 Estonian quiz questions without answer choices. Politics and geography each contribute 80 questions. GPT-5.4 nano judges answers that miss an exact match.
The institute publishes accuracy for 93 models. The authors selected harder questions from two volumes by Lembit and Uno Ainsoo.
- Released
- August 2026
- Kind
- Knowledge in many languages
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Short answer
- Measures
- Capability
- Language
- Estonian
- Interaction
- Single turn
- Items from
- Real work and use
- 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
Gemini 3.1 Pro leads with 50.8% Gemini 3.1 Pro leads with 50.8%
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.
- 50.8
Gemini 3.1 Pro
- 50.6
Gemini 4 Argon
- 50.3
Gemini 3.8 Flash
- 47.0
Gemini 3.7 Flash
- 45.8 GPT-6 Astra
- 43.9 GPT-5.6 Sol
- 42.3
Gemini 3.5 Flash
- 41.3
Gemini 3.6 Flash
- 39.1 Claude Fable 5.2
- 38.4 GPT-5.5
- 37.1 GPT-6 Sol
- 30.4 GPT-6.1 Terra
- 28.5 Claude Fable 5
- 27.1 Claude Fable 5.1
- 26.8
Gemini 3 Flash
- 26.0
Gemini 2.5 Pro
- 24.1
Muse Spark 1.3
- 24.1
Muse Spark Open
- 23.1
Muse Spark 1.2
- 22.3 GPT-6 Luna
- 21.3 Claude Opus 5.5
- 21.0 Claude Opus 5
- 20.1 GPT-5.6 Terra
- 19.3 GPT-5
- 18.6 GPT-5.6 Luna
- 18.5 Grok 4.5
- 17.6 Grok 4.7
- 16.9 Grok 4.6
- 12.5
Qwen3.7-Max
- 12.3 GPT-5.2
- 12.1
DeepSeek-V4-Pro
- 11.4
DeepSeek V4.1 Flash
- 10.9 Claude Sonnet 5.5
- 10.0 Kimi K3
- 8.62 Claude Opus 4.7
- 8.62 Claude Opus 4.8
- 7.25 GLM-5.3
- 7.12 Claude Opus 4.6
- 7.12 GLM-5
- 6.75
Qwen 3.8 Max
- 6.25 GLM-5.3-Flash
- 6.12 Claude Opus 4
- 6.12 GLM-5.2
- 5.88 Claude Opus 4.5
- 5.25
Tencent Hy4 preview
- 5.12
DeepSeek-V4-Flash
- 4.88 GPT-5.4
- 4.62
Mistral Large 4
- 4.50 GLM-4.7
- 4.38 GPT-4.1
- 4.25 GPT-4o
- 4.25 Claude Sonnet 5
- 3.50
Qwen 3.6 Plus
- 3.50 Claude Haiku 5.5
- 3.38 GPT-4
- 3.12 GPT-5.4 Mini
- 3.12
Nemotron 3 Ultra
- 3.00 MiMo-V2.6 Pro
- 2.88
MiniMax-M3
- 2.75
Llama 4 Maverick
- 2.75 Claude Sonnet 4.6
- 2.75
Qwen3.8 Flash
- 2.62 Llama 3.1 70B Instruct
- 2.38 Claude Sonnet 4
- 2.25
DeepSeek-V3.2
- 2.12
Muse Glimmer
- 2.00 Mistral Large 2512
- 2.00 gpt-oss-120b
- 2.00 Kimi K2
- 2.00
Gemini 2.5 Flash
- 1.88
Llama 3.3 70B Instruct
- 1.75 Nemotron 3 Super 120B
- 1.38
Gemma 2 27B
- 1.38 MiMo-V2.6 Flash
- 1.25
Gemma 4 31B IT
- 1.25
Step 3.7 Flash
- 1.12 Command R+ (08-2024)
- 1.12 GPT-3.5 Turbo
- 1.12
DeepSeek-V3
- 1.12 Claude Sonnet 4.5
- 1.12
Qwen3.5-27B
- 1.12
MiniMax-M2.7
- 1.12
Mistral Medium 3.5
- 1.00
Mistral Small 4
- 0.88
Gemma 3 27B
- 0.88
Step 3.5 Flash
- 0.88
Qwen3.6 27B
- 0.75 Claude 3 Haiku
- 0.75 Claude Haiku 4.5
- 0.75 Grok 4.20
- 0.62
Laguna S 2.1
- 0.62
Qwen 3.8 27B
- 0.50 GPT-4o mini
- 1
Gemini 3.1 Pro 50.8%
- 2
Gemini 4 Argon 50.6%
- 3
Gemini 3.8 Flash 50.3%
- 4
Gemini 3.7 Flash 47%
- 5 GPT-6 Astra 45.8%
- 6 GPT-5.6 Sol 43.9%
- 7
Gemini 3.5 Flash 42.3%
- 8
Gemini 3.6 Flash 41.3%
- 9 Claude Fable 5.2 39.1%
- 10 GPT-5.5 38.4%
- 11 GPT-6 Sol 37.1%
- 12 GPT-6.1 Terra 30.4%
- 13 Claude Fable 5 28.5%
- 14 Claude Fable 5.1 27.1%
- 15
Gemini 3 Flash 26.8%
- 16
Gemini 2.5 Pro Jun 2025 26%
