DTeval

A Collective Intelligence Project

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

Analysis: Gd4 C5 Dtef Global Dialogues Gd4 Religion%3Ajudaism C5 - Run 8e9be62...

Global Dialogues GD4 - Judaism (5 context Qs)

DTEF: Predict response distributions for Judaism. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Social interaction

AI Safety & Robustness

Economic Disruption & Reskilling Advice

Mental Health & Crisis Support

Demographic Processes

Best Models (Coverage)

1.Claude Sonnet 4
72.5%
2.Claude Sonnet 4.5
72.0%
3.Claude Haiku 4.5
71.6%
4.GPT 4.1 Mini
71.5%
5.GPT 4.1
71.3%

Select Prompt:

Macro Coverage Overview

Average key point coverage extent for each model across all prompts.

Pro Tip

Click on any result cell to open a detailed view.

Advanced view

Highlight best performers

Sort prompts by

Sort models by

Color Scale - Simplified View (Avg. Coverage)

Perfect

Excellent

Good

Fair

Poor

Bad

Not Met

	Prompts vs. Models	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 71.6%	1st 72.5%	2nd 72.0%	13th 64.7%	11th 67.7%	6th 70.9%	10th 68.7%	5th 71.3%	4th 71.5%	12th 67.1%	7th 70.1%	8th 69.8%	9th 68.9%
59.8%		70%	64%	67%	62%	44%	61%	64%	57%	56%	50%	57%	66%	60%
73.9%		73%	81%	81%	72%	53%	73%	78%	78%	80%	76%	74%	70%	72%
78.0%		75%	81%	81%	69%	77%	82%	75%	84%	79%	76%	81%	73%	81%
67.1%		70%	78%	79%	56%	64%	68%	57%	67%	73%	63%	65%	59%	73%
62.2%		75%	63%	61%	57%	51%	62%	68%	67%	62%	53%	58%	66%	66%
73.5%		77%	74%	73%	64%	67%	71%	79%	79%	74%	71%	82%	83%	62%
47.1%		56%	57%	64%	63%	42%	45%	46%	36%	50%	27%	32%	48%	46%
64.5%		70%	59%	50%	36%	79%	64%	61%	61%	73%	74%	73%	69%	70%
75.5%		76%	84%	75%	58%	77%	80%	52%	85%	80%	79%	76%	84%	76%
70.8%		74%	73%	55%	55%	85%	60%	54%	60%	78%	82%	82%	82%	81%
75.3%		75%	77%	82%	74%	68%	77%	77%	82%	73%	71%	71%	73%	79%
78.1%		76%	87%	82%	71%	84%	73%	75%	84%	87%	57%	90%	71%	78%
55.1%		59%	55%	55%	55%	55%	56%	61%	52%	56%	42%	55%	59%	56%
73.0%		77%	77%	73%	75%	73%	84%	73%	73%	73%	52%	73%	73%	73%
56.2%		53%	70%	63%	22%	69%	58%	56%	60%	59%	44%	61%	57%	59%
80.0%		88%	86%	73%	65%	76%	88%	83%	66%	86%	79%	87%	81%	82%
62.3%		58%	48%	54%	59%	64%	63%	64%	69%	58%	84%	68%	63%	58%
81.0%		84%	80%	72%	78%	76%	80%	82%	75%	86%	85%	94%	86%	75%
73.2%		68%	86%	72%	67%	82%	66%	70%	75%	77%	57%	81%	73%	78%
84.1%		80%	90%	90%	83%	69%	93%	81%	93%	75%	83%	89%	90%	77%
77.2%		77%	79%	71%	77%	72%	73%	80%	78%	78%	77%	82%	82%	78%
61.0%		65%	58%	70%	56%	67%	58%	65%	66%	63%	51%	62%	54%	58%
71.4%		72%	73%	75%	63%	69%	69%	85%	85%	63%	73%	84%	74%	43%
48.8%		56%	70%	75%	64%	28%	47%	52%	62%	36%	42%	31%	35%	36%
68.4%		69%	75%	80%	73%	66%	73%	66%	80%	62%	61%	55%	61%	68%
66.8%		73%	65%	71%	68%	62%	67%	61%	67%	69%	74%	65%	69%	58%
