	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 65.7%	3rd 62.4%	6th 60.2%	1st 66.0%	4th 62.2%	5th 61.3%
65.2%	83%	62%	69%	65%	57%	55%
78.3%	76%	80%	71%	85%	75%	83%
82.3%	77%	93%	93%	88%	78%	65%
66.7%	78%	66%	51%	67%	64%	74%
47.0%	73%	21%	69%	48%	37%	34%
49.5%	59%	32%	55%	58%	43%	50%
69.0%	76%	47%	78%	72%	69%	72%
72.2%	68%	100%	53%	100%	68%	44%
69.0%	67%	67%	56%	76%	76%	72%
69.0%	73%	81%	48%	69%	74%	69%
76.7%	83%	82%	56%	86%	72%	81%
44.8%	43%	15%	50%	56%	50%	55%
48.3%	61%	74%	31%	63%	26%	35%
60.8%	56%	63%	60%	65%	56%	65%
47.8%	44%	50%	47%	50%	48%	48%
61.2%	60%	63%	53%	71%	59%	61%
58.7%	63%	72%	53%	62%	57%	45%
56.8%	60%	56%	54%	55%	65%	51%
67.3%	72%	68%	68%	68%	66%	62%
82.2%	80%	79%	78%	92%	82%	82%
49.0%	53%	36%	60%	51%	44%	50%
75.2%	73%	73%	76%	71%	78%	80%
37.2%	45%	41%	38%	29%	35%	35%
64.7%	73%	40%	69%	64%	68%	74%
56.3%	54%	51%	65%	67%	36%	65%
70.3%	73%	65%	80%	72%	58%	74%
67.2%	66%	64%	65%	77%	61%	70%
69.7%	81%	55%	56%	73%	81%	72%
40.3%	40%	56%	9%	58%	47%	32%
85.2%	81%	86%	86%	86%	86%	86%
30.2%	21%	68%	15%	28%	10%	39%
66.8%	70%	77%	66%	69%	60%	59%
58.0%	59%	66%	53%	48%	65%	57%
65.0%	62%	53%	68%	57%	70%	80%
44.2%	49%	49%	53%	44%	44%	26%
63.3%	68%	60%	66%	61%	60%	65%
60.2%	66%	49%	56%	61%	70%	59%
61.3%	52%	82%	48%	68%	69%	49%
57.2%	61%	36%	48%	71%	63%	64%
65.3%	69%	66%	59%	70%	59%	69%
60.0%	65%	50%	57%	60%	60%	68%
63.8%	64%	60%	69%	60%	70%	60%
61.2%	70%	81%	52%	70%	55%	39%
64.2%	74%	56%	69%	58%	70%	58%
79.2%	83%	87%	69%	73%	81%	82%
77.2%	66%	86%	71%	87%	86%	67%
60.5%	73%	58%	58%	52%	70%	52%
63.2%	72%	64%	49%	67%	70%	57%
81.7%	80%	87%	86%	78%	78%	81%
65.2%	65%	65%	75%	65%	63%	58%
58.2%	59%	51%	59%	63%	51%	66%
56.2%	56%	56%	50%	56%	59%	60%
87.2%	82%	89%	94%	76%	93%	89%
63.3%	71%	33%	65%	80%	65%	66%