	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 80.2%	2nd 77.0%	6th 68.0%	3rd 75.2%	5th 71.2%	4th 71.4%
51.0%	54%	57%	56%	53%	46%	40%
84.7%	92%	94%	83%	86%	75%	78%
83.0%	79%	84%	90%	91%	79%	75%
68.7%	75%	70%	62%	71%	67%	67%
68.0%	84%	74%	65%	60%	63%	62%
72.3%	84%	56%	83%	84%	71%	56%
76.2%	87%	70%	64%	76%	81%	79%
58.2%	67%	95%	57%	38%	50%	42%
63.8%	67%	50%	58%	75%	60%	73%
64.2%	78%	56%	51%	63%	70%	67%
85.3%	97%	95%	60%	95%	70%	95%
81.0%	74%	59%	89%	90%	85%	89%
54.3%	65%	68%	38%	65%	45%	45%
80.0%	86%	84%	69%	73%	86%	82%
76.2%	87%	83%	66%	72%	80%	69%
87.0%	94%	84%	90%	91%	81%	82%
69.5%	77%	69%	62%	77%	68%	64%
66.8%	81%	70%	59%	73%	48%	70%
83.3%	84%	85%	85%	80%	85%	81%
65.5%	79%	75%	60%	66%	58%	55%
75.3%	82%	92%	63%	71%	74%	70%
79.7%	92%	92%	61%	83%	84%	66%
52.0%	70%	69%	53%	37%	33%	50%
74.7%	86%	67%	67%	83%	73%	72%
78.8%	86%	89%	61%	76%	86%	75%
86.0%	86%	88%	82%	91%	84%	85%
91.8%	96%	94%	81%	89%	96%	95%
65.8%	88%	82%	49%	63%	58%	55%
73.8%	89%	78%	50%	85%	66%	75%
84.7%	87%	87%	87%	73%	87%	87%
55.3%	45%	70%	43%	70%	46%	58%
70.3%	87%	38%	69%	88%	64%	76%
63.3%	73%	81%	41%	61%	61%	63%
76.3%	77%	79%	72%	79%	71%	80%
55.2%	59%	81%	59%	51%	38%	43%
83.0%	85%	89%	80%	82%	82%	80%
67.8%	76%	63%	59%	70%	71%	68%
76.8%	77%	84%	69%	73%	84%	74%
81.0%	76%	77%	82%	86%	81%	84%
85.7%	82%	87%	83%	84%	88%	90%
77.8%	81%	66%	78%	83%	79%	80%
62.2%	71%	70%	50%	58%	64%	60%
65.8%	76%	75%	62%	67%	54%	61%
90.7%	97%	91%	88%	94%	92%	82%
74.3%	81%	78%	65%	69%	75%	78%
86.7%	85%	92%	81%	88%	87%	87%
65.5%	79%	68%	57%	57%	75%	57%
62.5%	71%	82%	47%	54%	67%	54%
78.2%	84%	88%	78%	77%	74%	68%
77.3%	71%	76%	87%	85%	72%	73%
83.3%	83%	86%	85%	87%	78%	81%
80.7%	84%	62%	84%	82%	84%	88%
84.2%	89%	83%	81%	93%	78%	81%
81.0%	91%	75%	72%	91%	71%	86%