Training logs (final)

training_logs/per_generator_auroc.tsv

@@ -183,3 +183,578 @@ step	generator	AUROC
 35	qwen1.5-72b-chat-8bit	0.9995
 35	text-bison-002	0.9992
 35	MACRO_AVG	0.9960
+40	deepseek-r1-distill-qwen-32b	0.9998
+40	falcon3-10b-instruct	0.9992
+40	gemini-1.5-pro	0.9689
+40	gemini-2.0-flash	0.9998
+40	gemini-pro	0.9851
+40	gemini-pro-paraphrase	0.9884
+40	gpt-3.5-turbo	0.9999
+40	gpt-4-turbo	1.0000
+40	gpt-4-turbo-paraphrase	0.9963
+40	gpt-4.5-preview	0.9980
+40	gpt-4o	0.9999
+40	gpt-4o-mini	0.9999
+40	llama-2-70b-chat	0.9974
+40	llama-2-7b-chat	0.9967
+40	llama-3.1-8b-instruct	0.9929
+40	llama-3.3-70b-instruct	0.9993
+40	ministral-8b-instruct-2410	0.9997
+40	mistral-7b-instruct-v0.2	0.9965
+40	mixtral-8x7b-instruct-v0.1	0.9947
+40	o3-mini	0.9999
+40	qwen1.5-72b-chat-8bit	0.9995
+40	text-bison-002	0.9992
+40	MACRO_AVG	0.9960
+45	deepseek-r1-distill-qwen-32b	0.9998
+45	falcon3-10b-instruct	0.9992
+45	gemini-1.5-pro	0.9689
+45	gemini-2.0-flash	0.9998
+45	gemini-pro	0.9851
+45	gemini-pro-paraphrase	0.9884
+45	gpt-3.5-turbo	0.9999
+45	gpt-4-turbo	1.0000
+45	gpt-4-turbo-paraphrase	0.9963
+45	gpt-4.5-preview	0.9980
+45	gpt-4o	0.9999
+45	gpt-4o-mini	0.9999
+45	llama-2-70b-chat	0.9974
+45	llama-2-7b-chat	0.9967
+45	llama-3.1-8b-instruct	0.9929
+45	llama-3.3-70b-instruct	0.9993
+45	ministral-8b-instruct-2410	0.9997
+45	mistral-7b-instruct-v0.2	0.9965
+45	mixtral-8x7b-instruct-v0.1	0.9947
+45	o3-mini	0.9999
+45	qwen1.5-72b-chat-8bit	0.9995
+45	text-bison-002	0.9992
+45	MACRO_AVG	0.9960
+50	deepseek-r1-distill-qwen-32b	0.9998
+50	falcon3-10b-instruct	0.9992
+50	gemini-1.5-pro	0.9689
+50	gemini-2.0-flash	0.9998
+50	gemini-pro	0.9851
+50	gemini-pro-paraphrase	0.9884
+50	gpt-3.5-turbo	0.9999
+50	gpt-4-turbo	1.0000
+50	gpt-4-turbo-paraphrase	0.9963
+50	gpt-4.5-preview	0.9980
+50	gpt-4o	0.9999
+50	gpt-4o-mini	0.9999
+50	llama-2-70b-chat	0.9974
+50	llama-2-7b-chat	0.9967
+50	llama-3.1-8b-instruct	0.9929
+50	llama-3.3-70b-instruct	0.9993
+50	ministral-8b-instruct-2410	0.9997
+50	mistral-7b-instruct-v0.2	0.9965
+50	mixtral-8x7b-instruct-v0.1	0.9947
+50	o3-mini	0.9999
+50	qwen1.5-72b-chat-8bit	0.9995
+50	text-bison-002	0.9992
+50	MACRO_AVG	0.9960
+55	deepseek-r1-distill-qwen-32b	0.9998
+55	falcon3-10b-instruct	0.9992
+55	gemini-1.5-pro	0.9689
+55	gemini-2.0-flash	0.9998
+55	gemini-pro	0.9851
+55	gemini-pro-paraphrase	0.9884
+55	gpt-3.5-turbo	0.9999
+55	gpt-4-turbo	1.0000
+55	gpt-4-turbo-paraphrase	0.9963
