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%3Apakistan C5 - Run 1d5c164...

Global Dialogues GD4 - Pakistan (5 context Qs)

DTEF: Predict response distributions for Pakistan. 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

Interpersonal & Social Skill Modeling

Sociology & Anthropology

Best Models (Coverage)

1.Claude Sonnet 4
74.4%
2.Claude Haiku 4.5
72.9%
3.GPT 4.1 Mini
72.6%
4.Llama 4 Maverick
72.5%
5.GPT 4.1
72.5%

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		2nd 72.9%	1st 74.4%	7th 70.5%	13th 66.5%	12th 67.2%	5th 72.5%	6th 72.3%	4th 72.5%	3rd 72.6%	11th 67.3%	8th 70.3%	10th 68.9%	9th 69.0%
57.8%		61%	69%	77%	69%	43%	57%	57%	48%	51%	60%	47%	56%	56%
73.8%		78%	79%	83%	77%	50%	72%	89%	77%	71%	60%	72%	69%	83%
76.2%		73%	78%	78%	75%	78%	78%	75%	73%	82%	71%	74%	71%	84%
83.6%		88%	89%	78%	82%	84%	81%	78%	79%	84%	94%	89%	84%	77%
56.0%		57%	63%	62%	60%	35%	56%	62%	68%	63%	54%	45%	45%	58%
69.1%		78%	79%	79%	64%	65%	70%	72%	74%	73%	56%	71%	73%	44%
74.9%		81%	82%	82%	80%	60%	84%	71%	67%	76%	73%	65%	81%	72%
74.9%		84%	78%	86%	43%	70%	79%	76%	74%	72%	76%	85%	80%	71%
73.4%		78%	60%	60%	79%	75%	78%	78%	69%	77%	69%	81%	75%	75%
75.8%		85%	84%	82%	88%	78%	81%	69%	83%	84%	77%	69%	69%	37%
80.7%		88%	88%	79%	50%	84%	82%	82%	79%	85%	84%	84%	88%	76%
66.2%		70%	66%	66%	67%	66%	67%	70%	68%	73%	54%	66%	64%	64%
81.6%		84%	88%	85%	59%	90%	88%	68%	70%	87%	84%	88%	83%	87%
52.8%		65%	71%	65%	27%	40%	54%	51%	51%	55%	32%	51%	55%	70%
58.0%		60%	58%	59%	42%	53%	66%	68%	59%	55%	63%	67%	50%	54%
60.6%		67%	61%	63%	74%	50%	67%	70%	69%	59%	47%	58%	45%	58%
65.2%		70%	67%	70%	77%	61%	64%	63%	68%	66%	56%	58%	57%	70%
74.5%		68%	79%	72%	77%	79%	81%	64%	78%	68%	79%	72%	78%	73%
84.9%		90%	83%	74%	95%	94%	83%	83%	76%	77%	83%	97%	86%	83%
62.8%		59%	57%	58%	67%	57%	70%	67%	72%	58%	70%	63%	62%	57%
72.9%		81%	70%	69%	71%	62%	76%	71%	62%	76%	71%	82%	76%	81%
85.8%		85%	90%	91%	79%	94%	72%	90%	87%	90%	78%	87%	85%	88%
61.7%		75%	70%	55%	24%	68%	68%	75%	63%	70%	66%	75%	52%	41%
41.6%		38%	45%	42%	54%	24%	45%	58%	54%	37%	47%	34%	24%	39%
68.7%		69%	72%	73%	70%	68%	75%	63%	73%	68%	74%	67%	56%	65%
81.5%		89%	78%	89%	75%	89%	76%	74%	80%	78%	79%	87%	90%	76%
77.7%		82%	83%	71%	79%	79%	78%	74%	76%	83%	78%	76%	78%	73%
72.5%		76%	81%	91%	74%	50%	82%	91%	74%	70%	77%	68%	56%	53%
67.2%		71%	74%	75%	51%	78%	67%	67%	74%	69%	63%	58%	63%	64%
