MIZAN: A Persian LLM Leaderboard
Models answer questions, complete sentences, follow instructions, and hold conversations in Persian. The leaderboard averages six task scores.
The organizers publish overall scores for 45 model entries, alongside the six scores used to calculate each average.
- Made by
- MCINext
- Released
- May 2025
- Kind
- Knowledge in many languages
- Level
- School
- Scored
- Checked automatically
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Subject
- Languages and literature
- Language
- Persian
- Interaction
- Multi-turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- o3 #84 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 20th, 2026
o3 leads with 0.75 among models released by September 2025 o3 leads with 0.75 among models released by September 2025
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 September 2025, 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 16 more
- 0.75 o3
- 0.73
Gemini 2.5 Pro
- 0.72 GPT-5 mini
- 0.71 Claude 3.7 Sonnet
- 0.70 GPT-4.1
- 0.70
Gemini 2.5 Flash
- 0.69
Gemini 2.0 Flash
- 0.69 GPT-4o
- 0.66
Gemini 2.0 Flash-Lite
- 0.66 GPT-5 nano
- 0.66 gpt-oss-120b
- 0.66 GPT-4.1 mini
- 0.65 deepseek-reasoner
- 0.65 deepseek-chat
- 0.62
Gemma 3 27B
- 0.62 GPT-4o mini
- 0.62
Qwen3-32B
- 0.62 gpt-oss-20b
- 0.61
Llama 3.3 70B Instruct
- 0.61
Cohere Command A
- 0.60
Gemma 3 12B
- 0.59
Qwen3-30B-A3B
- 0.59
Qwen3-14B
- 0.57
Llama 4 Scout
- 0.57
Command R+
- 0.56
Mistral Small 3.1
- 0.55 Claude 3.5 Haiku
- 0.55 GPT-4.1 nano
- 0.54
Gemma 3n E4B
- 0.53
Qwen3-8B
- 0.50
Gemma 3 4B
- 0.49
Aya Expanse 32B
- 0.49 deepseek-r1-0528-qwen3-8b
- 0.48
Command R (03-2024)
- 0.48
Qwen3-4B
- 0.42 yandexgpt-lite
- 0.33
Gemma 3 1B
- 0.30 Mistral-7B-Instruct-v0.3
- 0.28 Llama-3.2-3B-Instruct
- 0.20 Llama-3.2-1B-Instruct
- 0.17
Gemma 3 270M
- 1 o3 Thinking 0.75
- 2
Gemini 2.5 Pro Jun 2025, Thinking 0.73
- 3 GPT-5 mini Thinking 0.72
- 4 Claude 3.7 Sonnet Non-thinking 0.71
- 5 GPT-4.1 Non-thinking 0.70
- 6
Gemini 2.5 Flash Sep 2025, Thinking 0.70
- 7
Gemini 2.0 Flash Feb 2025, Non-thinking 0.69
- 8 GPT-4o Mar 2025, Non-thinking 0.69
- 9
Gemini 2.0 Flash-Lite Non-thinking 0.66
- 10 GPT-5 nano Thinking 0.66
- 11 gpt-oss-120b Thinking 0.66
- 12 GPT-4.1 mini Non-thinking 0.66
- 13 deepseek-reasoner Thinking 0.65
- 14 deepseek-chat Non-thinking 0.65
- 15
Gemma 3 27B Non-thinking 0.62
- 16 GPT-4o mini Non-thinking 0.62
- 17
Qwen3-32B Non-thinking 0.62
- 18 gpt-oss-20b Thinking 0.62
- 19
Llama 3.3 70B Instruct Non-thinking 0.61
- 20
Cohere Command A Non-thinking 0.61
- 21
Gemma 3 12B Non-thinking 0.60
- 22
Qwen3-30B-A3B Non-thinking 0.59
- 23
Qwen3-14B Non-thinking 0.59
- 24
Llama 4 Scout Non-thinking 0.57
- 25
Command R+ Non-thinking 0.57
- 26
Mistral Small 3.1 Non-thinking 0.56
- 27 Claude 3.5 Haiku Non-thinking 0.55
