Note: Overall leaderboard rankings may not reflect true model quality — individual benchmarks give a clearer picture. ARC-Challenge MMLU GPQA GSM8K Artificial Analysis Intelligence Index v4.1
← Back to leaderboard

MBPP

30 models

Top 5 Models Performance

webai-official: twil-8b ######################################## 93.7
Qwen: Qwen3 4B ####################################### 92.3
Tencent: youtu-llm-2b #################################### 85
OpenAI: gpt-4o ################################### 82.2
Qwen: qwen3-1.7b ################################## 80.5
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
❓ 1 webai-official: twil-8b 93.7
🇨🇳 2 Qwen: Qwen3 4B通义千问 92.3
🇨🇳 3 Tencent: youtu-llm-2b腾讯控股有限公司 85
🇺🇸 4 OpenAI: gpt-4o 82.2
🇨🇳 5 Qwen: qwen3-1.7b通义千问 80.5
🇺🇸 6 Inception: mercury 77.1
🇺🇸 7 Apple: diffucoder-7b-instruct 75.1
🇺🇸 8 Apple: diffucoder-7b-base 74.2
🇦🇪 9 Technology Innovation Institute: falcon-h1-1.5b-deep-base 70.9
🇷🇺 10 Sber: gigachat3.5-432b-a28b-baseСбер 70.4
🇦🇪 11 Technology Innovation Institute: falcon-h1-1.5b-deep-instruct 68.25
🇷🇺 12 Yandex: gpt-5-lite-pretrainЯндекс 68.2
🇺🇸 13 Meta Llama: Llama 4 Scout Instruct 67.8
🇺🇸 14 Hugging Face Smol Models Research: smollm3-3b 66.7
🇺🇸 15 Google: Gemma 3 27B Pretrained 65.6
🇦🇪 16 Technology Innovation Institute: falcon-h1-1.5b-base 65.08
🇦🇪 17 Technology Innovation Institute: falcon-h1-1.5b-instruct 64.81
🇨🇳 18 Moonshot AI: Moonlight Instruct月之暗面 63.8
🇨🇳 19 OpenBMB: bitcpm4-1b 61.48
🇺🇸 20 Google: gemma-3-12b-pt 60.4
🇨🇳 21 Qwen: qwen3-1.7b-base通义千问 55.4
🇨🇳 22 DeepSeek: deepseek-r1-distill-qwen-1.5b深度求索 51.5
🇺🇸 23 Google: gemma-3-4b-pt 46
🇨🇳 24 Qwen: qwen2.5-1.5b通义千问 43.6
🇨🇳 25 Qwen: qwen-14b通义千问 40.8
🇨🇳 26 Qwen: qwen3-0.6b-base通义千问 36.6
🇨🇳 27 Qwen: qwen-7b通义千问 31.6
🇨🇳 28 Qwen: qwen2.5-0.5b通义千问 29.8
🇨🇳 29 Qwen: qwen-1.8b通义千问 14.8
🇺🇸 30 Google: gemma-3-1b-pt 9.2