- 17
Muse Spark 1.3 24.1%
- 18
Muse Spark Open 24.1%
- 19
Muse Spark 1.2 23.1%
- 20 GPT-6 Luna 22.3%
- 21 Claude Opus 5.5 21.3%
- 22 Claude Opus 5 21%
- 23 GPT-5.6 Terra 20.1%
- 24 GPT-5 19.3%
- 25 GPT-5.6 Luna 18.6%
- 26 Grok 4.5 18.5%
- 27 Grok 4.7 17.6%
- 28 Grok 4.6 16.9%
- 29
Qwen3.7-Max 12.5%
- 30 GPT-5.2 12.3%
- 31
DeepSeek-V4-Pro 12.1%
- 32
DeepSeek V4.1 Flash 11.4%
- 33 Claude Sonnet 5.5 10.9%
- 34 Kimi K3 10%
- 35 Claude Opus 4.7 8.62%
- 36 Claude Opus 4.8 8.62%
- 37 GLM-5.3 7.25%
- 38 Claude Opus 4.6 7.12%
- 39 GLM-5 7.12%
- 40
Qwen 3.8 Max 6.75%
- 41 GLM-5.3-Flash 6.25%
- 42 Claude Opus 4 6.12%
- 43 GLM-5.2 6.12%
- 44 Claude Opus 4.5 5.88%
- 45
Tencent Hy4 preview 5.25%
- 46
DeepSeek-V4-Flash 5.12%
- 47 GPT-5.4 4.88%
- 48
Mistral Large 4 4.62%
- 49 GLM-4.7 4.50%
- 50 GPT-4.1 4.38%
- 51 GPT-4o Mar 2025 4.25%
- 52 Claude Sonnet 5 4.25%
- 53
Qwen 3.6 Plus 3.50%
- 54 Claude Haiku 5.5 3.50%
- 55 GPT-4 Jun 2023 3.38%
- 56 GPT-5.4 Mini 3.12%
- 57
Nemotron 3 Ultra 3.12%
- 58 MiMo-V2.6 Pro 3.00%
- 59
MiniMax-M3 2.88%
- 60
Llama 4 Maverick 2.75%
- 61 Claude Sonnet 4.6 2.75%
- 62
Qwen3.8 Flash 2.75%
- 63 Llama 3.1 70B Instruct 2.62%
- 64 Claude Sonnet 4 2.38%
- 65
DeepSeek-V3.2 2.25%
- 66
Muse Glimmer 2.12%
- 67 Mistral Large 2512 2.00%
- 68 gpt-oss-120b 2.00%
- 69 Kimi K2 Sep 2025 2.00%
- 70
Gemini 2.5 Flash Sep 2025 2.00%
- 71
Llama 3.3 70B Instruct 1.88%
- 72 Nemotron 3 Super 120B 1.75%
- 73
Gemma 2 27B 1.38%
- 74 MiMo-V2.6 Flash 1.38%
- 75
Gemma 4 31B IT 1.25%
- 76
Step 3.7 Flash 1.25%
- 77 Command R+ (08-2024) 1.12%
- 78 GPT-3.5 Turbo Jan 2024 1.12%
- 79
DeepSeek-V3 Mar 2025 1.12%
- 80 Claude Sonnet 4.5 1.12%
- 81
Qwen3.5-27B 1.12%
- 82
MiniMax-M2.7 1.12%
- 83
Mistral Medium 3.5 1.12%
- 84
Mistral Small 4 1.00%
- 85
Gemma 3 27B 0.88%
- 86
Step 3.5 Flash 0.88%
- 87
Qwen3.6 27B 0.88%
- 88 Claude 3 Haiku 0.75%
- 89 Claude Haiku 4.5 0.75%
- 90 Grok 4.20 0.75%
- 91
Laguna S 2.1 0.62%
- 92
Qwen 3.8 27B 0.62%
- 93 GPT-4o mini 0.50%
Source: Official EKI Mälumäng leaderboard
- 50.8
Gemini 3.1 Pro
- 50.6
Gemini 4 Argon
- 50.3
Gemini 3.8 Flash
- 47.0
Gemini 3.7 Flash
- 45.8 GPT-6 Astra
- 43.9 GPT-5.6 Sol
- 42.3
Gemini 3.5 Flash
- 41.3
Gemini 3.6 Flash
- 39.1 Claude Fable 5.2
- 38.4 GPT-5.5
- 37.1 GPT-6 Sol
- 30.4 GPT-6.1 Terra
- 28.5 Claude Fable 5
- 27.1 Claude Fable 5.1
- 26.8
Gemini 3 Flash
- 26.0
Gemini 2.5 Pro
- 24.1
Muse Spark 1.3
- 24.1
Muse Spark Open
- 23.1
Muse Spark 1.2
- 22.3 GPT-6 Luna
- 21.3 Claude Opus 5.5
- 21.0 Claude Opus 5
- 20.1 GPT-5.6 Terra
- 19.3 GPT-5
- 18.6 GPT-5.6 Luna
- 18.5 Grok 4.5
- 17.6 Grok 4.7
- 16.9 Grok 4.6
- 12.5
Qwen3.7-Max
- 12.3 GPT-5.2
- 12.1
DeepSeek-V4-Pro
- 11.4
DeepSeek V4.1 Flash
- 10.9 Claude Sonnet 5.5
- 10.0 Kimi K3
- 8.62 Claude Opus 4.7
- 8.62 Claude Opus 4.8
- 7.25 GLM-5.3
- 7.12 Claude Opus 4.6
- 7.12 GLM-5
- 6.75
Qwen 3.8 Max
- 6.25 GLM-5.3-Flash
- 6.12 Claude Opus 4
- 6.12 GLM-5.2
- 5.88 Claude Opus 4.5
- 5.25
Tencent Hy4 preview
- 5.12
DeepSeek-V4-Flash
- 4.88 GPT-5.4
- 4.62
Mistral Large 4
- 4.50 GLM-4.7
- 4.38 GPT-4.1
- 4.25 GPT-4o
- 4.25 Claude Sonnet 5
