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

swebenchlite

7 models

Top 5 Models Performance

Qwen: qwen3-coder-30b-a3b-instruct ######################################## 49.7
DeepSeek: deepseek-v3 ############################## 36.7
DeepSeek: deepseek-v3.2 ######################### 30.7
Anthropic: claude-3-opus ### 4.33
Anthropic: claude-2.0 ## 3
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
🇨🇳 1 Qwen: qwen3-coder-30b-a3b-instruct通义千问 49.7
🇨🇳 2 DeepSeek: deepseek-v3深度求索 36.7
🇨🇳 3 DeepSeek: deepseek-v3.2深度求索 30.7
🇺🇸 4 Anthropic: claude-3-opus 4.33
🇺🇸 5 Anthropic: claude-2.0 3
🇺🇸 6 OpenAI: gpt-4-turbo 2.67
🇺🇸 7 OpenAI: GPT-3.5 0.33