- 28 GPT-4.1 nano Non-thinking 0.55
- 29
Gemma 3n E4B Non-thinking 0.54
- 30
Qwen3-8B Non-thinking 0.53
- 31
Gemma 3 4B Non-thinking 0.50
- 32
Aya Expanse 32B Non-thinking 0.49
- 33 deepseek-r1-0528-qwen3-8b Thinking 0.49
- 34
Command R (03-2024) Non-thinking 0.48
- 35
Qwen3-4B Non-thinking 0.48
- 36 yandexgpt-lite Non-thinking 0.42
- 37
Gemma 3 1B Non-thinking 0.33
- 38 Mistral-7B-Instruct-v0.3 Non-thinking 0.30
- 39 Llama-3.2-3B-Instruct Non-thinking 0.28
- 40 Llama-3.2-1B-Instruct Non-thinking 0.20
- 41
Gemma 3 270M Non-thinking 0.17
Source: Official MIZAN: A Persian LLM Leaderboard leaderboard
- 0.75 o3
- 0.73
Gemini 2.5 Pro
- 0.72 GPT-5 mini
- 0.71 Claude 3.7 Sonnet
- 0.70 GPT-4.1
- 0.70
Gemini 2.5 Flash
- 0.69
Gemini 2.0 Flash
- 0.69 GPT-4o
- 0.66
Gemini 2.0 Flash-Lite
- 0.66 GPT-5 nano
- 0.66 gpt-oss-120b
- 0.66 GPT-4.1 mini
- 0.62
Gemma 3 27B
- 0.62 GPT-4o mini
- 0.62
Qwen3-32B
- 0.62 gpt-oss-20b
- 0.61
Llama 3.3 70B Instruct
- 0.61
Cohere Command A
- 0.60
Gemma 3 12B
- 0.59
Qwen3-30B-A3B
- 0.59
Qwen3-14B
- 0.57
Llama 4 Scout
- 0.57
Command R+
- 0.56
Mistral Small 3.1
- 0.55 Claude 3.5 Haiku
- 0.55 GPT-4.1 nano
- 0.54
Gemma 3n E4B
- 0.53
Qwen3-8B
- 0.50
Gemma 3 4B
- 0.49
Aya Expanse 32B
- 0.49 deepseek-r1-0528-qwen3-8b
- 0.48
Command R (03-2024)
- 0.48
Qwen3-4B
- 0.33
Gemma 3 1B
- 0.17
Gemma 3 270M
- 1 o3 Thinking 0.75
- 2
Gemini 2.5 Pro Jun 2025, Thinking 0.73
- 3 GPT-5 mini Thinking 0.72
- 4 Claude 3.7 Sonnet Non-thinking 0.71
- 5 GPT-4.1 Non-thinking 0.70
- 6
Gemini 2.5 Flash Sep 2025, Thinking 0.70
- 7
Gemini 2.0 Flash Feb 2025, Non-thinking 0.69
- 8 GPT-4o Mar 2025, Non-thinking 0.69
- 9
Gemini 2.0 Flash-Lite Non-thinking 0.66
- 10 GPT-5 nano Thinking 0.66
- 11 gpt-oss-120b Thinking 0.66
- 12 GPT-4.1 mini Non-thinking 0.66
- 13
Gemma 3 27B Non-thinking 0.62
- 14 GPT-4o mini Non-thinking 0.62
- 15
Qwen3-32B Non-thinking 0.62
- 16 gpt-oss-20b Thinking 0.62
- 17
Llama 3.3 70B Instruct Non-thinking 0.61
- 18
Cohere Command A Non-thinking 0.61
- 19
Gemma 3 12B Non-thinking 0.60
- 20
Qwen3-30B-A3B Non-thinking 0.59
- 21
Qwen3-14B Non-thinking 0.59
- 22
Llama 4 Scout Non-thinking 0.57
- 23
Command R+ Non-thinking 0.57
- 24
Mistral Small 3.1 Non-thinking 0.56
- 25 Claude 3.5 Haiku Non-thinking 0.55
- 26 GPT-4.1 nano Non-thinking 0.55
- 27
Gemma 3n E4B Non-thinking 0.54
- 28
Qwen3-8B Non-thinking 0.53
- 29
Gemma 3 4B Non-thinking 0.50
- 30
Aya Expanse 32B Non-thinking 0.49
- 31 deepseek-r1-0528-qwen3-8b Thinking 0.49
- 32
Command R (03-2024) Non-thinking 0.48
- 33
Qwen3-4B Non-thinking 0.48
- 34
Gemma 3 1B Non-thinking 0.33
- 35
Gemma 3 270M Non-thinking 0.17
Source: Official MIZAN: A Persian LLM Leaderboard leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o3 | 0.75 | Thinking | Apr 2025 | Official leaderboard |
