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 Country%3Amorocco C5 - Run 28d2957...

Global Dialogues GD4 - Morocco (5 context Qs)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

AI Safety & Robustness

Interpersonal & Social Skill Modeling

Emotional Intelligence

Social interaction

Best Models (Coverage)

1.GPT 4.1 Mini
65.9%
2.Claude Sonnet 4
65.8%
3.Claude Haiku 4.5
65.8%
4.Mistral Medium 3
65.7%
5.GPT 4o Mini
65.5%

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 65.8%	2nd 65.8%	11th 63.0%	13th 60.3%	9th 63.6%	7th 64.5%	4th 65.7%	10th 63.2%	1st 65.9%	12th 60.9%	5th 65.5%	6th 65.4%	8th 64.1%
54.2%		64%	64%	69%	68%	24%	44%	55%	66%	60%	53%	48%	45%	44%
64.0%		62%	62%	62%	75%	44%	59%	75%	84%	69%	51%	65%	58%	66%
78.5%		84%	75%	92%	82%	68%	79%	79%	83%	77%	74%	79%	74%	75%
52.8%		55%	52%	56%	46%	53%	59%	54%	39%	51%	58%	50%	56%	57%
57.6%		57%	55%	55%	59%	54%	59%	64%	52%	59%	66%	48%	61%	60%
72.5%		78%	77%	84%	54%	74%	72%	80%	84%	72%	70%	81%	75%	41%
53.5%		67%	67%	74%	63%	46%	52%	47%	47%	52%	41%	47%	52%	41%
54.3%		56%	58%	58%	55%	52%	52%	52%	59%	39%	61%	53%	55%	56%
65.2%		68%	60%	53%	65%	62%	74%	73%	57%	68%	62%	71%	68%	66%
57.3%		60%	62%	65%	51%	72%	52%	44%	29%	62%	69%	66%	75%	38%
78.1%		78%	75%	80%	80%	81%	75%	80%	60%	75%	85%	76%	85%	85%
72.7%		84%	76%	61%	68%	79%	70%	71%	65%	80%	53%	80%	79%	79%
74.4%		79%	82%	62%	62%	77%	74%	76%	62%	77%	76%	78%	81%	81%
60.6%		74%	85%	64%	53%	46%	58%	58%	62%	62%	42%	58%	64%	62%
51.5%		45%	48%	37%	22%	50%	66%	54%	56%	56%	40%	71%	57%	67%
62.6%		60%	65%	67%	58%	59%	65%	71%	67%	58%	57%	61%	66%	60%
71.5%		75%	66%	74%	70%	72%	74%	77%	64%	72%	64%	77%	67%	77%
64.7%		70%	63%	55%	64%	64%	65%	66%	50%	80%	63%	74%	72%	55%
73.5%		79%	78%	71%	76%	77%	70%	71%	69%	77%	67%	74%	69%	77%
75.8%		89%	83%	86%	68%	54%	75%	72%	87%	81%	58%	81%	83%	69%
73.5%		78%	75%	53%	80%	76%	76%	75%	61%	75%	75%	75%	83%	73%
77.0%		76%	72%	79%	80%	79%	70%	72%	82%	79%	79%	79%	76%	78%
55.1%		57%	60%	63%	38%	61%	56%	61%	63%	49%	56%	61%	54%	37%
20.9%		24%	22%	22%	26%	17%	22%	32%	27%	9%	18%	13%	18%	22%
52.8%		61%	49%	49%	43%	56%	47%	61%	49%	49%	58%	57%	55%	53%
74.5%		80%	73%	75%	76%	76%	72%	71%	72%	72%	67%	78%	77%	79%
80.8%		85%	80%	75%	79%	86%	85%	75%	75%	85%	75%	79%	80%	91%
68.3%		70%	63%	68%	63%	61%	69%	69%	56%	76%	76%	73%	72%	72%
72.6%		79%	75%	74%	69%	75%	69%	68%	73%	75%	70%	73%	73%	71%
74.0%		74%	71%	68%	68%	66%	80%	78%	74%	78%	73%	76%	76%	80%
66.5%		70%	77%	65%	59%	73%	72%	69%	65%	70%	69%	64%	60%	52%
62.0%		56%	88%	78%	56%	43%	56%	57%	80%	68%	48%	48%	52%	76%