+55	gpt-4.5-preview	0.9980
+55	gpt-4o	0.9999
+55	gpt-4o-mini	0.9999
+55	llama-2-70b-chat	0.9974
+55	llama-2-7b-chat	0.9967
+55	llama-3.1-8b-instruct	0.9929
+55	llama-3.3-70b-instruct	0.9993
+55	ministral-8b-instruct-2410	0.9997
+55	mistral-7b-instruct-v0.2	0.9965
+55	mixtral-8x7b-instruct-v0.1	0.9947
+55	o3-mini	0.9999
+55	qwen1.5-72b-chat-8bit	0.9995
+55	text-bison-002	0.9992
+55	MACRO_AVG	0.9960
+60	deepseek-r1-distill-qwen-32b	0.9998
+60	falcon3-10b-instruct	0.9992
+60	gemini-1.5-pro	0.9689
+60	gemini-2.0-flash	0.9998
+60	gemini-pro	0.9851
+60	gemini-pro-paraphrase	0.9884
+60	gpt-3.5-turbo	0.9999
+60	gpt-4-turbo	1.0000
+60	gpt-4-turbo-paraphrase	0.9963
+60	gpt-4.5-preview	0.9980
+60	gpt-4o	0.9999
+60	gpt-4o-mini	0.9999
+60	llama-2-70b-chat	0.9974
+60	llama-2-7b-chat	0.9967
+60	llama-3.1-8b-instruct	0.9929
+60	llama-3.3-70b-instruct	0.9993
+60	ministral-8b-instruct-2410	0.9997
+60	mistral-7b-instruct-v0.2	0.9965
+60	mixtral-8x7b-instruct-v0.1	0.9947
+60	o3-mini	0.9999
+60	qwen1.5-72b-chat-8bit	0.9995
+60	text-bison-002	0.9992
+60	MACRO_AVG	0.9960
+65	deepseek-r1-distill-qwen-32b	0.9998
+65	falcon3-10b-instruct	0.9992
+65	gemini-1.5-pro	0.9689
+65	gemini-2.0-flash	0.9998
+65	gemini-pro	0.9851
+65	gemini-pro-paraphrase	0.9884
+65	gpt-3.5-turbo	0.9999
+65	gpt-4-turbo	1.0000
+65	gpt-4-turbo-paraphrase	0.9963
+65	gpt-4.5-preview	0.9980
+65	gpt-4o	0.9999
+65	gpt-4o-mini	0.9999
+65	llama-2-70b-chat	0.9974
+65	llama-2-7b-chat	0.9967
+65	llama-3.1-8b-instruct	0.9929
+65	llama-3.3-70b-instruct	0.9993
+65	ministral-8b-instruct-2410	0.9997
+65	mistral-7b-instruct-v0.2	0.9965
+65	mixtral-8x7b-instruct-v0.1	0.9947
+65	o3-mini	0.9999
+65	qwen1.5-72b-chat-8bit	0.9995
+65	text-bison-002	0.9992
+65	MACRO_AVG	0.9960
+70	deepseek-r1-distill-qwen-32b	0.9998
+70	falcon3-10b-instruct	0.9992
+70	gemini-1.5-pro	0.9689
+70	gemini-2.0-flash	0.9998
+70	gemini-pro	0.9851
+70	gemini-pro-paraphrase	0.9884
+70	gpt-3.5-turbo	0.9999
+70	gpt-4-turbo	1.0000
+70	gpt-4-turbo-paraphrase	0.9963
+70	gpt-4.5-preview	0.9980
+70	gpt-4o	0.9999
+70	gpt-4o-mini	0.9999
+70	llama-2-70b-chat	0.9974
+70	llama-2-7b-chat	0.9967
+70	llama-3.1-8b-instruct	0.9929
+70	llama-3.3-70b-instruct	0.9993
+70	ministral-8b-instruct-2410	0.9997
+70	mistral-7b-instruct-v0.2	0.9965
+70	mixtral-8x7b-instruct-v0.1	0.9947
+70	o3-mini	0.9999
+70	qwen1.5-72b-chat-8bit	0.9995
+70	text-bison-002	0.9992
+70	MACRO_AVG	0.9960
+75	deepseek-r1-distill-qwen-32b	0.9998
