	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 74.3%	1st 75.5%	6th 59.8%	3rd 71.6%	5th 69.4%	4th 70.3%
51.2%	52%	50%	55%	51%	55%	44%
83.7%	83%	80%	89%	83%	75%	92%
84.0%	92%	82%	94%	79%	79%	78%
70.5%	72%	77%	69%	69%	65%	71%
62.0%	71%	59%	47%	57%	59%	79%
69.2%	71%	78%	55%	74%	69%	68%
78.3%	86%	88%	55%	82%	80%	79%
40.7%	67%	7%	37%	38%	57%	38%
70.8%	70%	85%	55%	78%	66%	71%
63.7%	73%	79%	37%	59%	69%	65%
87.3%	89%	95%	64%	89%	95%	92%
78.5%	75%	63%	75%	84%	85%	89%
50.0%	65%	77%	10%	58%	45%	45%
82.5%	90%	92%	63%	82%	86%	82%
76.2%	84%	86%	56%	81%	81%	69%
85.3%	90%	79%	94%	87%	76%	86%
71.0%	73%	79%	60%	77%	77%	60%
69.3%	70%	89%	62%	67%	58%	70%
52.5%	53%	69%	38%	59%	45%	51%
62.8%	72%	77%	44%	64%	64%	56%
78.3%	84%	88%	57%	77%	88%	76%
74.2%	90%	80%	49%	78%	80%	68%
52.2%	59%	48%	56%	45%	59%	46%
76.3%	82%	77%	67%	80%	76%	76%
79.0%	85%	89%	60%	84%	75%	81%
81.7%	88%	89%	73%	80%	74%	86%
96.0%	97%	94%	97%	98%	97%	93%
66.8%	78%	90%	38%	68%	72%	55%
73.2%	84%	80%	55%	80%	70%	70%
49.3%	49%	66%	45%	47%	37%	52%
67.8%	71%	60%	53%	74%	74%	75%
62.5%	61%	70%	44%	66%	61%	73%
59.5%	69%	77%	32%	55%	63%	61%
76.8%	78%	70%	68%	83%	80%	82%
33.8%	25%	46%	22%	34%	34%	42%
81.5%	80%	79%	86%	83%	80%	81%
73.2%	82%	76%	61%	70%	74%	76%
45.3%	42%	63%	34%	43%	47%	43%
84.8%	88%	82%	88%	78%	85%	88%
86.2%	84%	92%	85%	88%	90%	78%
83.0%	82%	81%	84%	82%	90%	79%
61.8%	71%	70%	48%	59%	67%	56%
66.7%	67%	84%	60%	65%	58%	66%
86.0%	89%	93%	88%	88%	74%	84%
73.3%	77%	73%	62%	74%	77%	77%
57.0%	49%	66%	53%	56%	49%	69%
44.2%	47%	57%	33%	59%	20%	49%
63.8%	72%	75%	44%	69%	65%	58%
71.5%	78%	84%	57%	68%	79%	63%
75.8%	82%	85%	66%	83%	64%	75%
77.3%	82%	83%	68%	79%	71%	81%
83.2%	85%	78%	85%	82%	81%	88%
83.7%	90%	84%	79%	89%	79%	81%
73.2%	69%	58%	71%	85%	71%	85%