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 v4.0
← Back to leaderboard

RefCOCO

7 models

Top 5 Models Performance

Intern Language Models: intern-s1-pro ######################################## 91.9
Moondream: Moondream 3 (Preview) ######################################## 91.1
Qwen: qwen3-vl-32b-instruct ####################################### 90.6
NVIDIA Corporation: cosmos3-super ####################################### 89.5
OpenBMB: minicpm-v-4.6 ###################################### 86.7
970 – 1.1T
2019 – 2026
Rank Model Score
🇨🇳 1 Intern Language Models: intern-s1-pro 91.9
2 Moondream: Moondream 3 (Preview) 91.1
🇨🇳 3 Qwen: qwen3-vl-32b-instruct通义千问 90.6
🇺🇸 4 NVIDIA Corporation: cosmos3-super 89.5
🇨🇳 5 OpenBMB: minicpm-v-4.6 86.7
🇺🇸 6 Google: Gemma 4 31B Instruct 81.8
🇺🇸 7 NVIDIA Corporation: cosmos-reason2-32b 70.7