57.9%		65%	54%	70%	63%	44%	57%	70%	57%	62%	49%	64%	51%	47%
31.4%		28%	33%	23%	53%	32%	33%	33%	41%	28%	25%	28%	23%	28%
60.0%		56%	61%	61%	58%	55%	59%	61%	61%	63%	62%	61%	63%	59%
49.8%		54%	50%	55%	46%	53%	46%	45%	55%	46%	51%	51%	52%	44%
71.2%		70%	81%	79%	25%	68%	74%	79%	74%	74%	73%	74%	75%	79%
57.2%		42%	55%	48%	53%	67%	43%	44%	49%	45%	77%	70%	77%	73%
72.8%		83%	85%	81%	45%	80%	78%	75%	66%	77%	70%	79%	80%	47%
20.8%		15%	22%	22%	22%	28%	16%	15%	16%	22%	22%	37%	17%	16%
68.3%		67%	65%	72%	61%	66%	75%	80%	76%	62%	62%	62%	71%	69%
57.0%		58%	57%	71%	35%	71%	52%	56%	41%	55%	51%	50%	79%	65%
56.8%		54%	58%	61%	66%	58%	43%	49%	70%	54%	53%	67%	51%	54%
63.1%		59%	63%	47%	71%	74%	72%	71%	55%	54%	72%	56%	63%	63%
77.2%		78%	74%	71%	82%	79%	78%	74%	78%	75%	74%	62%	87%	91%
73.0%		85%	79%	80%	70%	55%	74%	71%	79%	77%	50%	69%	76%	84%
62.5%		62%	63%	63%	66%	62%	68%	66%	45%	64%	70%	54%	71%	58%
87.1%		98%	86%	75%	89%	81%	89%	82%	98%	98%	82%	92%	89%	73%
79.8%		76%	88%	87%	74%	88%	69%	82%	81%	78%	77%	74%	83%	81%
67.6%		71%	74%	71%	63%	67%	68%	74%	72%	62%	64%	65%	62%	66%
59.2%		60%	57%	49%	66%	63%	53%	55%	61%	64%	48%	62%	64%	68%
47.2%		52%	51%	51%	44%	41%	46%	54%	60%	38%	42%	55%	39%	40%
72.5%		82%	75%	71%	70%	57%	64%	82%	82%	75%	68%	77%	71%	68%
44.3%		48%	42%	40%	49%	40%	38%	48%	46%	45%	40%	45%	52%	43%
72.6%		77%	69%	56%	77%	79%	84%	77%	74%	72%	69%	70%	68%	72%
83.4%		91%	92%	62%	48%	91%	90%	90%	71%	88%	92%	92%	93%	84%
49.2%		52%	59%	52%	59%	52%	61%	52%	52%	52%	37%	39%	34%	39%
64.8%		69%	67%	67%	49%	69%	63%	64%	50%	66%	65%	68%	73%	73%
45.7%		40%	46%	62%	66%	42%	46%	46%	53%	40%	34%	40%	33%	46%
59.9%		62%	58%	58%	46%	77%	62%	51%	43%	66%	67%	51%	75%	63%
62.2%		64%	64%	54%	54%	62%	71%	61%	56%	56%	69%	69%	60%	69%
62.8%		64%	66%	61%	67%	41%	67%	65%	73%	58%	66%	70%	67%	52%
72.1%		73%	71%	65%	64%	69%	58%	65%	71%	70%	80%	82%	87%	82%
57.9%		58%	60%	62%	46%	60%	56%	57%	62%	56%	58%	54%	69%	55%
73.7%		91%	87%	75%	23%	93%	87%	90%	72%	86%	56%	78%	74%	46%
71.6%		76%	76%	68%	58%	78%	75%	67%	70%	71%	75%	72%	74%	71%
74.5%		74%	73%	78%	92%	65%	82%	76%	93%	76%	70%	68%	56%	65%
70.5%		79%	81%	67%	62%	83%	66%	73%	73%	81%	48%	65%	66%	73%
44.5%		38%	43%	37%	44%	43%	41%	48%	48%	47%	47%	43%	56%	43%
63.8%		77%	61%	67%	51%	58%	63%	51%	63%	78%	44%	75%	75%	67%
63.2%		61%	70%	54%	38%	74%	61%	51%	73%	70%	75%	60%	64%	71%
72.4%		80%	79%	69%	64%	72%	74%	65%	66%	79%	78%	72%	74%	69%
69.2%		70%	72%	69%	65%	67%	68%	69%	65%	68%	72%	74%	71%	69%
58.4%		50%	64%	56%	71%	48%	64%	70%	71%	42%	52%	61%	51%	59%