- 3.50
Qwen 3.6 Plus
- 3.50 Claude Haiku 5.5
- 3.38 GPT-4
- 3.12 GPT-5.4 Mini
- 3.12
Nemotron 3 Ultra
- 3.00 MiMo-V2.6 Pro
- 2.88
MiniMax-M3
- 2.75
Llama 4 Maverick
- 2.75 Claude Sonnet 4.6
- 2.75
Qwen3.8 Flash
- 2.38 Claude Sonnet 4
- 2.25
DeepSeek-V3.2
- 2.12
Muse Glimmer
- 2.00 gpt-oss-120b
- 2.00 Kimi K2
- 2.00
Gemini 2.5 Flash
- 1.88
Llama 3.3 70B Instruct
- 1.38
Gemma 2 27B
- 1.38 MiMo-V2.6 Flash
- 1.25
Gemma 4 31B IT
- 1.25
Step 3.7 Flash
- 1.12 GPT-3.5 Turbo
- 1.12
DeepSeek-V3
- 1.12 Claude Sonnet 4.5
- 1.12
Qwen3.5-27B
- 1.12
MiniMax-M2.7
- 1.12
Mistral Medium 3.5
- 1.00
Mistral Small 4
- 0.88
Gemma 3 27B
- 0.88
Step 3.5 Flash
- 0.88
Qwen3.6 27B
- 0.75 Claude 3 Haiku
- 0.75 Claude Haiku 4.5
- 0.75 Grok 4.20
- 0.62
Laguna S 2.1
- 0.62
Qwen 3.8 27B
- 0.50 GPT-4o mini
- 1
Gemini 3.1 Pro 50.8%
- 2
Gemini 4 Argon 50.6%
- 3
Gemini 3.8 Flash 50.3%
- 4
Gemini 3.7 Flash 47%
- 5 GPT-6 Astra 45.8%
- 6 GPT-5.6 Sol 43.9%
- 7
Gemini 3.5 Flash 42.3%
- 8
Gemini 3.6 Flash 41.3%
- 9 Claude Fable 5.2 39.1%
- 10 GPT-5.5 38.4%
- 11 GPT-6 Sol 37.1%
- 12 GPT-6.1 Terra 30.4%
- 13 Claude Fable 5 28.5%
- 14 Claude Fable 5.1 27.1%
- 15
Gemini 3 Flash 26.8%
- 16
Gemini 2.5 Pro Jun 2025 26%
- 17
Muse Spark 1.3 24.1%
- 18
Muse Spark Open 24.1%
- 19
Muse Spark 1.2 23.1%
- 20 GPT-6 Luna 22.3%
- 21 Claude Opus 5.5 21.3%
- 22 Claude Opus 5 21%
- 23 GPT-5.6 Terra 20.1%
- 24 GPT-5 19.3%
- 25 GPT-5.6 Luna 18.6%
- 26 Grok 4.5 18.5%
- 27 Grok 4.7 17.6%
- 28 Grok 4.6 16.9%
- 29
Qwen3.7-Max 12.5%
- 30 GPT-5.2 12.3%
- 31
DeepSeek-V4-Pro 12.1%
- 32
DeepSeek V4.1 Flash 11.4%
- 33 Claude Sonnet 5.5 10.9%
- 34 Kimi K3 10%
- 35 Claude Opus 4.7 8.62%
- 36 Claude Opus 4.8 8.62%
- 37 GLM-5.3 7.25%
- 38 Claude Opus 4.6 7.12%
- 39 GLM-5 7.12%
- 40
Qwen 3.8 Max 6.75%
- 41 GLM-5.3-Flash 6.25%
- 42 Claude Opus 4 6.12%
- 43 GLM-5.2 6.12%
- 44 Claude Opus 4.5 5.88%
- 45
Tencent Hy4 preview 5.25%
- 46
DeepSeek-V4-Flash 5.12%
- 47 GPT-5.4 4.88%
- 48
Mistral Large 4 4.62%
- 49 GLM-4.7 4.50%
- 50 GPT-4.1 4.38%
- 51 GPT-4o Mar 2025 4.25%
- 52 Claude Sonnet 5 4.25%
- 53
Qwen 3.6 Plus 3.50%
- 54 Claude Haiku 5.5 3.50%
- 55 GPT-4 Jun 2023 3.38%
- 56 GPT-5.4 Mini 3.12%
- 57
Nemotron 3 Ultra 3.12%
- 58 MiMo-V2.6 Pro 3.00%
- 59
MiniMax-M3 2.88%
- 60
Llama 4 Maverick 2.75%
- 61 Claude Sonnet 4.6 2.75%
- 62
Qwen3.8 Flash 2.75%
- 63 Claude Sonnet 4 2.38%
- 64
DeepSeek-V3.2 2.25%
- 65
Muse Glimmer 2.12%
- 66 gpt-oss-120b 2.00%
- 67 Kimi K2 Sep 2025 2.00%
- 68
Gemini 2.5 Flash Sep 2025 2.00%
- 69
Llama 3.3 70B Instruct 1.88%
- 70
Gemma 2 27B 1.38%
- 71 MiMo-V2.6 Flash 1.38%
- 72
Gemma 4 31B IT 1.25%
- 73
Step 3.7 Flash 1.25%
- 74 GPT-3.5 Turbo Jan 2024 1.12%
- 75
DeepSeek-V3 Mar 2025 1.12%
- 76 Claude Sonnet 4.5 1.12%
- 77
Qwen3.5-27B 1.12%
- 78
MiniMax-M2.7 1.12%
- 79
Mistral Medium 3.5 1.12%
- 80
Mistral Small 4 1.00%
- 81
Gemma 3 27B 0.88%
- 82
Step 3.5 Flash 0.88%
- 83
Qwen3.6 27B 0.88%
- 84 Claude 3 Haiku 0.75%
- 85 Claude Haiku 4.5 0.75%
- 86 Grok 4.20 0.75%
- 87
Laguna S 2.1 0.62%
- 88
Qwen 3.8 27B 0.62%
- 89 GPT-4o mini 0.50%