+75	falcon3-10b-instruct	0.9992
+75	gemini-1.5-pro	0.9689
+75	gemini-2.0-flash	0.9998
+75	gemini-pro	0.9851
+75	gemini-pro-paraphrase	0.9884
+75	gpt-3.5-turbo	0.9999
+75	gpt-4-turbo	1.0000
+75	gpt-4-turbo-paraphrase	0.9963
+75	gpt-4.5-preview	0.9980
+75	gpt-4o	0.9999
+75	gpt-4o-mini	0.9999
+75	llama-2-70b-chat	0.9974
+75	llama-2-7b-chat	0.9967
+75	llama-3.1-8b-instruct	0.9929
+75	llama-3.3-70b-instruct	0.9993
+75	ministral-8b-instruct-2410	0.9997
+75	mistral-7b-instruct-v0.2	0.9965
+75	mixtral-8x7b-instruct-v0.1	0.9947
+75	o3-mini	0.9999
+75	qwen1.5-72b-chat-8bit	0.9995
+75	text-bison-002	0.9992
+75	MACRO_AVG	0.9960
+80	deepseek-r1-distill-qwen-32b	0.9998
+80	falcon3-10b-instruct	0.9992
+80	gemini-1.5-pro	0.9689
+80	gemini-2.0-flash	0.9998
+80	gemini-pro	0.9851
+80	gemini-pro-paraphrase	0.9884
+80	gpt-3.5-turbo	0.9999
+80	gpt-4-turbo	1.0000
+80	gpt-4-turbo-paraphrase	0.9963
+80	gpt-4.5-preview	0.9980
+80	gpt-4o	0.9999
+80	gpt-4o-mini	0.9999
+80	llama-2-70b-chat	0.9974
+80	llama-2-7b-chat	0.9967
+80	llama-3.1-8b-instruct	0.9929
+80	llama-3.3-70b-instruct	0.9993
+80	ministral-8b-instruct-2410	0.9997
+80	mistral-7b-instruct-v0.2	0.9965
+80	mixtral-8x7b-instruct-v0.1	0.9947
+80	o3-mini	0.9999
+80	qwen1.5-72b-chat-8bit	0.9995
+80	text-bison-002	0.9992
+80	MACRO_AVG	0.9960
+85	deepseek-r1-distill-qwen-32b	0.9998
+85	falcon3-10b-instruct	0.9992
+85	gemini-1.5-pro	0.9689
+85	gemini-2.0-flash	0.9998
+85	gemini-pro	0.9851
+85	gemini-pro-paraphrase	0.9884
+85	gpt-3.5-turbo	0.9999
+85	gpt-4-turbo	1.0000
+85	gpt-4-turbo-paraphrase	0.9963
+85	gpt-4.5-preview	0.9980
+85	gpt-4o	0.9999
+85	gpt-4o-mini	0.9999
+85	llama-2-70b-chat	0.9974
+85	llama-2-7b-chat	0.9967
+85	llama-3.1-8b-instruct	0.9929
+85	llama-3.3-70b-instruct	0.9993
+85	ministral-8b-instruct-2410	0.9997
+85	mistral-7b-instruct-v0.2	0.9965
+85	mixtral-8x7b-instruct-v0.1	0.9947
+85	o3-mini	0.9999
+85	qwen1.5-72b-chat-8bit	0.9995
+85	text-bison-002	0.9992
+85	MACRO_AVG	0.9960
+90	deepseek-r1-distill-qwen-32b	0.9998
+90	falcon3-10b-instruct	0.9992
+90	gemini-1.5-pro	0.9689
+90	gemini-2.0-flash	0.9998
+90	gemini-pro	0.9851
+90	gemini-pro-paraphrase	0.9884
+90	gpt-3.5-turbo	0.9999
+90	gpt-4-turbo	1.0000
+90	gpt-4-turbo-paraphrase	0.9963
+90	gpt-4.5-preview	0.9980
+90	gpt-4o	0.9999
+90	gpt-4o-mini	0.9999
+90	llama-2-70b-chat	0.9974
+90	llama-2-7b-chat	0.9967
+90	llama-3.1-8b-instruct	0.9929
+90	llama-3.3-70b-instruct	0.9993
+90	ministral-8b-instruct-2410	0.9997
