	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini	Qwen3 30b A3B Instruct 2507	Qwen3 Next 80b A3B Instruct
Score	4th 63.1%	2nd 64.3%	1st 67.0%	5th 62.9%	13th 56.5%	8th 61.1%	10th 60.9%	3rd 63.9%	7th 62.2%	12th 56.9%	9th 61.0%	6th 62.5%	11th 60.5%
43.5%	43%	42%	52%	16%	40%	37%	45%	30%	59%	45%	46%	52%	59%
29.5%	38%	42%	48%	15%	21%	29%	24%	42%	20%	29%	20%	26%	30%
64.7%	73%	73%	68%	78%	41%	56%	60%	60%	68%	68%	60%	68%	68%
91.0%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%
42.9%	36%	34%	48%	45%	30%	60%	42%	45%	41%	49%	60%	39%	29%
48.1%	45%	44%	65%	60%	38%	46%	55%	55%	37%	61%	53%	37%	29%
57.3%	63%	62%	60%	68%	54%	54%	50%	62%	56%	54%	54%	54%	54%
63.8%	65%	60%	75%	20%	58%	75%	60%	62%	74%	55%	74%	76%	75%
39.2%	38%	40%	47%	64%	35%	47%	49%	47%	47%	27%	16%	13%	40%
84.3%	84%	76%	86%	86%	79%	85%	86%	85%	90%	95%	92%	85%	67%
76.4%	75%	100%	91%	100%	70%	70%	64%	75%	75%	70%	63%	70%	70%
64.1%	58%	58%	58%	58%	75%	84%	66%	48%	76%	47%	58%	78%	69%
75.2%	77%	77%	77%	97%	56%	77%	80%	80%	72%	52%	77%	77%	78%
91.0%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%
52.0%	56%	52%	52%	46%	45%	56%	50%	50%	42%	61%	52%	58%	56%
41.4%	47%	41%	54%	27%	32%	53%	27%	27%	47%	41%	41%	47%	54%
70.2%	74%	69%	72%	74%	90%	69%	75%	74%	69%	27%	74%	73%	73%
64.2%	68%	68%	75%	79%	51%	72%	68%	74%	54%	56%	52%	54%	64%
53.1%	53%	71%	71%	76%	31%	47%	52%	68%	36%	41%	45%	36%	63%
51.6%	54%	54%	62%	53%	54%	45%	54%	60%	54%	31%	48%	54%	48%
72.2%	76%	80%	64%	74%	77%	80%	76%	80%	67%	60%	67%	67%	70%
50.5%	67%	67%	64%	17%	48%	20%	64%	40%	43%	12%	71%	80%	64%
92.7%	89%	97%	95%	97%	95%	97%	97%	97%	89%	79%	89%	95%	89%
55.9%	52%	59%	59%	70%	50%	52%	56%	67%	53%	51%	52%	54%	52%
74.5%	76%	76%	76%	100%	53%	76%	77%	77%	74%	51%	76%	78%	78%
68.4%	65%	72%	72%	59%	72%	72%	57%	68%	72%	76%	64%	72%	68%
63.3%	59%	64%	64%	69%	62%	68%	73%	78%	58%	70%	45%	68%	45%
71.3%	75%	69%	67%	65%	79%	76%	70%	76%	79%	62%	71%	76%	62%
67.8%	80%	80%	80%	80%	10%	57%	72%	80%	80%	77%	64%	57%	64%
40.1%	48%	50%	53%	43%	39%	38%	24%	48%	37%	37%	46%	35%	23%
41.4%	40%	40%	53%	27%	34%	40%	40%	27%	45%	40%	45%	53%	54%
60.5%	61%	61%	69%	59%	61%	59%	54%	68%	61%	61%	57%	61%	54%
67.5%	73%	56%	60%	71%	57%	71%	61%	71%	77%	74%	75%	71%	61%
50.6%	67%	51%	51%	84%	52%	51%	51%	60%	51%	38%	46%	32%	24%
78.4%	74%	74%	87%	74%	77%	74%	74%	74%	100%	74%	74%	90%	73%
88.2%	80%	87%	76%	88%	94%	88%	93%	88%	76%	93%	94%	96%	93%
72.4%	73%	73%	73%	40%	74%	73%	73%	73%	73%	78%	73%	87%	78%
36.5%	45%	29%	49%	69%	31%	27%	28%	44%	27%	36%	31%	29%	29%
59.3%	56%	65%	68%	65%	50%	43%	56%	60%	68%	69%	51%	60%	60%
55.5%	55%	63%	55%	49%	55%	49%	50%	55%	63%	55%	55%	63%	55%
63.5%	71%	74%	68%	53%	71%	67%	60%	67%	67%	15%	74%	65%	74%
59.7%	59%	62%	71%	49%	53%	60%	56%	65%	56%	65%	61%	61%	58%
45.8%	43%	53%	64%	61%	31%	41%	34%	49%	34%	57%	50%	34%	45%
51.2%	50%	61%	54%	45%	34%	49%	50%	55%	61%	41%	55%	55%	55%
85.3%	79%	87%	87%	75%	94%	75%	100%	74%	87%	89%	88%	91%	83%
64.4%	60%	61%	61%	66%	63%	62%	66%	72%	66%	66%	66%	66%	62%