| 2 | | 0.73 | Thinking | Jun 2025 | Official leaderboard |
| 3 | GPT-5 mini | 0.72 | Thinking | Aug 2025 | Official leaderboard |
| 4 | Claude 3.7 Sonnet | 0.71 | Non-thinking | Feb 2025 | Official leaderboard |
| 5 | GPT-4.1 | 0.70 | Non-thinking | Apr 2025 | Official leaderboard |
| 6 | | 0.70 | Thinking | Sep 2025 | Official leaderboard |
| 7 | | 0.69 | Non-thinking | Feb 2025 | Official leaderboard |
| 8 | GPT-4o Mar 2025 | 0.69 | Non-thinking | Mar 2025 | Official leaderboard |
| 9 | | 0.66 | Non-thinking | Feb 2025 | Official leaderboard |
| 10 | GPT-5 nano | 0.66 | Thinking | Aug 2025 | Official leaderboard |
| 11 | gpt-oss-120b | 0.66 | Thinking | Aug 2025 | Official leaderboard |
| 12 | GPT-4.1 mini | 0.66 | Non-thinking | Apr 2025 | Official leaderboard |
| 13 | deepseek-reasoner open weights, 671B | 0.65 | Thinking | Official leaderboard | |
| 14 | deepseek-chat open weights, 671B | 0.65 | Non-thinking | Official leaderboard | |
| 15 | | 0.62 | Non-thinking | Mar 2025 | Official leaderboard |
| 16 | GPT-4o mini | 0.62 | Non-thinking | Jul 2024 | Official leaderboard |
| 17 | | 0.62 | Non-thinking | Apr 2025 | Official leaderboard |
| 18 | gpt-oss-20b | 0.62 | Thinking | Aug 2025 | Official leaderboard |
| 19 | | 0.61 | Non-thinking | Dec 2024 | Official leaderboard |
| 20 | | 0.61 | Non-thinking | Mar 2025 | Official leaderboard |
| 21 | | 0.60 | Non-thinking | Mar 2025 | Official leaderboard |
| 22 | | 0.59 | Non-thinking | Apr 2025 | Official leaderboard |
| 23 | | 0.59 | Non-thinking | Apr 2025 | Official leaderboard |
| 24 | | 0.57 | Non-thinking | Apr 2025 | Official leaderboard |
| 25 | | 0.57 | Non-thinking | Aug 2024 | Official leaderboard |
| 26 | | 0.56 | Non-thinking | Mar 2025 | Official leaderboard |
| 27 | Claude 3.5 Haiku | 0.55 | Non-thinking | Oct 2024 | Official leaderboard |
| 28 | GPT-4.1 nano | 0.55 | Non-thinking | Apr 2025 | Official leaderboard |
| 29 | | 0.54 | Non-thinking | Jun 2025 | Official leaderboard |
| 30 | | 0.53 | Non-thinking | Apr 2025 | Official leaderboard |
| 31 | | 0.50 | Non-thinking | Mar 2025 | Official leaderboard |
| 32 | | 0.49 | Non-thinking | Oct 2024 | Official leaderboard |
| 33 | deepseek-r1-0528-qwen3-8b | 0.49 | Thinking | May 2025 | Official leaderboard |
| 34 | | 0.48 | Non-thinking | Mar 2024 | Official leaderboard |
| 35 | | 0.48 | Non-thinking | Apr 2025 | Official leaderboard |
| 36 | yandexgpt-lite open weights, 8B | 0.42 | Non-thinking | Official leaderboard | |
| 37 | | 0.33 | Non-thinking | Mar 2025 | Official leaderboard |
| 38 | Mistral-7B-Instruct-v0.3 open weights, 7.3B | 0.30 | Non-thinking | Official leaderboard | |
| 39 | Llama-3.2-3B-Instruct open weights, 3.2B | 0.28 | Non-thinking | Official leaderboard | |
