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

BoolQ

21 models

Top 5 Models Performance

Qwen: qwen-14b ######################################## 86.2
Arcee AI: trinity-nano-base ####################################### 84.3
Google: Gemma 3 27B Pretrained ###################################### 82.4
Google: gemma-3-12b-pt ##################################### 78.8
Qwen: qwen-7b ################################### 76.4
– 970 – 1.1T
– 2019 – 2026
Rank Model Score
🇨🇳 1 Qwen: qwen-14b通义千问 86.2
🇺🇸 2 Arcee AI: trinity-nano-base 84.3
🇺🇸 3 Google: Gemma 3 27B Pretrained 82.4
🇺🇸 4 Google: gemma-3-12b-pt 78.8
🇨🇳 5 Qwen: qwen-7b通义千问 76.4
🇺🇸 6 Google: gemma-3-4b-pt 72.3
🇺🇸 7 Apple: openelm-1_1b-instruct 70
🇺🇸 8 Apple: openelm-3b-instruct 68.17
🇨🇳 9 Qwen: qwen-1.8b通义千问 68
🇺🇸 10 Apple: openelm-3b 67.4
🇺🇸 11 Apple: openelm-1_1b 63.58
🇺🇸 12 Google: gemma-3-1b-pt 63.2
🇺🇸 13 AMD: amd-olmo-1b 60.58
🇺🇸 14 Apple: openelm-450m-instruct 60.37
🇺🇸 15 Apple: openelm-450m 55.78
🇺🇸 16 Apple: openelm-270m 53.98
❓ 17 SupraLabs: Supra-50M BASE 53.03
🇺🇸 18 Apple: openelm-270m-instruct 48.56
❓ 19 SupraLabs: Supra-50M-Reasoning 46.06
❓ 20 SupraLabs: Supra-50M Instruct 42.05
❓ 21 SupraLabs: Supra Mini v6 1M 38.87