Source: Official EKI Mälumäng leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 50.8% | Feb 2026 | Official leaderboard | |
| 2 | | 50.6% | Sep 2026 | Official leaderboard | |
| 3 | | 50.3% | Sep 2026 | Official leaderboard | |
| 4 | | 47% | Aug 2026 | Official leaderboard | |
| 5 | GPT-6 Astra | 45.8% | Sep 2026 | Official leaderboard | |
| 6 | GPT-5.6 Sol | 43.9% | Jul 2026 | Official leaderboard | |
| 7 | | 42.3% | May 2026 | Official leaderboard | |
| 8 | | 41.3% | Jul 2026 | Official leaderboard | |
| 9 | Claude Fable 5.2 | 39.1% | Nov 2026 | Official leaderboard | |
| 10 | GPT-5.5 | 38.4% | Apr 2026 | Official leaderboard | |
| 11 | GPT-6 Sol | 37.1% | Sep 2026 | Official leaderboard | |
| 12 | GPT-6.1 Terra | 30.4% | Oct 2026 | Official leaderboard | |
| 13 | Claude Fable 5 | 28.5% | Jun 2026 | Official leaderboard | |
| 14 | Claude Fable 5.1 | 27.1% | Sep 2026 | Official leaderboard | |
| 15 | | 26.8% | Dec 2025 | Official leaderboard | |
| 16 | | 26% | Jun 2025 | Official leaderboard | |
| 17 | | 24.1% | Sep 2026 | Official leaderboard | |
| 18 | | 24.1% | Oct 2026 | Official leaderboard | |
| 19 | | 23.1% | Aug 2026 | Official leaderboard | |
| 20 | GPT-6 Luna | 22.3% | Sep 2026 | Official leaderboard | |
| 21 | Claude Opus 5.5 | 21.3% | Sep 2026 | Official leaderboard | |
| 22 | Claude Opus 5 | 21% | Jul 2026 | Official leaderboard | |
| 23 | GPT-5.6 Terra | 20.1% | Jul 2026 | Official leaderboard | |
| 24 | GPT-5 | 19.3% | Aug 2025 | Official leaderboard | |
| 25 | GPT-5.6 Luna | 18.6% | Jul 2026 | Official leaderboard | |
| 26 | Grok 4.5 | 18.5% | Jul 2026 | Official leaderboard | |
| 27 | Grok 4.7 | 17.6% | Sep 2026 | Official leaderboard | |
| 28 | Grok 4.6 | 16.9% | Aug 2026 | Official leaderboard | |
| 29 | | 12.5% | May 2026 | Official leaderboard | |
| 30 | GPT-5.2 | 12.3% | Dec 2025 | Official leaderboard | |
| 31 | | 12.1% | Apr 2026 | Official leaderboard | |
| 32 | | 11.4% | Sep 2026 | Official leaderboard | |
| 33 | Claude Sonnet 5.5 | 10.9% | Sep 2026 | Official leaderboard | |
| 34 | Kimi K3 | 10% | Jul 2026 | Official leaderboard | |
| 35 | Claude Opus 4.7 | 8.62% | Apr 2026 | Official leaderboard | |
| 36 | Claude Opus 4.8 | 8.62% | May 2026 | Official leaderboard | |
| 37 | GLM-5.3 | 7.25% | Aug 2026 | Official leaderboard | |
| 38 | Claude Opus 4.6 | 7.12% | Feb 2026 | Official leaderboard | |
| 39 | GLM-5 | 7.12% | Feb 2026 | Official leaderboard | |
| 40 | | 6.75% | Aug 2026 | Official leaderboard | |
| 41 | GLM-5.3-Flash | 6.25% | Aug 2026 | Official leaderboard | |
| 42 | Claude Opus 4 | 6.12% | May 2025 | Official leaderboard | |
| 43 | GLM-5.2 | 6.12% | Jun 2026 | Official leaderboard | |
| 44 | Claude Opus 4.5 | 5.88% | Nov 2025 | Official leaderboard | |
| 45 | | 5.25% | Aug 2026 | Official leaderboard | |
| 46 | | 5.12% | Apr 2026 | Official leaderboard | |
| 47 | GPT-5.4 | 4.88% | Mar 2026 | Official leaderboard | |
| 48 | | 4.62% | Oct 2026 | Official leaderboard | |
| 49 | GLM-4.7 | 4.50% | Dec 2025 | Official leaderboard | |
| 50 | GPT-4.1 | 4.38% | Apr 2025 | Official leaderboard | |
