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

MT-Bench

4 models

Top 5 Models Performance

DeepSeek: deepseek-v2.5 ######################################## 90.2
Hugging Face Smol Models Research: smollm2-135m-instruct ######### 19.8
Technology Innovation Institute: falcon-h1-1.5b-deep-instruct #### 8.53
Technology Innovation Institute: falcon-h1-1.5b-instruct #### 8.46
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
🇨🇳 1 DeepSeek: deepseek-v2.5深度求索 90.2
🇺🇸 2 Hugging Face Smol Models Research: smollm2-135m-instruct 19.8
🇦🇪 3 Technology Innovation Institute: falcon-h1-1.5b-deep-instruct 8.53
🇦🇪 4 Technology Innovation Institute: falcon-h1-1.5b-instruct 8.46