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

MMBench-Dev

4 models

Top 5 Models Performance

Qwen: qwen3-vl-32b-instruct ######################################## 87.8
NVIDIA Corporation: cosmos3-super ######################################## 87.4
Google: Gemma 4 31B Instruct ####################################### 86.7
NVIDIA Corporation: cosmos-reason2-32b ####################################### 86.3
970 – 1.1T
2019 – 2026
Rank Model Score
🇨🇳 1 Qwen: qwen3-vl-32b-instruct通义千问 87.8
🇺🇸 2 NVIDIA Corporation: cosmos3-super 87.4
🇺🇸 3 Google: Gemma 4 31B Instruct 86.7
🇺🇸 4 NVIDIA Corporation: cosmos-reason2-32b 86.3