	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	11th 71.6%	2nd 74.5%	1st 75.3%	12th 70.7%	7th 72.2%	4th 73.7%	3rd 73.9%	6th 73.1%	10th 71.6%	13th 68.7%	5th 73.1%	9th 71.7%	8th 72.0%
80.6%	75%	75%	75%	95%	82%	83%	70%	83%	75%	95%	76%	69%	95%
57.7%	55%	67%	54%	49%	55%	67%	75%	62%	49%	59%	50%	59%	49%
75.1%	72%	76%	69%	76%	83%	72%	76%	82%	69%	71%	72%	82%	76%
100.0%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%
67.4%	50%	70%	70%	67%	76%	69%	63%	71%	55%	84%	69%	63%	69%
75.6%	73%	66%	77%	84%	70%	79%	81%	77%	76%	70%	76%	73%	81%
64.8%	55%	59%	62%	52%	72%	55%	88%	65%	61%	61%	68%	72%	72%
55.8%	47%	58%	58%	38%	58%	67%	58%	74%	62%	42%	46%	61%	56%
67.2%	74%	88%	88%	74%	36%	94%	76%	58%	88%	37%	54%	44%	63%
95.0%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%
84.7%	84%	88%	95%	100%	78%	91%	73%	81%	80%	81%	81%	74%	95%
66.5%	65%	58%	73%	70%	74%	67%	67%	68%	61%	61%	70%	61%	70%
90.0%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%
100.0%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%
68.2%	77%	63%	66%	72%	41%	67%	79%	69%	72%	70%	82%	69%	60%
80.6%	75%	85%	90%	79%	73%	78%	79%	72%	80%	79%	89%	90%	79%
79.2%	85%	93%	80%	83%	89%	83%	83%	81%	76%	37%	83%	74%	83%
66.2%	65%	74%	73%	61%	68%	61%	65%	65%	66%	65%	58%	73%	66%
67.2%	67%	68%	67%	58%	69%	75%	69%	73%	67%	58%	68%	73%	62%
76.1%	87%	87%	87%	83%	87%	69%	67%	69%	78%	67%	74%	67%	67%
63.7%	71%	65%	65%	63%	57%	67%	63%	64%	61%	49%	57%	75%	71%
60.8%	80%	70%	79%	14%	90%	32%	58%	51%	46%	43%	81%	86%	60%
80.5%	73%	80%	80%	75%	98%	89%	85%	69%	75%	85%	95%	85%	57%
72.2%	74%	74%	72%	57%	82%	71%	79%	79%	82%	30%	79%	77%	82%
90.0%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%	90%
74.4%	78%	76%	77%	75%	70%	78%	70%	80%	78%	78%	70%	67%	70%
69.8%	78%	80%	94%	41%	83%	71%	59%	80%	76%	46%	88%	46%	65%
69.1%	67%	73%	74%	61%	74%	68%	69%	68%	61%	74%	61%	74%	74%
73.4%	83%	79%	66%	90%	10%	95%	90%	66%	66%	93%	84%	66%	66%
56.1%	43%	56%	63%	56%	47%	56%	51%	58%	56%	58%	76%	58%	51%
85.9%	79%	76%	82%	95%	95%	69%	95%	83%	95%	79%	79%	95%	95%
81.5%	73%	87%	100%	88%	84%	91%	77%	83%	80%	73%	70%	76%	77%
95.0%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%
73.4%	72%	75%	77%	70%	67%	80%	72%	79%	73%	71%	73%	72%	73%
57.8%	47%	57%	57%	59%	60%	56%	68%	64%	46%	63%	63%	52%	60%
56.8%	52%	56%	65%	52%	72%	57%	61%	56%	55%	52%	47%	55%	59%
74.2%	72%	82%	80%	78%	70%	67%	73%	78%	73%	90%	73%	62%	67%
74.1%	66%	73%	73%	57%	84%	73%	78%	78%	76%	67%	80%	76%	82%
69.7%	71%	69%	70%	67%	67%	69%	74%	70%	71%	67%	69%	75%	67%
89.5%	88%	95%	84%	74%	100%	100%	74%	79%	94%	90%	92%	100%	94%
84.8%	86%	86%	86%	83%	83%	84%	89%	86%	86%	83%	83%	84%	83%
40.2%	35%	41%	34%	56%	43%	62%	43%	50%	28%	41%	32%	28%	29%
59.2%	49%	59%	58%	75%	54%	53%	56%	60%	65%	73%	62%	50%	55%
46.5%	54%	54%	54%	33%	37%	50%	47%	50%	52%	36%	46%	42%	50%
72.3%	75%	69%	73%	75%	65%	68%	71%	73%	71%	67%	80%	75%	78%
45.2%	51%	52%	48%	48%	47%	39%	57%	38%	44%	44%	38%	46%	35%