| 51 | GPT-4o Mar 2025 | 4.25% | Mar 2025 | Official leaderboard | |
| 52 | Claude Sonnet 5 | 4.25% | Jun 2026 | Official leaderboard | |
| 53 | | 3.50% | Mar 2026 | Official leaderboard | |
| 54 | Claude Haiku 5.5 | 3.50% | Oct 2026 | Official leaderboard | |
| 55 | GPT-4 Jun 2023 | 3.38% | Jun 2023 | Official leaderboard | |
| 56 | GPT-5.4 Mini | 3.12% | Mar 2026 | Official leaderboard | |
| 57 | | 3.12% | Jun 2026 | Official leaderboard | |
| 58 | MiMo-V2.6 Pro | 3.00% | Sep 2026 | Official leaderboard | |
| 59 | | 2.88% | Jun 2026 | Official leaderboard | |
| 60 | | 2.75% | Apr 2025 | Official leaderboard | |
| 61 | Claude Sonnet 4.6 | 2.75% | Feb 2026 | Official leaderboard | |
| 62 | | 2.75% | Aug 2026 | Official leaderboard | |
| 63 | Llama 3.1 70B Instruct open weights | 2.62% | Official leaderboard | ||
| 64 | Claude Sonnet 4 | 2.38% | May 2025 | Official leaderboard | |
| 65 | | 2.25% | Dec 2025 | Official leaderboard | |
| 66 | | 2.12% | Aug 2026 | Official leaderboard | |
| 67 | Mistral Large 2512 open weights | 2.00% | Official leaderboard | ||
| 68 | gpt-oss-120b | 2.00% | Aug 2025 | Official leaderboard | |
| 69 | Kimi K2 Sep 2025 | 2.00% | Sep 2025 | Official leaderboard | |
| 70 | | 2.00% | Sep 2025 | Official leaderboard | |
| 71 | | 1.88% | Dec 2024 | Official leaderboard | |
| 72 | Nemotron 3 Super 120B open weights | 1.75% | Official leaderboard | ||
| 73 | | 1.38% | Jun 2024 | Official leaderboard | |
| 74 | MiMo-V2.6 Flash | 1.38% | Sep 2026 | Official leaderboard | |
| 75 | | 1.25% | Apr 2026 | Official leaderboard | |
| 76 | | 1.25% | May 2026 | Official leaderboard | |
| 77 | Command R+ (08-2024) | 1.12% | Official leaderboard | ||
| 78 | GPT-3.5 Turbo Jan 2024 | 1.12% | Jan 2024 | Official leaderboard | |
| 79 | | 1.12% | Mar 2025 | Official leaderboard | |
| 80 | Claude Sonnet 4.5 | 1.12% | Sep 2025 | Official leaderboard | |
| 81 | | 1.12% | Feb 2026 | Official leaderboard | |
| 82 | | 1.12% | Mar 2026 | Official leaderboard | |
| 83 | | 1.12% | Apr 2026 | Official leaderboard | |
| 84 | | 1.00% | Mar 2026 | Official leaderboard | |
| 85 | | 0.88% | Mar 2025 | Official leaderboard | |
| 86 | | 0.88% | Feb 2026 | Official leaderboard | |
| 87 | | 0.88% | Apr 2026 | Official leaderboard | |
| 88 | Claude 3 Haiku | 0.75% | Mar 2024 | Official leaderboard | |
| 89 | Claude Haiku 4.5 | 0.75% | Oct 2025 | Official leaderboard | |
| 90 | Grok 4.20 | 0.75% | Feb 2026 | Official leaderboard | |
| 91 | | 0.62% | Jul 2026 | Official leaderboard | |
| 92 | | 0.62% | Aug 2026 | Official leaderboard | |
| 93 | GPT-4o mini | 0.50% | Jul 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 50.8% | Feb 2026 | Official leaderboard | |
| 2 | | 50.6% | Sep 2026 | Official leaderboard | |
| 3 | | 50.3% | Sep 2026 | Official leaderboard | |
| 4 | | 47% | Aug 2026 | Official leaderboard | |
| 5 | GPT-6 Astra | 45.8% | Sep 2026 | Official leaderboard | |
| 6 | GPT-5.6 Sol | 43.9% | Jul 2026 | Official leaderboard | |
| 7 | | 42.3% | May 2026 | Official leaderboard | |