66.5%		66%	62%	63%	46%	72%	69%	64%	64%	74%	70%	70%	73%	71%
74.6%		75%	72%	86%	76%	65%	77%	75%	76%	75%	72%	77%	72%	72%
52.7%		55%	53%	53%	47%	64%	54%	53%	34%	53%	49%	60%	57%	53%
75.2%		71%	75%	74%	74%	59%	77%	79%	82%	79%	78%	78%	72%	79%
77.2%		82%	80%	86%	54%	86%	75%	84%	67%	78%	80%	88%	84%	59%
64.4%		64%	65%	51%	65%	66%	69%	70%	64%	65%	60%	57%	63%	78%
76.1%		83%	65%	65%	86%	70%	65%	70%	83%	87%	63%	90%	69%	93%
75.2%		81%	68%	63%	79%	82%	70%	75%	82%	75%	52%	68%	91%	91%
78.2%		80%	80%	69%	64%	88%	76%	83%	63%	80%	84%	81%	86%	82%
86.1%		89%	82%	82%	80%	85%	83%	91%	82%	91%	96%	96%	80%	82%
72.7%		81%	77%	55%	74%	71%	72%	80%	60%	74%	67%	78%	78%	78%
75.2%		76%	75%	77%	60%	80%	73%	75%	77%	76%	77%	82%	82%	67%
51.9%		44%	50%	50%	55%	56%	56%	56%	53%	56%	37%	44%	58%	60%
63.6%		63%	62%	46%	62%	71%	63%	58%	46%	74%	67%	67%	74%	74%
80.4%		76%	90%	87%	78%	88%	87%	86%	86%	82%	50%	64%	83%	88%
72.7%		72%	80%	73%	80%	77%	81%	81%	64%	73%	42%	69%	73%	80%
44.2%		37%	43%	42%	45%	43%	48%	47%	39%	43%	41%	51%	48%	47%
38.2%		33%	79%	31%	24%	21%	37%	51%	51%	77%	27%	27%	27%	11%
59.5%		64%	68%	72%	22%	57%	56%	58%	74%	63%	53%	76%	54%	56%
62.3%		59%	61%	61%	57%	71%	62%	64%	46%	64%	59%	66%	65%	75%
24.7%		24%	23%	22%	28%	36%	31%	22%	9%	22%	28%	18%	27%	31%
64.5%		59%	67%	57%	63%	61%	68%	67%	67%	64%	64%	63%	64%	75%
66.5%		67%	60%	64%	38%	76%	63%	55%	58%	74%	74%	83%	79%	74%
73.3%		76%	77%	77%	51%	65%	77%	77%	76%	75%	72%	77%	76%	77%
62.7%		59%	59%	63%	87%	38%	59%	71%	87%	59%	54%	71%	45%	63%
58.2%		61%	61%	50%	53%	51%	59%	59%	59%	70%	51%	51%	53%	79%
52.3%		51%	54%	66%	41%	57%	49%	50%	54%	54%	52%	55%	43%	54%
80.0%		83%	80%	67%	73%	80%	86%	91%	70%	86%	80%	80%	86%	78%
58.5%		57%	56%	67%	56%	56%	56%	56%	61%	56%	63%	64%	56%	57%
84.2%		80%	85%	69%	93%	75%	89%	94%	70%	82%	93%	84%	88%	93%
77.3%		86%	91%	75%	68%	78%	79%	79%	71%	80%	65%	76%	78%	79%
61.3%		45%	46%	57%	60%	59%	70%	68%	66%	66%	68%	67%	59%	66%
72.8%		77%	58%	58%	80%	76%	80%	74%	77%	79%	72%	75%	73%	68%
41.1%		42%	46%	38%	48%	28%	39%	51%	54%	46%	28%	38%	32%	44%
62.3%		62%	60%	60%	67%	61%	60%	79%	56%	69%	41%	71%	62%	62%
68.2%		63%	65%	75%	80%	69%	72%	71%	81%	66%	59%	59%	63%	63%
74.1%		75%	75%	72%	78%	74%	72%	75%	74%	76%	71%	76%	75%	70%
62.9%		69%	65%	60%	68%	54%	66%	66%	62%	68%	67%	69%	54%	50%
68.0%		64%	71%	68%	67%	71%	76%	71%	63%	76%	67%	64%	59%	67%
75.2%		80%	77%	79%	58%	82%	78%	78%	61%	84%	75%	83%	81%	61%
49.3%		39%	38%	48%	65%	69%	54%	54%	37%	48%	32%	65%	49%	43%
53.7%		56%	48%	48%	53%	63%	46%	57%	48%	57%	53%	53%	59%	57%