| 40 | Llama-3.2-1B-Instruct open weights, 1.2B | 0.20 | Non-thinking | Official leaderboard | |
| 41 | | 0.17 | Non-thinking | Aug 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | o3 | 0.75 | Thinking | Apr 2025 | Official leaderboard |
| 2 | | 0.73 | Thinking | Jun 2025 | Official leaderboard |
| 3 | GPT-5 mini | 0.72 | Thinking | Aug 2025 | Official leaderboard |
| 4 | Claude 3.7 Sonnet | 0.71 | Non-thinking | Feb 2025 | Official leaderboard |
| 5 | GPT-4.1 | 0.70 | Non-thinking | Apr 2025 | Official leaderboard |
| 6 | | 0.70 | Thinking | Sep 2025 | Official leaderboard |
| 7 | | 0.69 | Non-thinking | Feb 2025 | Official leaderboard |
| 8 | GPT-4o Mar 2025 | 0.69 | Non-thinking | Mar 2025 | Official leaderboard |
| 9 | | 0.66 | Non-thinking | Feb 2025 | Official leaderboard |
| 10 | GPT-5 nano | 0.66 | Thinking | Aug 2025 | Official leaderboard |
| 11 | gpt-oss-120b | 0.66 | Thinking | Aug 2025 | Official leaderboard |
| 12 | GPT-4.1 mini | 0.66 | Non-thinking | Apr 2025 | Official leaderboard |
| 13 | | 0.62 | Non-thinking | Mar 2025 | Official leaderboard |
| 14 | GPT-4o mini | 0.62 | Non-thinking | Jul 2024 | Official leaderboard |
| 15 | | 0.62 | Non-thinking | Apr 2025 | Official leaderboard |
| 16 | gpt-oss-20b | 0.62 | Thinking | Aug 2025 | Official leaderboard |
| 17 | | 0.61 | Non-thinking | Dec 2024 | Official leaderboard |
| 18 | | 0.61 | Non-thinking | Mar 2025 | Official leaderboard |
| 19 | | 0.60 | Non-thinking | Mar 2025 | Official leaderboard |
| 20 | | 0.59 | Non-thinking | Apr 2025 | Official leaderboard |
| 21 | | 0.59 | Non-thinking | Apr 2025 | Official leaderboard |
| 22 | | 0.57 | Non-thinking | Apr 2025 | Official leaderboard |
| 23 | | 0.57 | Non-thinking | Aug 2024 | Official leaderboard |
| 24 | | 0.56 | Non-thinking | Mar 2025 | Official leaderboard |
| 25 | Claude 3.5 Haiku | 0.55 | Non-thinking | Oct 2024 | Official leaderboard |
| 26 | GPT-4.1 nano | 0.55 | Non-thinking | Apr 2025 | Official leaderboard |
| 27 | | 0.54 | Non-thinking | Jun 2025 | Official leaderboard |
| 28 | | 0.53 | Non-thinking | Apr 2025 | Official leaderboard |
| 29 | | 0.50 | Non-thinking | Mar 2025 | Official leaderboard |
| 30 | | 0.49 | Non-thinking | Oct 2024 | Official leaderboard |
| 31 | deepseek-r1-0528-qwen3-8b | 0.49 | Thinking | May 2025 | Official leaderboard |
| 32 | | 0.48 | Non-thinking | Mar 2024 | Official leaderboard |
| 33 | | 0.48 | Non-thinking | Apr 2025 | Official leaderboard |
| 34 | | 0.33 | Non-thinking | Mar 2025 | Official leaderboard |
| 35 | | 0.17 | Non-thinking | Aug 2025 | Official leaderboard |
Rankings by part
We read 6 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Persian IFEval, Persian MT-Bench and PerMMLU. o3 leads 3 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.
Persian IFEval
35 models we track have a score here.