60.8%		56%	54%	63%	62%	62%	59%	63%	64%	67%	52%	65%	64%	60%
74.5%		82%	77%	73%	61%	63%	80%	77%	80%	79%	78%	68%	76%	74%
74.2%		77%	78%	77%	72%	70%	79%	74%	78%	75%	75%	65%	66%	78%
83.5%		87%	83%	79%	69%	81%	86%	90%	86%	90%	72%	90%	86%	86%
81.8%		85%	86%	85%	59%	85%	81%	86%	82%	86%	87%	80%	88%	74%
68.5%		73%	44%	49%	64%	82%	75%	69%	77%	72%	93%	78%	71%	44%
77.0%		75%	80%	89%	84%	70%	78%	75%	94%	78%	64%	70%	66%	78%
67.6%		73%	71%	66%	75%	49%	66%	82%	77%	67%	64%	68%	61%	60%
76.3%		89%	78%	71%	75%	72%	90%	57%	51%	80%	76%	76%	84%	93%
64.1%		70%	65%	65%	70%	67%	65%	62%	73%	58%	63%	65%	62%	48%
59.5%		54%	71%	73%	59%	65%	50%	57%	59%	65%	59%	56%	56%	49%
68.8%		67%	81%	80%	63%	59%	55%	58%	91%	81%	72%	63%	51%	73%
66.2%		68%	62%	62%	71%	66%	61%	68%	64%	70%	71%	67%	76%	54%
45.5%		43%	43%	51%	36%	49%	42%	37%	42%	54%	49%	47%	44%	54%
66.6%		65%	77%	77%	77%	44%	67%	69%	78%	64%	53%	60%	58%	77%
74.7%		78%	78%	78%	68%	78%	78%	61%	68%	78%	81%	67%	78%	80%
54.7%		57%	53%	59%	49%	49%	55%	58%	63%	55%	55%	55%	44%	59%
62.2%		67%	68%	68%	73%	59%	73%	64%	54%	52%	60%	62%	54%	55%
66.7%		67%	72%	72%	73%	72%	70%	51%	78%	55%	57%	58%	72%	70%
76.1%		52%	77%	77%	72%	88%	76%	82%	76%	67%	85%	71%	73%	93%
70.3%		73%	64%	53%	66%	80%	64%	74%	64%	74%	83%	76%	76%	67%
92.8%		95%	100%	84%	87%	91%	100%	100%	100%	100%	87%	84%	100%	78%
74.5%		72%	77%	81%	73%	81%	63%	77%	74%	74%	69%	80%	72%	75%
62.8%		51%	62%	65%	71%	64%	62%	60%	62%	60%	55%	70%	75%	60%
75.2%		77%	88%	71%	76%	83%	69%	65%	88%	65%	57%	84%	80%	74%
53.9%		54%	60%	60%	34%	60%	54%	60%	64%	52%	43%	50%	53%	57%
65.5%		65%	67%	70%	75%	60%	61%	67%	64%	66%	77%	65%	58%	57%
60.9%		68%	59%	63%	83%	53%	63%	64%	47%	59%	64%	54%	56%	59%
83.5%		77%	83%	88%	78%	89%	83%	87%	86%	90%	80%	83%	93%	69%
80.2%		85%	83%	74%	88%	74%	88%	86%	80%	87%	60%	80%	72%	86%
55.3%		48%	78%	62%	68%	38%	70%	57%	66%	57%	20%	57%	48%	50%
74.0%		78%	76%	76%	74%	65%	67%	72%	72%	82%	68%	76%	78%	78%
61.9%		63%	65%	82%	82%	41%	63%	67%	80%	61%	49%	54%	41%	57%
72.7%		72%	86%	76%	67%	81%	78%	62%	60%	69%	78%	73%	77%	66%
63.4%		56%	69%	74%	37%	80%	68%	53%	40%	53%	78%	74%	68%	74%
71.5%		72%	71%	71%	70%	61%	71%	79%	71%	68%	78%	70%	73%	74%
67.2%		77%	57%	59%	59%	59%	50%	66%	63%	72%	90%	79%	69%	74%
74.8%		81%	74%	72%	54%	78%	75%	78%	81%	75%	79%	81%	77%	68%
69.1%		70%	67%	70%	74%	66%	76%	70%	71%	67%	72%	77%	70%	48%
78.5%		85%	89%	80%	62%	69%	89%	86%	77%	81%	68%	78%	81%	75%
80.1%		83%	91%	83%	64%	85%	83%	61%	80%	83%	87%	82%	86%	73%
64.8%		73%	73%	63%	63%	72%	66%	58%	63%	69%	47%	61%	65%	70%
60.1%		59%	51%	51%	56%	57%	58%	61%	61%	69%	57%	67%	67%	67%
89.2%		89%	87%	87%	90%	87%	95%	84%	78%	89%	95%	97%	87%	95%
72.5%		72%	70%	67%	63%	72%	67%	64%	79%	67%	79%	75%	86%	82%