68.7%		70%	72%	60%	64%	64%	68%	65%	65%	75%	74%	69%	72%	75%
79.0%		91%	92%	74%	51%	92%	91%	92%	79%	79%	66%	77%	92%	51%
77.2%		90%	81%	87%	54%	59%	89%	84%	87%	76%	70%	72%	72%	83%
62.6%		70%	68%	70%	64%	55%	67%	71%	75%	63%	69%	42%	43%	57%
69.2%		75%	71%	75%	80%	51%	76%	81%	79%	72%	57%	64%	50%	68%
69.5%		80%	82%	48%	78%	59%	72%	66%	70%	63%	63%	71%	73%	79%
76.6%		83%	82%	64%	41%	85%	84%	84%	82%	84%	82%	75%	84%	66%
78.2%		84%	71%	80%	84%	73%	81%	81%	67%	75%	81%	80%	82%	78%
68.1%		67%	67%	58%	65%	63%	65%	67%	80%	65%	70%	84%	68%	66%
68.2%		73%	72%	58%	64%	73%	70%	54%	76%	73%	72%	65%	73%	63%
58.8%		51%	54%	54%	54%	66%	39%	56%	52%	58%	84%	72%	69%	56%
67.0%		70%	68%	77%	63%	56%	65%	71%	82%	76%	53%	68%	54%	68%
77.7%		79%	79%	73%	65%	89%	81%	73%	69%	77%	93%	66%	88%	78%
70.4%		72%	78%	85%	68%	58%	71%	69%	76%	60%	84%	58%	56%	80%
64.8%		53%	66%	53%	65%	60%	72%	72%	65%	58%	75%	75%	66%	63%
79.2%		87%	89%	83%	80%	72%	78%	84%	75%	90%	75%	85%	72%	59%
74.4%		64%	80%	76%	71%	64%	85%	78%	80%	76%	65%	71%	73%	84%
55.9%		61%	51%	51%	55%	59%	56%	59%	51%	53%	70%	51%	62%	48%
90.4%		85%	77%	77%	95%	92%	90%	100%	95%	100%	95%	83%	100%	86%
84.6%		86%	90%	87%	73%	87%	94%	84%	83%	81%	84%	78%	78%	95%
72.8%		73%	80%	79%	62%	82%	76%	73%	76%	72%	69%	69%	73%	63%
64.6%		67%	67%	73%	55%	70%	68%	66%	60%	62%	70%	63%	62%	57%
50.2%		50%	46%	52%	39%	53%	51%	60%	62%	53%	30%	55%	53%	48%
75.9%		79%	84%	91%	72%	59%	74%	82%	70%	73%	84%	68%	78%	73%
49.9%		50%	50%	50%	69%	35%	52%	67%	52%	52%	38%	53%	40%	41%
75.7%		81%	80%	67%	72%	79%	79%	74%	82%	80%	59%	77%	81%	73%
78.5%		86%	85%	63%	78%	70%	79%	80%	73%	87%	84%	72%	78%	86%
44.8%		33%	62%	46%	74%	35%	44%	36%	62%	64%	19%	34%	31%	43%
76.8%		79%	77%	72%	50%	89%	79%	63%	78%	85%	75%	84%	82%	86%
53.8%		58%	53%	58%	75%	36%	55%	62%	65%	57%	44%	48%	35%	53%
77.0%		78%	83%	73%	53%	81%	87%	65%	61%	75%	81%	88%	87%	89%
74.5%		81%	83%	83%	66%	45%	80%	78%	74%	86%	67%	67%	80%	78%
62.5%		64%	68%	63%	63%	54%	55%	65%	68%	66%	61%	59%	64%	62%
82.1%		78%	83%	83%	87%	90%	92%	92%	85%	79%	63%	74%	78%	83%
77.8%		78%	79%	71%	86%	76%	79%	79%	77%	77%	79%	80%	82%	69%
70.0%		82%	75%	68%	25%	74%	77%	75%	77%	79%	69%	77%	75%	57%
70.4%		73%	71%	75%	69%	68%	75%	84%	69%	71%	66%	60%	56%	78%
57.5%		64%	61%	66%	72%	46%	69%	56%	75%	51%	54%	41%	40%	53%
67.9%		78%	74%	70%	65%	74%	67%	63%	65%	74%	41%	63%	73%	76%