+90	mistral-7b-instruct-v0.2	0.9965
+90	mixtral-8x7b-instruct-v0.1	0.9947
+90	o3-mini	0.9999
+90	qwen1.5-72b-chat-8bit	0.9995
+90	text-bison-002	0.9992
+90	MACRO_AVG	0.9960
+95	deepseek-r1-distill-qwen-32b	0.9998
+95	falcon3-10b-instruct	0.9992
+95	gemini-1.5-pro	0.9689
+95	gemini-2.0-flash	0.9998
+95	gemini-pro	0.9851
+95	gemini-pro-paraphrase	0.9884
+95	gpt-3.5-turbo	0.9999
+95	gpt-4-turbo	1.0000
+95	gpt-4-turbo-paraphrase	0.9963
+95	gpt-4.5-preview	0.9980
+95	gpt-4o	0.9999
+95	gpt-4o-mini	0.9999
+95	llama-2-70b-chat	0.9974
+95	llama-2-7b-chat	0.9967
+95	llama-3.1-8b-instruct	0.9929
+95	llama-3.3-70b-instruct	0.9993
+95	ministral-8b-instruct-2410	0.9997
+95	mistral-7b-instruct-v0.2	0.9965
+95	mixtral-8x7b-instruct-v0.1	0.9947
+95	o3-mini	0.9999
+95	qwen1.5-72b-chat-8bit	0.9995
+95	text-bison-002	0.9992
+95	MACRO_AVG	0.9960
+100	deepseek-r1-distill-qwen-32b	0.9998
+100	falcon3-10b-instruct	0.9992
+100	gemini-1.5-pro	0.9689
+100	gemini-2.0-flash	0.9998
+100	gemini-pro	0.9851
+100	gemini-pro-paraphrase	0.9884
+100	gpt-3.5-turbo	0.9999
+100	gpt-4-turbo	1.0000
+100	gpt-4-turbo-paraphrase	0.9963
+100	gpt-4.5-preview	0.9980
+100	gpt-4o	0.9999
+100	gpt-4o-mini	0.9999
+100	llama-2-70b-chat	0.9974
+100	llama-2-7b-chat	0.9967
+100	llama-3.1-8b-instruct	0.9929
+100	llama-3.3-70b-instruct	0.9993
+100	ministral-8b-instruct-2410	0.9997
+100	mistral-7b-instruct-v0.2	0.9965
+100	mixtral-8x7b-instruct-v0.1	0.9947
+100	o3-mini	0.9999
+100	qwen1.5-72b-chat-8bit	0.9995
+100	text-bison-002	0.9992
+100	MACRO_AVG	0.9960
+105	deepseek-r1-distill-qwen-32b	0.9998
+105	falcon3-10b-instruct	0.9992
+105	gemini-1.5-pro	0.9689
+105	gemini-2.0-flash	0.9998
+105	gemini-pro	0.9851
+105	gemini-pro-paraphrase	0.9884
+105	gpt-3.5-turbo	0.9999
+105	gpt-4-turbo	1.0000
+105	gpt-4-turbo-paraphrase	0.9963
+105	gpt-4.5-preview	0.9980
+105	gpt-4o	0.9999
+105	gpt-4o-mini	0.9999
+105	llama-2-70b-chat	0.9974
+105	llama-2-7b-chat	0.9967
+105	llama-3.1-8b-instruct	0.9929
+105	llama-3.3-70b-instruct	0.9993
+105	ministral-8b-instruct-2410	0.9997
+105	mistral-7b-instruct-v0.2	0.9965
+105	mixtral-8x7b-instruct-v0.1	0.9947
+105	o3-mini	0.9999
+105	qwen1.5-72b-chat-8bit	0.9995
+105	text-bison-002	0.9992
+105	MACRO_AVG	0.9960
+110	deepseek-r1-distill-qwen-32b	0.9998
+110	falcon3-10b-instruct	0.9992
+110	gemini-1.5-pro	0.9689
+110	gemini-2.0-flash	0.9998
+110	gemini-pro	0.9851
+110	gemini-pro-paraphrase	0.9884
+110	gpt-3.5-turbo	0.9999
+110	gpt-4-turbo	1.0000
