自定义评测选择
+
+
| 模型名称 | 参数数量 | 开源情况 | 发布机构 | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Phi-4-mini-instruct (3.8B) | 52.80 | 67.30 | 88.60 | 64.00 | 36.00 | 74.40 | 71.80 | 0.00 | 38.0 |
|
|
| Qwen2.5-3B | 34.60 | 65.60 | 79.10 | 42.60 | 24.30 | 42.10 | 0.00 | 0.00 | 30.0 |
|
|
| Llama-3.2-3B | 25.00 | 54.75 | 34.00 | 8.50 | 26.60 | 28.00 | 0.00 | 0.00 | 32.0 |
|
|
| Phi-4-instruct (reasoning-trained) | 0.00 | 0.00 | 0.00 | 0.00 | 49.00 | 0.00 | 90.40 | 0.00 | 38.0 |
|
MMLU Pro
52.80
MMLU
67.30
GSM8K
88.60
MATH
64.00
GPQA Diamond
36.00
HumanEval
74.40
MATH-500
71.80
LiveCodeBench
0.00
MMLU Pro
34.60
MMLU
65.60
GSM8K
79.10
MATH
42.60
GPQA Diamond
24.30
HumanEval
42.10
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
25.00
MMLU
54.75
GSM8K
34.00
MATH
8.50
GPQA Diamond
26.60
HumanEval
28.00
MATH-500
0.00
LiveCodeBench
0.00
MMLU Pro
0.00
MMLU
0.00
GSM8K
0.00
MATH
0.00
GPQA Diamond
49.00
HumanEval
0.00
MATH-500
90.40
LiveCodeBench
0.00