AraGen v3
Arabic generative-task benchmark for chat and instruct models, evaluated with the 3C3H rubric over culturally relevant Arabic QA and safety tasks.
69rows
3c3h_scoreprimary metric
2026-05-06sampled
Metadata
Metrics
3C3H Score, Correctness, Completeness, Conciseness, Helpfulness, Honesty, Harmlessness, Question Answering (QA), Safety
| Rank | Subject | 3C3H Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | o1-2024-12-17 | 84.29 |  o1 openai-o1 | Imported | 2026-05-06 |
| 2 | gpt-5-2025-08-07 | 84.25 | GPT-5 openai-gpt-5 | Imported | 2026-05-06 |
| 3 | o3-2025-04-16 | 82.19 | o3 openai-o3 | Imported | 2026-05-06 |
| 4 | claude-opus-4-20250514 | 80.96 |  Claude Opus 4 anthropic-claude-opus-4 | Imported | 2026-05-06 |
| 5 | claude-opus-4-5-20251101 | 80.29 | Claude Opus 4.5 anthropic-claude-opus-4.5 | Imported | 2026-05-06 |
| 6 | claude-sonnet-4-5-20250929 | 78.17 | Claude Sonnet 4.5 anthropic-claude-sonnet-4.5 | Imported | 2026-05-06 |
| 7 | claude-3-7-sonnet-20250219 | 78.16 | Claude 3.7 Sonnet anthropic-claude-3.7-sonnet | Imported | 2026-05-06 |
| 8 | claude-sonnet-4-20250514 | 75.58 | Claude Sonnet 4 anthropic-claude-sonnet-4 | Imported | 2026-05-06 |
| 9 | gpt-4.1 | 74.54 | GPT-4.1 openai-gpt-4.1 | Imported | 2026-05-06 |
| 10 | google/gemma-4-31B-it | 72.71 |  Gemma 4 31B google-gemma-4-31b-it | Imported | 2026-05-06 |
| 11 | o4-mini-2025-04-16 | 70.60 | o4 Mini openai-o4-mini | Imported | 2026-05-06 |
| 12 | o1-mini-2024-09-12 | 70.46 | — | Imported | 2026-05-06 |
| 13 | gemini-2.5-pro-preview-05-06 | 68.37 | Gemini 2.5 Pro Preview 05-06 google-gemini-2.5-pro-preview-05-06 | Imported | 2026-05-06 |
| 14 | google/gemma-4-26B-A4B-it | 67.35 | Gemma 4 26B A4B google-gemma-4-26b-a4b-it | Imported | 2026-05-06 |
| 15 | claude-haiku-4-5-20251001 | 65.80 | Claude Haiku 4.5 anthropic-claude-haiku-4.5 | Imported | 2026-05-06 |
| 16 | gemini-3-pro-preview | 64.15 | Gemini 3 google-gemini-3 | Imported | 2026-05-06 |
| 17 | o3-mini-2025-01-31 | 59.81 | o3-mini openai-o3-mini | Imported | 2026-05-06 |
| 18 | inceptionai/Jais-2-70B-Chat | 52.39 | — | Imported | 2026-05-06 |
| 19 | meta-llama/Llama-3.3-70B-Instruct | 52.12 |  Llama 3.3 70B Instruct meta-llama-llama-3.3-70b-instruct | Imported | 2026-05-06 |
| 20 | mistralai/Mistral-Large-Instruct-2411 | 52.02 | — | Imported | 2026-05-06 |
| 21 | MaziyarPanahi/calme-2.1-qwen2.5-72b | 50.81 | — | Imported | 2026-05-06 |
| 22 | gpt-4o-mini-2024-07-18 | 50.74 | GPT-4o-mini (2024-07-18) openai-gpt-4o-mini-2024-07-18 | Imported | 2026-05-06 |
| 23 | meta-llama/Llama-3.2-90B-Vision-Instruct | 50.51 | — | Imported | 2026-05-06 |
| 24 | MaziyarPanahi/calme-2.2-qwen2.5-72b | 50.31 | — | Imported | 2026-05-06 |
| 25 | meta-llama/Llama-3.1-70B-Instruct | 50 | Llama 3.1 70B Instruct meta-llama-llama-3.1-70b-instruct | Imported | 2026-05-06 |
| 26 | Qwen/Qwen2.5-72B-Instruct | 48.92 |  Qwen2.5 72B Instruct qwen-qwen-2.5-72b-instruct | Imported | 2026-05-06 |
| 27 | zai-org/GLM-5 | 46.01 | GLM 5 z-ai-glm-5 | Imported | 2026-05-06 |
| 28 | tiiuae/Falcon-H1-34B-Instruct | 45.74 | — | Imported | 2026-05-06 |
| 29 | JasperV13/Yehia-7B-Reasoning-preview | 45.25 | — | Imported | 2026-05-06 |
| 30 | JasperV13/Yehia-7B-Reasoning-preview | 45 | — | Imported | 2026-05-06 |
| 31 | openai/gpt-oss-120b | 43.23 | gpt-oss-120b openai-gpt-oss-120b | Imported | 2026-05-06 |
