	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 68.1%	4th 65.7%	5th 63.4%	1st 68.8%	6th 62.4%	3rd 67.4%
30.2%	32%	29%	31%	36%	18%	35%
62.2%	67%	69%	49%	54%	75%	59%
55.0%	60%	71%	61%	43%	44%	51%
69.2%	68%	67%	61%	67%	79%	73%
58.5%	64%	54%	70%	61%	44%	58%
77.8%	90%	54%	83%	76%	81%	83%
70.5%	72%	70%	71%	68%	71%	71%
53.3%	66%	47%	46%	56%	52%	53%
71.7%	77%	73%	68%	75%	73%	64%
87.2%	80%	83%	87%	91%	96%	86%
66.5%	69%	83%	63%	63%	58%	63%
68.2%	63%	61%	78%	72%	60%	75%
83.2%	89%	90%	72%	96%	70%	82%
70.0%	68%	71%	61%	74%	79%	67%
67.5%	68%	61%	53%	70%	80%	73%
37.5%	35%	39%	34%	47%	29%	41%
49.3%	48%	52%	45%	57%	41%	53%
71.5%	70%	70%	65%	78%	74%	72%
67.0%	67%	67%	63%	72%	70%	63%
73.0%	78%	75%	83%	83%	50%	69%
77.8%	82%	75%	80%	85%	69%	76%
55.7%	69%	40%	59%	53%	38%	75%
95.5%	99%	96%	98%	84%	97%	99%
70.7%	70%	71%	69%	72%	72%	70%
83.2%	89%	90%	72%	96%	70%	82%
62.7%	57%	59%	81%	68%	38%	73%
44.3%	50%	33%	43%	42%	49%	49%
80.8%	77%	80%	78%	86%	77%	87%
81.2%	97%	99%	10%	91%	96%	94%
66.0%	61%	72%	55%	68%	66%	74%
30.7%	32%	20%	38%	38%	18%	38%
60.2%	59%	57%	64%	59%	63%	59%
73.7%	67%	72%	78%	78%	78%	69%
74.0%	72%	72%	74%	79%	74%	73%
80.8%	82%	79%	79%	89%	69%	87%
70.2%	65%	74%	68%	75%	67%	72%
64.5%	66%	66%	65%	66%	59%	65%
41.5%	46%	36%	38%	44%	43%	42%
58.3%	60%	59%	65%	72%	38%	56%
88.0%	97%	82%	88%	91%	81%	89%
56.0%	64%	61%	56%	56%	41%	58%
51.5%	56%	48%	54%	50%	50%	51%
66.5%	68%	75%	51%	69%	70%	66%
72.7%	70%	71%	77%	79%	68%	71%
81.2%	81%	86%	80%	75%	83%	82%
58.5%	65%	63%	54%	61%	54%	54%