- 1 o3 0.93
- 2 GPT-5 mini ↑1 0.91
- 3 GPT-5 nano ↑7 0.90
- 4
Gemini 2.5 Pro Jun 2025 ↓2 0.89
- 5 gpt-oss-120b ↑6 0.89
- 6 Claude 3.7 Sonnet ↓2 0.88
- 7
Gemini 2.5 Flash Sep 2025 ↓1 0.88
- 8 GPT-4.1 ↓3 0.86
- 9 gpt-oss-20b ↑7 0.86
- 10
Gemini 2.0 Flash Feb 2025 ↓3 0.85
Persian MT-Bench
35 models we track have a score here.
- 1 o3 0.91
- 2
Gemini 2.5 Pro Jun 2025 0.91
- 3
Gemini 2.5 Flash Sep 2025 ↑3 0.88
- 4 GPT-4.1 ↑1 0.87
- 5 Claude 3.7 Sonnet ↓1 0.87
- 6 GPT-5 mini ↓3 0.87
- 7 gpt-oss-120b ↑4 0.84
- 8 GPT-4.1 mini ↑4 0.84
- 9
Gemini 2.0 Flash Feb 2025 ↓2 0.84
- 10 GPT-4o Mar 2025 ↓2 0.84
PerMMLU
35 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑1 0.84
- 2 o3 ↓1 0.82
- 3 GPT-5 mini 0.76
- 4
Gemini 2.5 Flash Sep 2025 ↑2 0.73
- 5 Claude 3.7 Sonnet ↓1 0.72
- 6 GPT-4.1 ↓1 0.70
- 7
Gemini 2.0 Flash Feb 2025 0.70
- 8 GPT-4o Mar 2025 0.69
- 9 GPT-5 nano ↑1 0.69
- 10 gpt-oss-120b ↑1 0.68
PerCoR
35 models we track have a score here.
- 1
Gemini 2.5 Pro Jun 2025 ↑1 0.94
- 2 o3 ↓1 0.92
- 3 Claude 3.7 Sonnet ↑1 0.91
- 4 GPT-4.1 ↑1 0.88
- 5
Gemini 2.5 Flash Sep 2025 ↑1 0.87
- 6 GPT-4o Mar 2025 ↑2 0.87
- 7 GPT-5 mini ↓4 0.87
- 8
Gemini 2.0 Flash Feb 2025 ↓1 0.86
- 9
Gemini 2.0 Flash-Lite 0.81
- 10
Cohere Command A ↑8 0.80
Persian NLU
35 models we track have a score here.
- 1 o3 0.72
- 2 GPT-5 mini ↑1 0.72
- 3 GPT-4o Mar 2025 ↑5 0.71
- 4 Claude 3.7 Sonnet 0.71
- 5
Gemini 2.0 Flash Feb 2025 ↑2 0.71
- 6
Gemini 2.5 Pro Jun 2025 ↓4 0.70
- 7
Gemma 3 12B ↑12 0.70
- 8
Gemini 2.5 Flash Sep 2025 ↓2 0.69
- 9
Gemini 2.0 Flash-Lite 0.69
- 10
Gemma 3 27B ↑3 0.69
Persian NLG
35 models we track have a score here.
