	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	3rd 65.9%	2nd 66.7%	1st 68.9%	6th 63.9%	13th 58.5%	7th 63.7%	10th 61.7%	4th 65.9%	5th 65.4%	12th 59.0%	11th 60.5%	9th 63.0%	8th 63.0%
60.5%	54%	62%	72%	51%	54%	67%	50%	42%	82%	49%	50%	75%	78%
46.3%	53%	66%	65%	56%	28%	44%	53%	46%	40%	42%	30%	41%	38%
51.4%	61%	61%	61%	74%	34%	55%	37%	40%	57%	37%	37%	57%	57%
100.0%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%
39.8%	32%	36%	49%	42%	37%	47%	48%	37%	36%	42%	49%	32%	31%
55.7%	37%	56%	60%	60%	64%	61%	67%	54%	53%	66%	58%	60%	28%
74.2%	70%	74%	74%	69%	80%	80%	78%	66%	75%	72%	73%	73%	80%
54.7%	47%	67%	60%	51%	47%	76%	62%	72%	43%	48%	50%	40%	48%
71.8%	71%	78%	80%	60%	72%	77%	68%	82%	82%	67%	61%	61%	74%
69.0%	76%	72%	75%	70%	70%	79%	66%	88%	55%	56%	65%	58%	67%
71.5%	79%	76%	78%	79%	72%	59%	56%	73%	76%	79%	61%	79%	63%
49.4%	47%	59%	62%	34%	53%	58%	47%	54%	58%	27%	45%	58%	40%
68.2%	72%	72%	72%	88%	82%	68%	65%	70%	72%	21%	67%	70%	67%
100.0%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%
62.5%	72%	68%	68%	55%	46%	56%	69%	61%	73%	53%	73%	61%	57%
50.9%	54%	53%	66%	47%	36%	55%	43%	43%	66%	41%	42%	51%	65%
75.9%	76%	79%	76%	73%	76%	73%	75%	79%	79%	73%	73%	79%	76%
71.0%	75%	77%	77%	68%	64%	73%	71%	81%	73%	69%	64%	58%	73%
72.1%	77%	82%	84%	79%	58%	65%	72%	84%	73%	55%	73%	57%	78%
55.4%	61%	61%	61%	59%	50%	40%	55%	64%	57%	57%	43%	55%	57%
60.1%	65%	65%	58%	65%	47%	65%	61%	66%	58%	51%	52%	58%	70%
60.4%	62%	65%	59%	51%	49%	65%	65%	66%	54%	54%	60%	65%	70%
83.5%	87%	87%	96%	83%	87%	91%	68%	73%	68%	91%	91%	91%	73%
51.5%	58%	55%	54%	33%	46%	54%	53%	42%	53%	57%	54%	55%	56%
68.2%	72%	72%	72%	88%	82%	68%	65%	70%	72%	21%	67%	70%	67%
66.2%	73%	72%	71%	70%	72%	69%	49%	72%	66%	53%	56%	69%	69%
54.2%	58%	57%	47%	47%	49%	57%	58%	50%	50%	61%	52%	60%	58%
62.4%	68%	57%	68%	59%	60%	73%	51%	73%	78%	50%	58%	68%	48%
80.1%	95%	86%	86%	100%	10%	65%	81%	100%	94%	81%	81%	81%	81%
54.0%	72%	63%	68%	56%	36%	56%	49%	58%	50%	84%	38%	36%	36%
54.7%	51%	49%	62%	41%	54%	54%	41%	36%	66%	60%	60%	60%	77%
75.5%	75%	73%	82%	90%	77%	69%	75%	69%	78%	72%	73%	73%	76%
72.5%	78%	77%	83%	70%	63%	76%	77%	90%	62%	63%	66%	68%	69%
62.8%	60%	63%	67%	40%	63%	68%	68%	68%	68%	68%	68%	67%	48%
50.4%	46%	52%	55%	53%	55%	49%	47%	53%	57%	44%	49%	48%	47%
59.5%	51%	54%	49%	54%	65%	54%	65%	69%	50%	91%	52%	54%	65%
67.8%	73%	74%	77%	75%	62%	73%	61%	62%	77%	61%	52%	72%	62%
47.5%	48%	45%	48%	44%	45%	43%	58%	43%	38%	55%	55%	49%	47%
48.0%	61%	43%	61%	49%	34%	29%	37%	55%	57%	55%	42%	44%	57%
61.8%	76%	61%	60%	58%	55%	40%	52%	58%	74%	77%	58%	74%	60%
63.4%	73%	58%	58%	73%	65%	68%	68%	71%	68%	28%	65%	66%	63%
43.8%	36%	36%	42%	55%	52%	47%	39%	51%	45%	41%	35%	36%	55%
65.9%	71%	78%	80%	67%	38%	60%	64%	82%	60%	73%	60%	67%	57%
68.7%	61%	78%	78%	65%	59%	65%	66%	82%	74%	53%	73%	65%	74%
58.7%	62%	60%	69%	60%	60%	49%	53%	62%	60%	51%	60%	57%	60%
81.2%	85%	90%	80%	80%	81%	88%	83%	73%	82%	65%	90%	80%	78%