+110	gpt-4-turbo-paraphrase	0.9963
+110	gpt-4.5-preview	0.9980
+110	gpt-4o	0.9999
+110	gpt-4o-mini	0.9999
+110	llama-2-70b-chat	0.9974
+110	llama-2-7b-chat	0.9967
+110	llama-3.1-8b-instruct	0.9929
+110	llama-3.3-70b-instruct	0.9993
+110	ministral-8b-instruct-2410	0.9997
+110	mistral-7b-instruct-v0.2	0.9965
+110	mixtral-8x7b-instruct-v0.1	0.9947
+110	o3-mini	0.9999
+110	qwen1.5-72b-chat-8bit	0.9995
+110	text-bison-002	0.9992
+110	MACRO_AVG	0.9960
+115	deepseek-r1-distill-qwen-32b	0.9998
+115	falcon3-10b-instruct	0.9992
+115	gemini-1.5-pro	0.9689
+115	gemini-2.0-flash	0.9998
+115	gemini-pro	0.9851
+115	gemini-pro-paraphrase	0.9884
+115	gpt-3.5-turbo	0.9999
+115	gpt-4-turbo	1.0000
+115	gpt-4-turbo-paraphrase	0.9963
+115	gpt-4.5-preview	0.9980
+115	gpt-4o	0.9999
+115	gpt-4o-mini	0.9999
+115	llama-2-70b-chat	0.9974
+115	llama-2-7b-chat	0.9967
+115	llama-3.1-8b-instruct	0.9929
+115	llama-3.3-70b-instruct	0.9993
+115	ministral-8b-instruct-2410	0.9997
+115	mistral-7b-instruct-v0.2	0.9965
+115	mixtral-8x7b-instruct-v0.1	0.9947
+115	o3-mini	0.9999
+115	qwen1.5-72b-chat-8bit	0.9995
+115	text-bison-002	0.9992
+115	MACRO_AVG	0.9960
+120	deepseek-r1-distill-qwen-32b	0.9998
+120	falcon3-10b-instruct	0.9992
+120	gemini-1.5-pro	0.9689
+120	gemini-2.0-flash	0.9998
+120	gemini-pro	0.9851
+120	gemini-pro-paraphrase	0.9884
+120	gpt-3.5-turbo	0.9999
+120	gpt-4-turbo	1.0000
+120	gpt-4-turbo-paraphrase	0.9963
+120	gpt-4.5-preview	0.9980
+120	gpt-4o	0.9999
+120	gpt-4o-mini	0.9999
+120	llama-2-70b-chat	0.9974
+120	llama-2-7b-chat	0.9967
+120	llama-3.1-8b-instruct	0.9929
+120	llama-3.3-70b-instruct	0.9993
+120	ministral-8b-instruct-2410	0.9997
+120	mistral-7b-instruct-v0.2	0.9965
+120	mixtral-8x7b-instruct-v0.1	0.9947
+120	o3-mini	0.9999
+120	qwen1.5-72b-chat-8bit	0.9995
+120	text-bison-002	0.9992
+120	MACRO_AVG	0.9960
+125	deepseek-r1-distill-qwen-32b	0.9998
+125	falcon3-10b-instruct	0.9992
+125	gemini-1.5-pro	0.9689
+125	gemini-2.0-flash	0.9998
+125	gemini-pro	0.9851
+125	gemini-pro-paraphrase	0.9884
+125	gpt-3.5-turbo	0.9999
+125	gpt-4-turbo	1.0000
+125	gpt-4-turbo-paraphrase	0.9963
+125	gpt-4.5-preview	0.9980
+125	gpt-4o	0.9999
+125	gpt-4o-mini	0.9999
+125	llama-2-70b-chat	0.9974
+125	llama-2-7b-chat	0.9967
+125	llama-3.1-8b-instruct	0.9929
+125	llama-3.3-70b-instruct	0.9993
+125	ministral-8b-instruct-2410	0.9997
+125	mistral-7b-instruct-v0.2	0.9965
+125	mixtral-8x7b-instruct-v0.1	0.9947
+125	o3-mini	0.9999