| 32 | mistralai/Mistral-Small-24B-Instruct-2501 | 39.84 |  Mistral: Mistral Small 3 mistralai-mistral-small-24b-instruct-2501 | Imported | 2026-05-06 |
| 33 | Qwen/Qwen2.5-14B-Instruct | 36.90 | — | Imported | 2026-05-06 |
| 34 | Qwen/Qwen3-32B | 35.18 | Qwen3 32B qwen-qwen3-32b | Imported | 2026-05-06 |
| 35 | FreedomIntelligence/AceGPT-v2-8B-Chat | 35.03 | — | Imported | 2026-05-06 |
| 36 | inceptionai/Jais-2-8B-Chat | 33.95 | — | Imported | 2026-05-06 |
| 37 | mistralai/Mistral-Small-4-119B-2603 | 33.85 | — | Imported | 2026-05-06 |
| 38 | inceptionai/jais-family-30b-16k-chat | 32.33 | — | Imported | 2026-05-06 |
| 39 | mistralai/Magistral-Small-2509 | 32.31 | — | Imported | 2026-05-06 |
| 40 | inceptionai/jais-family-30b-8k-chat | 30.77 | — | Imported | 2026-05-06 |
| 41 | openai/gpt-oss-20b | 30.61 | gpt-oss-20b openai-gpt-oss-20b | Imported | 2026-05-06 |
| 42 | microsoft/phi-4 | 29.98 |  Phi 4 microsoft-phi-4 | Imported | 2026-05-06 |
| 43 | Qwen/Qwen3-14B | 29.74 | Qwen3 14B qwen-qwen3-14b | Imported | 2026-05-06 |
| 44 | CohereForAI/c4ai-command-r7b-arabic-02-2025 | 27.86 | — | Imported | 2026-05-06 |
| 45 | Qwen/Qwen3-8B | 26.55 | Qwen3 8B qwen-qwen3-8b | Imported | 2026-05-06 |
| 46 | Qwen/Qwen2.5-7B-Instruct | 26.25 | Qwen2.5 7B Instruct qwen-qwen-2.5-7b-instruct | Imported | 2026-05-06 |
| 47 | meta-llama/Meta-Llama-3-70B-Instruct | 26.14 | Llama 3 70B Instruct meta-llama-llama-3-70b-instruct | Imported | 2026-05-06 |
| 48 | meta-llama/Llama-3.1-8B-Instruct | 24.94 | Llama 3.1 8B Instruct meta-llama-llama-3.1-8b-instruct | Imported | 2026-05-06 |
| 49 | meta-llama/Llama-3.2-11B-Vision-Instruct | 24.42 | Llama 3.2 11B Vision Instruct meta-llama-llama-3.2-11b-vision-instruct | Imported | 2026-05-06 |
| 50 | tiiuae/Falcon-H1-7B-Instruct | 24.40 | — | Imported | 2026-05-06 |
| 51 | inceptionai/jais-family-13b-chat | 24.14 | — | Imported | 2026-05-06 |
| 52 | inceptionai/jais-family-6p7b-chat | 21.29 | — | Imported | 2026-05-06 |
| 53 | mistralai/Ministral-8B-Instruct-2410 | 17.61 | — | Imported | 2026-05-06 |
| 54 | HuggingFaceTB/SmolLM3-3B | 16.24 | — | Imported | 2026-05-06 |
| 55 | QCRI/Fanar-1-9B-Instruct | 16.18 | — | Imported | 2026-05-06 |
| 56 | FreedomIntelligence/AceGPT-13B-chat | 15.91 | — | Imported | 2026-05-06 |
| 57 | tiiuae/Falcon-H1-3B-Instruct | 15.05 | — | Imported | 2026-05-06 |
| 58 | meta-llama/Llama-3.2-3B-Instruct | 14.99 | Llama 3.2 3B Instruct meta-llama-llama-3.2-3b-instruct | Imported | 2026-05-06 |
| 59 | Qwen/Qwen2.5-1.5B-Instruct | 13.22 | — | Imported | 2026-05-06 |
| 60 | FreedomIntelligence/AceGPT-7B-chat | 12.45 | — | Imported | 2026-05-06 |
| 61 | meta-llama/Llama-3.2-1B-Instruct | 10.54 | Llama 3.2 1B Instruct meta-llama-llama-3.2-1b-instruct | Imported | 2026-05-06 |
| 62 | meta-llama/Meta-Llama-3-8B-Instruct | 9.21 | Llama 3 8B Instruct meta-llama-llama-3-8b-instruct | Imported | 2026-05-06 |
| 63 | silma-ai/SILMA-9B-Instruct-v1.0 | 6.70 | — | Imported | 2026-05-06 |
| 64 | Qwen/Qwen2.5-0.5B-Instruct | 5.21 | — | Imported | 2026-05-06 |
| 65 | mistralai/Mistral-7B-Instruct-v0.3 | 5.08 | — | Imported | 2026-05-06 |
| 66 | tiiuae/Falcon-H1-1.5B-Instruct | 4.58 | — | Imported | 2026-05-06 |
| 67 | Qwen/Qwen3-0.6B | 1.57 | — | Imported | 2026-05-06 |
| 68 | mistralai/Mistral-7B-Instruct-v0.2 | 0.48 | — | Imported | 2026-05-06 |
| 69 | Qwen/Qwen3.5-397B-A17B-FP8 | 0 | — | Imported | 2026-05-06 |
No matching rows.