| 8 | | 41.3% | Jul 2026 | Official leaderboard | |
| 9 | Claude Fable 5.2 | 39.1% | Nov 2026 | Official leaderboard | |
| 10 | GPT-5.5 | 38.4% | Apr 2026 | Official leaderboard | |
| 11 | GPT-6 Sol | 37.1% | Sep 2026 | Official leaderboard | |
| 12 | GPT-6.1 Terra | 30.4% | Oct 2026 | Official leaderboard | |
| 13 | Claude Fable 5 | 28.5% | Jun 2026 | Official leaderboard | |
| 14 | Claude Fable 5.1 | 27.1% | Sep 2026 | Official leaderboard | |
| 15 | | 26.8% | Dec 2025 | Official leaderboard | |
| 16 | | 26% | Jun 2025 | Official leaderboard | |
| 17 | | 24.1% | Sep 2026 | Official leaderboard | |
| 18 | | 24.1% | Oct 2026 | Official leaderboard | |
| 19 | | 23.1% | Aug 2026 | Official leaderboard | |
| 20 | GPT-6 Luna | 22.3% | Sep 2026 | Official leaderboard | |
| 21 | Claude Opus 5.5 | 21.3% | Sep 2026 | Official leaderboard | |
| 22 | Claude Opus 5 | 21% | Jul 2026 | Official leaderboard | |
| 23 | GPT-5.6 Terra | 20.1% | Jul 2026 | Official leaderboard | |
| 24 | GPT-5 | 19.3% | Aug 2025 | Official leaderboard | |
| 25 | GPT-5.6 Luna | 18.6% | Jul 2026 | Official leaderboard | |
| 26 | Grok 4.5 | 18.5% | Jul 2026 | Official leaderboard | |
| 27 | Grok 4.7 | 17.6% | Sep 2026 | Official leaderboard | |
| 28 | Grok 4.6 | 16.9% | Aug 2026 | Official leaderboard | |
| 29 | | 12.5% | May 2026 | Official leaderboard | |
| 30 | GPT-5.2 | 12.3% | Dec 2025 | Official leaderboard | |
| 31 | | 12.1% | Apr 2026 | Official leaderboard | |
| 32 | | 11.4% | Sep 2026 | Official leaderboard | |
| 33 | Claude Sonnet 5.5 | 10.9% | Sep 2026 | Official leaderboard | |
| 34 | Kimi K3 | 10% | Jul 2026 | Official leaderboard | |
| 35 | Claude Opus 4.7 | 8.62% | Apr 2026 | Official leaderboard | |
| 36 | Claude Opus 4.8 | 8.62% | May 2026 | Official leaderboard | |
| 37 | GLM-5.3 | 7.25% | Aug 2026 | Official leaderboard | |
| 38 | Claude Opus 4.6 | 7.12% | Feb 2026 | Official leaderboard | |
| 39 | GLM-5 | 7.12% | Feb 2026 | Official leaderboard | |
| 40 | | 6.75% | Aug 2026 | Official leaderboard | |
| 41 | GLM-5.3-Flash | 6.25% | Aug 2026 | Official leaderboard | |
| 42 | Claude Opus 4 | 6.12% | May 2025 | Official leaderboard | |
| 43 | GLM-5.2 | 6.12% | Jun 2026 | Official leaderboard | |
| 44 | Claude Opus 4.5 | 5.88% | Nov 2025 | Official leaderboard | |
| 45 | | 5.25% | Aug 2026 | Official leaderboard | |
| 46 | | 5.12% | Apr 2026 | Official leaderboard | |
| 47 | GPT-5.4 | 4.88% | Mar 2026 | Official leaderboard | |
| 48 | | 4.62% | Oct 2026 | Official leaderboard | |
| 49 | GLM-4.7 | 4.50% | Dec 2025 | Official leaderboard | |
| 50 | GPT-4.1 | 4.38% | Apr 2025 | Official leaderboard | |
| 51 | GPT-4o Mar 2025 | 4.25% | Mar 2025 | Official leaderboard | |
| 52 | Claude Sonnet 5 | 4.25% | Jun 2026 | Official leaderboard | |
| 53 | | 3.50% | Mar 2026 | Official leaderboard | |
| 54 | Claude Haiku 5.5 | 3.50% | Oct 2026 | Official leaderboard | |
| 55 | GPT-4 Jun 2023 | 3.38% | Jun 2023 | Official leaderboard | |
| 56 | GPT-5.4 Mini | 3.12% | Mar 2026 | Official leaderboard | |
| 57 | | 3.12% | Jun 2026 | Official leaderboard | |