+125	qwen1.5-72b-chat-8bit	0.9995
+125	text-bison-002	0.9992
+125	MACRO_AVG	0.9960
+130	deepseek-r1-distill-qwen-32b	0.9998
+130	falcon3-10b-instruct	0.9992
+130	gemini-1.5-pro	0.9689
+130	gemini-2.0-flash	0.9998
+130	gemini-pro	0.9851
+130	gemini-pro-paraphrase	0.9884
+130	gpt-3.5-turbo	0.9999
+130	gpt-4-turbo	1.0000
+130	gpt-4-turbo-paraphrase	0.9963
+130	gpt-4.5-preview	0.9980
+130	gpt-4o	0.9999
+130	gpt-4o-mini	0.9999
+130	llama-2-70b-chat	0.9974
+130	llama-2-7b-chat	0.9967
+130	llama-3.1-8b-instruct	0.9929
+130	llama-3.3-70b-instruct	0.9993
+130	ministral-8b-instruct-2410	0.9997
+130	mistral-7b-instruct-v0.2	0.9965
+130	mixtral-8x7b-instruct-v0.1	0.9947
+130	o3-mini	0.9999
+130	qwen1.5-72b-chat-8bit	0.9995
+130	text-bison-002	0.9992
+130	MACRO_AVG	0.9960
+135	deepseek-r1-distill-qwen-32b	0.9998
+135	falcon3-10b-instruct	0.9992
+135	gemini-1.5-pro	0.9689
+135	gemini-2.0-flash	0.9998
+135	gemini-pro	0.9851
+135	gemini-pro-paraphrase	0.9884
+135	gpt-3.5-turbo	0.9999
+135	gpt-4-turbo	1.0000
+135	gpt-4-turbo-paraphrase	0.9963
+135	gpt-4.5-preview	0.9980
+135	gpt-4o	0.9999
+135	gpt-4o-mini	0.9999
+135	llama-2-70b-chat	0.9974
+135	llama-2-7b-chat	0.9967
+135	llama-3.1-8b-instruct	0.9929
+135	llama-3.3-70b-instruct	0.9993
+135	ministral-8b-instruct-2410	0.9997
+135	mistral-7b-instruct-v0.2	0.9965
+135	mixtral-8x7b-instruct-v0.1	0.9947
+135	o3-mini	0.9999
+135	qwen1.5-72b-chat-8bit	0.9995
+135	text-bison-002	0.9992
+135	MACRO_AVG	0.9960
+140	deepseek-r1-distill-qwen-32b	0.9998
+140	falcon3-10b-instruct	0.9992
+140	gemini-1.5-pro	0.9689
+140	gemini-2.0-flash	0.9998
+140	gemini-pro	0.9851
+140	gemini-pro-paraphrase	0.9884
+140	gpt-3.5-turbo	0.9999
+140	gpt-4-turbo	1.0000
+140	gpt-4-turbo-paraphrase	0.9963
+140	gpt-4.5-preview	0.9980
+140	gpt-4o	0.9999
+140	gpt-4o-mini	0.9999
+140	llama-2-70b-chat	0.9974
+140	llama-2-7b-chat	0.9967
+140	llama-3.1-8b-instruct	0.9929
+140	llama-3.3-70b-instruct	0.9993
+140	ministral-8b-instruct-2410	0.9997
+140	mistral-7b-instruct-v0.2	0.9965
+140	mixtral-8x7b-instruct-v0.1	0.9947
+140	o3-mini	0.9999
+140	qwen1.5-72b-chat-8bit	0.9995
+140	text-bison-002	0.9992
+140	MACRO_AVG	0.9960
+145	deepseek-r1-distill-qwen-32b	0.9998
+145	falcon3-10b-instruct	0.9992
+145	gemini-1.5-pro	0.9689
+145	gemini-2.0-flash	0.9998
+145	gemini-pro	0.9851
+145	gemini-pro-paraphrase	0.9884
+145	gpt-3.5-turbo	0.9999
+145	gpt-4-turbo	1.0000
+145	gpt-4-turbo-paraphrase	0.9963
+145	gpt-4.5-preview	0.9980