- 1
Llama 3.3 70B Instruct ↑16 0.20
- 2 GPT-4.1 ↑3 0.19
- 3 GPT-4.1 mini ↑9 0.19
- 4 GPT-4o Mar 2025 ↑4 0.19
- 5
Command R+ ↑18 0.19
- 6 GPT-5 mini ↓3 0.18
- 7 GPT-4o mini ↑7 0.18
- 8
Gemini 2.0 Flash Feb 2025 ↓1 0.18
- 9 Claude 3.7 Sonnet ↓5 0.18
- 10 o3 ↓9 0.18
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 MIZAN: A Persian LLM Leaderboard leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| o3 | Thinking | 0.75 | |||
| Thinking | 0.73 | ||||
| GPT-5 mini | Thinking | 0.72 | |||
| Claude 3.7 Sonnet | Non-thinking | 0.71 | |||
| GPT-4.1 | Non-thinking | 0.70 | |||
| Thinking | 0.70 | ||||
| Non-thinking | 0.69 | ||||
| GPT-4o Mar 2025 | Non-thinking | 0.69 | |||
| Non-thinking | 0.66 | ||||
| GPT-5 nano | Thinking | 0.66 | |||
| gpt-oss-120b | Thinking | 0.66 | |||
| GPT-5 mini | minimal reasoning | 0.66 | |||
| GPT-4.1 mini | Non-thinking | 0.66 | |||
| Non-thinking | 0.62 | ||||
| GPT-4o mini | Non-thinking | 0.62 | |||
| gpt-oss-120b | low reasoning | 0.62 | |||
| Non-thinking | 0.62 | ||||
| gpt-oss-20b | Thinking | 0.62 | |||
| Non-thinking | 0.61 | ||||
| Non-thinking | 0.61 | ||||
| Non-thinking | 0.60 | ||||
| Non-thinking | 0.59 | ||||
| Non-thinking | 0.59 | ||||
| gpt-oss-20b | low reasoning | 0.58 | |||
| Non-thinking | 0.57 | ||||
| Non-thinking | 0.57 | ||||
| Non-thinking | 0.56 | ||||
| Claude 3.5 Haiku | Non-thinking | 0.55 | |||
| GPT-4.1 nano | Non-thinking | 0.55 | |||
| Non-thinking | 0.54 | ||||
| Non-thinking | 0.53 | ||||
| GPT-5 nano | minimal reasoning | 0.52 | |||
| Non-thinking | 0.50 | ||||
| Non-thinking | 0.49 | ||||
| deepseek-r1-0528-qwen3-8b | Thinking | 0.49 | |||
| Non-thinking | 0.48 | ||||
| Non-thinking | 0.48 | ||||
| Non-thinking | 0.33 | ||||
| Non-thinking | 0.17 |
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 MIZAN: A Persian LLM Leaderboard leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| o3 | Thinking | 0.75 | |||
| Thinking | 0.73 | ||||
| GPT-5 mini | Thinking | 0.72 | |||
| Claude 3.7 Sonnet | Non-thinking | 0.71 | |||
| GPT-4.1 | Non-thinking | 0.70 | |||
| Thinking | 0.70 | ||||
| Non-thinking | 0.69 | ||||
| GPT-4o Mar 2025 | Non-thinking | 0.69 | |||
| Non-thinking | 0.66 | ||||
| GPT-5 nano | Thinking | 0.66 | |||
| gpt-oss-120b | Thinking | 0.66 | |||
| GPT-5 mini | minimal reasoning | 0.66 | |||
| GPT-4.1 mini | Non-thinking | 0.66 | |||
| Non-thinking | 0.62 | ||||
| GPT-4o mini | Non-thinking | 0.62 | |||
| gpt-oss-120b | low reasoning | 0.62 | |||
| Non-thinking | 0.62 | ||||
| gpt-oss-20b | Thinking | 0.62 | |||
| Non-thinking | 0.61 | ||||
| Non-thinking | 0.61 | ||||
| Non-thinking | 0.60 | ||||
| Non-thinking | 0.59 | ||||
| Non-thinking | 0.59 | ||||
| gpt-oss-20b | low reasoning | 0.58 | |||
| Non-thinking | 0.57 | ||||
| Non-thinking | 0.57 | ||||
| Non-thinking | 0.56 | ||||
| Claude 3.5 Haiku | Non-thinking | 0.55 | |||
| GPT-4.1 nano | Non-thinking | 0.55 | |||
| Non-thinking | 0.54 | ||||
| Non-thinking | 0.53 | ||||
| GPT-5 nano | minimal reasoning | 0.52 | |||
| Non-thinking | 0.50 | ||||
| Non-thinking | 0.49 | ||||
| deepseek-r1-0528-qwen3-8b | Thinking | 0.49 | |||
| Non-thinking | 0.48 | ||||
| Non-thinking | 0.48 | ||||
| Non-thinking | 0.33 | ||||
| Non-thinking | 0.17 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official MIZAN: A Persian LLM Leaderboard 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 MIZAN: A Persian LLM Leaderboard 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (41 entries).
- Pass Models scored 35 models we track, plus 6 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is o3 (#84).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on mcinext-mizan-llm-leaderboard.hf.space: 39 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.