| 58 | MiMo-V2.6 Pro | 3.00% | Sep 2026 | Official leaderboard | |
| 59 | | 2.88% | Jun 2026 | Official leaderboard | |
| 60 | | 2.75% | Apr 2025 | Official leaderboard | |
| 61 | Claude Sonnet 4.6 | 2.75% | Feb 2026 | Official leaderboard | |
| 62 | | 2.75% | Aug 2026 | Official leaderboard | |
| 63 | Claude Sonnet 4 | 2.38% | May 2025 | Official leaderboard | |
| 64 | | 2.25% | Dec 2025 | Official leaderboard | |
| 65 | | 2.12% | Aug 2026 | Official leaderboard | |
| 66 | gpt-oss-120b | 2.00% | Aug 2025 | Official leaderboard | |
| 67 | Kimi K2 Sep 2025 | 2.00% | Sep 2025 | Official leaderboard | |
| 68 | | 2.00% | Sep 2025 | Official leaderboard | |
| 69 | | 1.88% | Dec 2024 | Official leaderboard | |
| 70 | | 1.38% | Jun 2024 | Official leaderboard | |
| 71 | MiMo-V2.6 Flash | 1.38% | Sep 2026 | Official leaderboard | |
| 72 | | 1.25% | Apr 2026 | Official leaderboard | |
| 73 | | 1.25% | May 2026 | Official leaderboard | |
| 74 | GPT-3.5 Turbo Jan 2024 | 1.12% | Jan 2024 | Official leaderboard | |
| 75 | | 1.12% | Mar 2025 | Official leaderboard | |
| 76 | Claude Sonnet 4.5 | 1.12% | Sep 2025 | Official leaderboard | |
| 77 | | 1.12% | Feb 2026 | Official leaderboard | |
| 78 | | 1.12% | Mar 2026 | Official leaderboard | |
| 79 | | 1.12% | Apr 2026 | Official leaderboard | |
| 80 | | 1.00% | Mar 2026 | Official leaderboard | |
| 81 | | 0.88% | Mar 2025 | Official leaderboard | |
| 82 | | 0.88% | Feb 2026 | Official leaderboard | |
| 83 | | 0.88% | Apr 2026 | Official leaderboard | |
| 84 | Claude 3 Haiku | 0.75% | Mar 2024 | Official leaderboard | |
| 85 | Claude Haiku 4.5 | 0.75% | Oct 2025 | Official leaderboard | |
| 86 | Grok 4.20 | 0.75% | Feb 2026 | Official leaderboard | |
| 87 | | 0.62% | Jul 2026 | Official leaderboard | |
| 88 | | 0.62% | Aug 2026 | Official leaderboard | |
| 89 | GPT-4o mini | 0.50% | Jul 2024 | Official leaderboard |
Rankings by part
We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as ajalugu, poliitika and sport. Gemini 4 Argon leads 4 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
ajalugu
89 models we track have a score here.
- 1
Gemini 3.8 Flash ↑2 53.8%
- 2
Gemini 3.1 Pro ↓1 48.8%
- 3
Gemini 4 Argon ↓1 48.8%
- 4
Gemini 3.7 Flash 47.5%
- 5 GPT-6 Astra 47.5%
- 6 GPT-5.6 Sol 46.3%
- 7 Claude Fable 5.2 ↑2 42.5%
- 8
Gemini 3.6 Flash 41.3%
- 9 GPT-5.5 ↑1 40%
- 10 GPT-6 Sol ↑1 40%
poliitika
89 models we track have a score here.
- 1
Gemini 3.1 Pro 56.3%
- 2
Gemini 3.7 Flash ↑2 51.3%
- 3
Gemini 3.8 Flash 50%
- 4 GPT-6 Astra ↑1 47.5%
- 5
Gemini 3.5 Flash ↑2 45%
- 6
Gemini 4 Argon ↓4 43.8%
- 7 GPT-5.5 ↑3 38.8%
- 8 GPT-5.6 Sol ↓2 38.8%
- 9 Claude Fable 5.2 38.8%
- 10 Claude Fable 5 ↑3 37.5%
sport
89 models we track have a score here.
- 1
Gemini 3.8 Flash ↑2 52.5%
- 2
Gemini 3.7 Flash ↑2 48.8%
- 3
Gemini 4 Argon ↓1 48.8%
- 4
Gemini 3.1 Pro ↓3 41.3%
- 5
Gemini 3.6 Flash ↑3 41.3%
- 6
Gemini 3.5 Flash ↑1 40%
- 7 GPT-5.6 Sol ↓1 33.8%
- 8 Claude Fable 5.2 ↑1 30%
- 9 GPT-5.5 ↑1 28.8%
- 10 GPT-6 Astra ↓5 28.8%
loodus
89 models we track have a score here.