+145	gpt-4o	0.9999
+145	gpt-4o-mini	0.9999
+145	llama-2-70b-chat	0.9974
+145	llama-2-7b-chat	0.9967
+145	llama-3.1-8b-instruct	0.9929
+145	llama-3.3-70b-instruct	0.9993
+145	ministral-8b-instruct-2410	0.9997
+145	mistral-7b-instruct-v0.2	0.9965
+145	mixtral-8x7b-instruct-v0.1	0.9947
+145	o3-mini	0.9999
+145	qwen1.5-72b-chat-8bit	0.9995
+145	text-bison-002	0.9992
+145	MACRO_AVG	0.9960
+150	deepseek-r1-distill-qwen-32b	0.9998
+150	falcon3-10b-instruct	0.9992
+150	gemini-1.5-pro	0.9689
+150	gemini-2.0-flash	0.9998
+150	gemini-pro	0.9851
+150	gemini-pro-paraphrase	0.9884
+150	gpt-3.5-turbo	0.9999
+150	gpt-4-turbo	1.0000
+150	gpt-4-turbo-paraphrase	0.9963
+150	gpt-4.5-preview	0.9980
+150	gpt-4o	0.9999
+150	gpt-4o-mini	0.9999
+150	llama-2-70b-chat	0.9974
+150	llama-2-7b-chat	0.9967
+150	llama-3.1-8b-instruct	0.9929
+150	llama-3.3-70b-instruct	0.9993
+150	ministral-8b-instruct-2410	0.9997
+150	mistral-7b-instruct-v0.2	0.9965
+150	mixtral-8x7b-instruct-v0.1	0.9947
+150	o3-mini	0.9999
+150	qwen1.5-72b-chat-8bit	0.9995
+150	text-bison-002	0.9992
+150	MACRO_AVG	0.9960
+155	deepseek-r1-distill-qwen-32b	0.9998
+155	falcon3-10b-instruct	0.9992
+155	gemini-1.5-pro	0.9689
+155	gemini-2.0-flash	0.9998
+155	gemini-pro	0.9851
+155	gemini-pro-paraphrase	0.9884
+155	gpt-3.5-turbo	0.9999
+155	gpt-4-turbo	1.0000
+155	gpt-4-turbo-paraphrase	0.9963
+155	gpt-4.5-preview	0.9980
+155	gpt-4o	0.9999
+155	gpt-4o-mini	0.9999
+155	llama-2-70b-chat	0.9974
+155	llama-2-7b-chat	0.9967
+155	llama-3.1-8b-instruct	0.9929
+155	llama-3.3-70b-instruct	0.9993
+155	ministral-8b-instruct-2410	0.9997
+155	mistral-7b-instruct-v0.2	0.9965
+155	mixtral-8x7b-instruct-v0.1	0.9947
+155	o3-mini	0.9999
+155	qwen1.5-72b-chat-8bit	0.9995
+155	text-bison-002	0.9992
+155	MACRO_AVG	0.9960
+160	deepseek-r1-distill-qwen-32b	0.9998
+160	falcon3-10b-instruct	0.9992
+160	gemini-1.5-pro	0.9689
+160	gemini-2.0-flash	0.9998
+160	gemini-pro	0.9851
+160	gemini-pro-paraphrase	0.9884
+160	gpt-3.5-turbo	0.9999
+160	gpt-4-turbo	1.0000
+160	gpt-4-turbo-paraphrase	0.9963
+160	gpt-4.5-preview	0.9980
+160	gpt-4o	0.9999
+160	gpt-4o-mini	0.9999
+160	llama-2-70b-chat	0.9974
+160	llama-2-7b-chat	0.9967
+160	llama-3.1-8b-instruct	0.9929
+160	llama-3.3-70b-instruct	0.9993
+160	ministral-8b-instruct-2410	0.9997
+160	mistral-7b-instruct-v0.2	0.9965
+160	mixtral-8x7b-instruct-v0.1	0.9947
+160	o3-mini	0.9999
+160	qwen1.5-72b-chat-8bit	0.9995
+160	text-bison-002	0.9992
+160	MACRO_AVG	0.9960