52.5%		58%	58%	58%	20%	56%	60%	43%	53%	55%	55%	51%	63%	53%
83.5%		87%	93%	86%	65%	80%	82%	86%	71%	85%	87%	89%	86%	89%
59.0%		66%	63%	67%	20%	73%	73%	68%	62%	54%	42%	57%	52%	70%
70.8%		66%	80%	79%	68%	73%	75%	48%	68%	80%	75%	57%	70%	81%
77.1%		76%	81%	81%	54%	82%	83%	76%	57%	80%	86%	81%	84%	81%
63.1%		68%	77%	77%	56%	69%	59%	52%	58%	59%	56%	63%	70%	56%
83.8%		85%	72%	86%	66%	77%	84%	84%	86%	90%	87%	92%	91%	90%
66.8%		69%	62%	65%	65%	64%	65%	71%	75%	64%	69%	65%	64%	70%
72.9%		72%	72%	74%	71%	78%	77%	74%	77%	66%	65%	72%	73%	77%
82.8%		92%	78%	71%	79%	75%	80%	79%	93%	93%	88%	85%	75%	88%
81.2%		85%	80%	83%	82%	80%	82%	80%	92%	83%	59%	87%	80%	83%
79.5%		86%	85%	74%	64%	82%	86%	77%	73%	86%	81%	80%	83%	76%
71.5%		73%	62%	67%	69%	85%	53%	76%	76%	76%	71%	66%	77%	78%
85.2%		80%	93%	87%	71%	84%	93%	93%	93%	87%	91%	88%	85%	62%
84.6%		86%	82%	86%	80%	82%	85%	86%	87%	86%	87%	87%	86%	80%
66.4%		64%	68%	74%	63%	64%	73%	64%	61%	73%	54%	67%	65%	73%
70.7%		72%	67%	73%	60%	66%	69%	65%	73%	69%	77%	82%	73%	73%
68.3%		75%	82%	80%	82%	59%	75%	62%	69%	63%	49%	51%	62%	79%
70.8%		83%	70%	70%	62%	57%	70%	70%	75%	81%	66%	68%	81%	67%
77.4%		72%	72%	78%	73%	67%	78%	88%	78%	78%	81%	79%	80%	82%
45.7%		84%	82%	83%	36%	24%	45%	44%	56%	53%	33%	24%	30%	0%
68.9%		74%	69%	77%	29%	69%	69%	69%	76%	69%	77%	82%	66%	70%
76.7%		79%	75%	71%	82%	69%	79%	83%	79%	83%	77%	72%	72%	76%
68.4%		78%	71%	71%	57%	74%	81%	56%	61%	69%	66%	67%	69%	69%
75.2%		69%	76%	84%	84%	80%	78%	60%	74%	84%	77%	72%	78%	61%
60.8%		58%	59%	72%	31%	66%	60%	51%	50%	68%	73%	70%	68%	64%
85.9%		89%	84%	89%	53%	86%	94%	79%	66%	92%	94%	100%	91%	100%
78.0%		84%	88%	76%	65%	65%	91%	84%	72%	91%	62%	82%	71%	83%
67.6%		76%	73%	77%	69%	60%	68%	57%	73%	73%	53%	57%	66%	77%
67.1%		69%	78%	79%	25%	69%	76%	77%	84%	72%	56%	64%	54%	69%
73.3%		76%	72%	71%	76%	76%	75%	73%	72%	76%	63%	75%	77%	71%
64.3%		65%	64%	65%	65%	69%	61%	59%	61%	64%	65%	68%	61%	69%
64.3%		61%	56%	60%	61%	47%	56%	61%	79%	79%	79%	79%	56%	62%
74.6%		75%	79%	87%	76%	75%	76%	71%	83%	72%	66%	72%	69%	69%
57.8%		56%	57%	64%	47%	41%	70%	56%	59%	61%	52%	56%	62%	70%
64.6%		79%	60%	44%	68%	49%	70%	81%	74%	72%	55%	54%	65%	69%
61.1%		67%	64%	64%	73%	39%	62%	68%	79%	68%	35%	58%	53%	64%
54.0%		57%	57%	51%	55%	68%	54%	57%	46%	50%	43%	58%	56%	50%
79.2%		79%	86%	83%	70%	73%	76%	82%	70%	83%	86%	82%	80%	79%
67.5%		58%	64%	69%	56%	73%	69%	63%	75%	69%	71%	67%	71%	72%
68.0%		76%	68%	73%	71%	63%	67%	73%	74%	68%	73%	58%	60%	60%
67.1%		66%	70%	74%	82%	51%	74%	69%	82%	78%	54%	52%	66%	54%
81.0%		76%	92%	83%	89%	85%	86%	69%	71%	80%	73%	83%	84%	82%
65.8%		56%	71%	71%	71%	71%	71%	76%	76%	61%	46%	68%	61%	56%
59.5%		61%	64%	56%	59%	65%	56%	47%	57%	66%	62%	56%	67%	58%