- 1
Gemini 4 Argon ↑1 61.3%
- 2 GPT-6 Astra ↑3 56.3%
- 3 GPT-5.6 Sol ↑3 53.8%
- 4
Gemini 3.8 Flash ↓1 50%
- 5 Claude Fable 5.2 ↑4 48.8%
- 6
Gemini 3.1 Pro ↓5 47.5%
- 7
Gemini 3.7 Flash ↓3 47.5%
- 8 GPT-5.5 ↑2 45%
- 9 GPT-6 Sol ↑2 45%
- 10
Gemini 3.5 Flash ↓3 43.8%
geograafia
89 models we track have a score here.
- 1
Gemini 3.1 Pro 68.8%
- 2
Gemini 3.8 Flash ↑1 63.8%
- 3 GPT-6 Astra ↑2 62.5%
- 4
Gemini 4 Argon ↓2 61.3%
- 5
Gemini 3.7 Flash ↓1 60%
- 6 Claude Fable 5.2 ↑3 60%
- 7
Gemini 3.5 Flash 56.3%
- 8 GPT-5.6 Sol ↓2 55%
- 9 GPT-5.5 ↑1 52.5%
- 10
Gemini 3.6 Flash ↓2 52.5%
varia
89 models we track have a score here.
- 1
Gemini 4 Argon ↑1 43.8%
- 2
Gemini 3.1 Pro ↓1 41.3%
- 3
Gemini 3.7 Flash ↑1 38.8%
- 4
Gemini 3.8 Flash ↓1 38.8%
- 5 GPT-6 Astra 36.3%
- 6 GPT-6 Sol ↑5 36.3%
- 7
Gemini 3.5 Flash 35%
- 8 GPT-5.5 ↑2 33.8%
- 9 GPT-5.6 Sol ↓3 33.8%
- 10
Gemini 3.6 Flash ↓2 33.8%
kirjandus
89 models we track have a score here.
- 1
Gemini 4 Argon ↑1 50%
- 2
Gemini 3.1 Pro ↓1 48.8%
- 3 GPT-5.6 Sol ↑3 47.5%
- 4 GPT-6 Astra ↑1 45%
- 5
Gemini 3.6 Flash ↑3 41.3%
- 6
Gemini 3.8 Flash ↓3 41.3%
- 7 Claude Fable 5.2 ↑2 40%
- 8
Gemini 3.7 Flash ↓4 37.5%
- 9
Gemini 3.5 Flash ↓2 36.3%
- 10 GPT-5.5 35%
kunst
89 models we track have a score here.
- 1
Gemini 3.8 Flash ↑2 60%
- 2
Gemini 3.1 Pro ↓1 56.3%
- 3 GPT-5.6 Sol ↑3 55%
- 4
Gemini 3.7 Flash 51.3%
- 5 GPT-6 Astra 48.8%
- 6
Gemini 4 Argon ↓4 48.8%
- 7
Gemini 3.6 Flash ↑1 46.3%
- 8
Gemini 3.5 Flash ↓1 45%
- 9 GPT-5.5 ↑1 42.5%
- 10 GPT-6 Sol ↑1 40%
muusika
89 models we track have a score here.
- 1
Gemini 4 Argon ↑1 58.8%
- 2
Gemini 3.1 Pro ↓1 57.5%
- 3
Gemini 3.8 Flash 53.8%
- 4
Gemini 3.5 Flash ↑3 52.5%
- 5
Gemini 3.7 Flash ↓1 52.5%
- 6
Gemini 3.6 Flash ↑2 46.3%
- 7 GPT-6 Astra ↓2 43.8%
- 8 GPT-5.6 Sol ↓2 41.3%
- 9 Claude Fable 5.2 40%
- 10 GPT-5.5 37.5%
eesti keel
89 models we track have a score here.
- 1
Gemini 3.1 Pro 41.3%
- 2 GPT-6 Astra ↑3 41.3%
- 3
Gemini 4 Argon ↓1 41.3%
- 4
Gemini 3.8 Flash ↓1 38.8%
- 5
Gemini 3.7 Flash ↓1 35%
- 6 Claude Fable 5.2 ↑3 35%
- 7 GPT-5.6 Sol ↓1 33.8%
- 8
Gemini 3.6 Flash 33.8%
- 9 Claude Fable 5.1 ↑5 33.8%
- 10
Gemini 3.5 Flash ↓3 31.3%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official EKI Mälumäng 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 EKI Mälumäng 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
10 of 11 checks pass, 1 warning. Look first at the Task access check. We don’t know whether the tasks are public. Every benchmark
Catalog record 1 warning 1 pass
- Warning Task access We don’t know whether the tasks are public.
- Pass Confidence Checked against a primary source.
Scores 5 pass
- Pass Independent runs Scores from the official leaderboard (93 entries).
- Pass Models scored 89 models we track, plus 4 other entries on its leaderboard.
- Pass Newest score The newest is from November 2026, for Claude Fable 5.2.
- Pass Frontier models 7 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Pass Headroom The best is 50.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on xn--mdupuu-pxaa.eki.ee: 89 rows for models we track and 4 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.