	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 76.1%	1st 76.5%	6th 70.6%	3rd 72.9%	5th 71.1%	4th 72.5%
50.0%	48%	49%	37%	55%	63%	48%
83.8%	85%	92%	88%	78%	92%	68%
80.7%	76%	86%	75%	77%	96%	74%
72.0%	78%	75%	57%	78%	85%	59%
69.0%	73%	86%	85%	72%	38%	60%
83.5%	85%	72%	87%	95%	81%	81%
77.8%	86%	77%	84%	71%	70%	79%
71.2%	79%	75%	66%	69%	69%	69%
83.0%	83%	86%	81%	85%	97%	66%
72.5%	81%	81%	76%	61%	54%	82%
71.3%	66%	80%	62%	72%	77%	71%
80.0%	79%	81%	80%	81%	80%	79%
72.8%	73%	73%	79%	62%	72%	78%
87.5%	89%	88%	94%	89%	79%	86%
49.2%	56%	52%	55%	37%	53%	42%
67.5%	62%	77%	65%	60%	81%	60%
86.2%	87%	87%	86%	86%	83%	88%
52.8%	60%	52%	64%	51%	45%	45%
77.7%	85%	85%	76%	77%	74%	69%
38.7%	47%	45%	45%	34%	19%	42%
81.0%	78%	81%	82%	82%	80%	83%
59.3%	63%	70%	43%	60%	60%	60%
79.2%	85%	81%	83%	69%	81%	76%
70.5%	67%	69%	77%	70%	65%	75%
63.5%	65%	60%	55%	68%	68%	65%
74.8%	76%	70%	71%	75%	74%	83%
88.5%	89%	89%	86%	85%	87%	95%
60.2%	55%	62%	59%	62%	66%	57%
76.5%	83%	86%	67%	76%	73%	74%
64.5%	77%	79%	41%	61%	68%	61%
59.0%	65%	66%	58%	51%	56%	58%
75.7%	82%	81%	75%	83%	69%	64%
77.5%	69%	88%	94%	68%	73%	73%
81.7%	84%	85%	87%	82%	68%	84%
79.3%	81%	71%	88%	85%	67%	84%
67.8%	70%	69%	66%	73%	61%	68%
73.5%	72%	60%	78%	74%	73%	84%
71.5%	65%	55%	83%	79%	61%	86%
75.8%	77%	77%	76%	77%	71%	77%
57.3%	62%	64%	41%	58%	69%	50%
74.5%	88%	66%	54%	74%	89%	76%
65.0%	77%	58%	60%	58%	67%	70%
61.5%	60%	71%	71%	52%	48%	67%
72.7%	80%	81%	56%	71%	85%	63%
87.0%	90%	88%	79%	87%	89%	89%
63.5%	66%	85%	52%	59%	59%	60%
76.0%	73%	75%	84%	74%	67%	83%
73.0%	68%	66%	89%	77%	59%	79%
87.0%	95%	91%	79%	89%	77%	91%
74.3%	83%	79%	59%	75%	75%	75%
71.8%	79%	84%	51%	73%	76%	68%
66.3%	73%	78%	60%	62%	63%	62%
79.0%	81%	83%	69%	82%	80%	79%
84.7%	91%	93%	80%	86%	77%	81%
84.8%	80%	84%	80%	94%	80%	91%
62.7%	70%	84%	43%	61%	53%	65%
63.3%	72%	57%	56%	75%	57%	63%
56.2%	66%	62%	48%	51%	66%	44%
85.2%	86%	87%	90%	88%	75%	85%
78.7%	81%	85%	72%	79%	76%	79%
62.5%	66%	69%	45%	61%	75%	59%
80.2%	83%	83%	86%	81%	63%	85%
81.7%	86%	77%	89%	79%	73%	86%
78.8%	70%	81%	85%	79%	76%	82%
86.3%	74%	89%	94%	85%	88%	88%
72.8%	71%	70%	79%	69%	64%	84%
87.0%	89%	88%	92%	87%	79%	87%
75.8%	77%	77%	85%	79%	61%	76%
84.5%	84%	89%	85%	90%	76%	83%
76.2%	83%	69%	84%	75%	81%	65%
86.7%	89%	88%	75%	83%	95%	90%
39.8%	48%	53%	48%	38%	21%	31%
70.8%	75%	69%	50%	75%	76%	80%
79.3%	78%	79%	78%	83%	74%	84%
54.0%	60%	57%	57%	46%	48%	56%
82.5%	84%	75%	80%	80%	88%	88%
77.8%	81%	85%	70%	78%	75%	78%
73.2%	64%	76%	66%	76%	80%	77%
82.3%	86%	85%	62%	91%	90%	80%
52.2%	61%	72%	55%	43%	41%	41%
59.7%	72%	88%	55%	49%	56%	38%
75.2%	83%	84%	74%	70%	71%	69%
55.5%	58%	63%	39%	57%	59%	57%
85.5%	92%	85%	81%	90%	83%	82%
88.7%	92%	87%	76%	94%	90%	93%
70.7%	77%	74%	59%	73%	71%	70%
77.0%	78%	89%	64%	79%	78%	74%
82.3%	85%	83%	84%	85%	72%	85%
84.3%	96%	81%	86%	87%	73%	83%
88.2%	95%	87%	81%	86%	89%	91%
85.0%	87%	88%	80%	89%	86%	80%