	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	8th 72.3%	1st 75.1%	3rd 74.4%	9th 71.8%	10th 71.7%	6th 73.0%	5th 74.2%	2nd 74.9%	7th 72.3%	13th 68.5%	4th 74.2%	11th 71.3%	12th 71.3%
81.2%	77%	82%	79%	78%	88%	88%	76%	88%	79%	78%	82%	78%	82%
72.9%	63%	79%	81%	72%	74%	68%	76%	79%	67%	77%	76%	76%	60%
57.2%	62%	74%	63%	53%	59%	53%	53%	53%	57%	41%	47%	57%	71%
100.0%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%
74.2%	70%	77%	68%	75%	74%	75%	79%	74%	73%	70%	73%	79%	77%
77.4%	78%	76%	76%	64%	78%	83%	82%	75%	76%	83%	83%	81%	71%
61.2%	56%	66%	57%	55%	56%	59%	76%	66%	58%	55%	70%	61%	61%
52.6%	46%	51%	41%	79%	34%	52%	47%	75%	67%	27%	70%	40%	55%
56.7%	59%	62%	72%	91%	44%	56%	67%	68%	69%	28%	51%	28%	42%
87.1%	87%	87%	87%	87%	88%	87%	87%	87%	87%	87%	87%	87%	87%
78.5%	79%	91%	90%	91%	72%	82%	63%	77%	83%	59%	69%	82%	82%
63.3%	63%	63%	72%	53%	60%	77%	67%	60%	53%	78%	61%	53%	63%
96.6%	97%	97%	97%	97%	92%	97%	97%	97%	97%	97%	97%	97%	97%
100.0%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%	100%
50.3%	51%	51%	53%	43%	45%	39%	48%	52%	58%	49%	57%	57%	51%
81.5%	80%	85%	85%	79%	82%	89%	82%	83%	77%	70%	80%	82%	85%
70.1%	67%	67%	76%	68%	67%	81%	65%	73%	68%	73%	68%	68%	70%
74.2%	70%	73%	74%	67%	89%	70%	74%	73%	79%	69%	81%	76%	70%
69.2%	78%	74%	70%	74%	68%	66%	65%	70%	67%	67%	64%	64%	73%
77.4%	76%	77%	82%	83%	79%	76%	72%	83%	81%	72%	77%	76%	72%
67.1%	77%	56%	57%	51%	63%	73%	73%	56%	75%	77%	54%	84%	76%
74.8%	77%	80%	80%	80%	74%	75%	80%	75%	68%	39%	81%	82%	82%
90.2%	96%	100%	95%	86%	81%	95%	82%	90%	95%	89%	99%	73%	91%
67.8%	73%	72%	71%	56%	66%	68%	80%	74%	64%	54%	72%	67%	64%
97.0%	97%	97%	97%	97%	97%	97%	97%	97%	97%	97%	97%	97%	97%
74.2%	72%	72%	75%	75%	81%	75%	71%	70%	82%	76%	74%	79%	63%
76.7%	78%	81%	80%	61%	78%	82%	73%	86%	85%	61%	79%	67%	86%
64.2%	58%	72%	73%	53%	71%	58%	73%	61%	53%	60%	72%	77%	53%
85.4%	87%	85%	81%	86%	71%	77%	87%	81%	94%	89%	94%	87%	91%
57.9%	53%	73%	73%	49%	48%	59%	59%	64%	55%	49%	66%	51%	54%
78.5%	79%	80%	81%	78%	78%	73%	78%	81%	78%	79%	79%	78%	78%
61.5%	55%	68%	66%	66%	63%	61%	66%	67%	63%	56%	59%	50%	59%
86.8%	87%	87%	87%	87%	85%	87%	87%	87%	87%	87%	87%	87%	87%
60.6%	60%	76%	76%	71%	54%	61%	61%	63%	59%	61%	57%	55%	34%
62.1%	48%	59%	52%	59%	59%	59%	74%	61%	50%	85%	82%	62%	57%
73.2%	68%	73%	71%	71%	91%	68%	82%	76%	65%	65%	76%	68%	77%
80.3%	89%	78%	69%	88%	79%	78%	88%	81%	78%	77%	77%	83%	79%
51.0%	55%	50%	50%	43%	59%	47%	55%	57%	36%	41%	58%	48%	64%
69.3%	74%	73%	64%	63%	71%	63%	69%	70%	69%	72%	66%	75%	72%
72.9%	72%	76%	76%	60%	72%	77%	68%	82%	71%	68%	74%	69%	83%
76.0%	82%	75%	75%	73%	68%	83%	75%	78%	84%	73%	78%	74%	70%
58.7%	55%	56%	63%	69%	68%	61%	63%	65%	47%	57%	52%	62%	45%
67.3%	63%	69%	75%	67%	57%	67%	66%	73%	58%	77%	77%	63%	63%
86.4%	88%	88%	94%	60%	95%	97%	95%	90%	88%	81%	91%	79%	77%
56.5%	53%	53%	55%	71%	50%	57%	62%	53%	62%	48%	66%	57%	48%
66.0%	69%	75%	64%	75%	69%	64%	73%	73%	66%	52%	54%	64%	60%