66.8%		68%	69%	67%	77%	60%	63%	73%	63%	70%	61%	63%	60%	75%
87.3%		87%	87%	90%	91%	86%	87%	84%	79%	85%	69%	100%	97%	93%
59.8%		58%	62%	45%	45%	66%	47%	43%	65%	67%	58%	74%	73%	74%
74.8%		82%	85%	74%	52%	86%	74%	55%	85%	84%	79%	75%	79%	63%
83.1%		95%	89%	89%	67%	81%	76%	85%	85%	79%	90%	81%	88%	75%
61.8%		67%	73%	64%	82%	42%	59%	73%	77%	51%	37%	72%	44%	63%
71.6%		74%	78%	57%	68%	75%	74%	61%	69%	80%	75%	73%	74%	73%
78.1%		77%	80%	80%	59%	89%	80%	71%	54%	85%	85%	82%	85%	88%
76.3%		79%	83%	70%	67%	75%	72%	70%	83%	75%	73%	78%	84%	83%
76.9%		76%	78%	78%	79%	75%	68%	66%	70%	74%	83%	85%	86%	82%
64.5%		69%	73%	62%	21%	70%	69%	70%	65%	69%	69%	67%	69%	65%
66.8%		69%	63%	54%	65%	71%	70%	70%	67%	63%	59%	73%	72%	72%
78.0%		70%	82%	75%	82%	71%	82%	84%	89%	70%	78%	76%	82%	73%
78.8%		76%	82%	66%	76%	86%	75%	72%	75%	88%	75%	79%	90%	85%
58.8%		60%	71%	66%	63%	47%	63%	56%	72%	59%	56%	50%	49%	52%
77.2%		81%	80%	72%	75%	74%	75%	80%	81%	81%	74%	80%	75%	76%
68.0%		69%	73%	72%	64%	77%	73%	73%	76%	73%	51%	71%	56%	56%
78.3%		87%	87%	76%	77%	78%	78%	83%	81%	75%	78%	76%	79%	63%
61.8%		61%	62%	66%	62%	59%	62%	62%	62%	69%	51%	64%	62%	62%
63.1%		63%	61%	58%	69%	65%	59%	65%	60%	60%	64%	67%	60%	69%
69.5%		71%	79%	76%	83%	49%	68%	79%	73%	70%	43%	61%	69%	82%
90.2%		86%	91%	86%	100%	90%	92%	93%	95%	90%	71%	96%	92%	90%
69.8%		67%	73%	81%	67%	53%	76%	81%	67%	63%	75%	70%	61%	74%
54.7%		55%	100%	66%	50%	24%	77%	65%	63%	81%	37%	44%	42%	7%
68.6%		70%	69%	76%	32%	84%	64%	69%	70%	70%	73%	77%	68%	70%
78.8%		68%	81%	63%	77%	84%	79%	79%	79%	80%	74%	76%	89%	95%
53.9%		57%	60%	47%	50%	61%	58%	41%	53%	50%	43%	52%	61%	68%
78.6%		83%	82%	72%	82%	74%	82%	79%	87%	79%	77%	74%	81%	70%
80.4%		86%	75%	86%	51%	83%	82%	77%	73%	87%	88%	87%	88%	82%
80.8%		82%	91%	91%	58%	75%	71%	87%	81%	96%	80%	73%	78%	88%
75.2%		87%	77%	81%	68%	50%	79%	91%	83%	80%	53%	88%	59%	82%
77.8%		85%	80%	58%	84%	72%	75%	75%	89%	87%	73%	81%	76%	77%
55.2%		57%	66%	62%	39%	60%	59%	67%	63%	51%	44%	59%	40%	50%
81.0%		75%	90%	79%	80%	72%	85%	87%	87%	82%	85%	72%	82%	77%
81.4%		86%	81%	89%	82%	78%	74%	77%	79%	87%	87%	73%	87%	78%
67.8%		64%	68%	68%	74%	53%	67%	72%	72%	78%	62%	69%	68%	67%
81.6%		86%	81%	79%	76%	73%	87%	91%	89%	89%	72%	87%	74%	77%
63.1%		79%	75%	83%	0%	51%	78%	65%	71%	73%	49%	58%	54%	84%
67.3%		55%	75%	58%	69%	73%	80%	78%	47%	76%	70%	62%	62%	70%
57.0%		58%	59%	59%	85%	32%	55%	71%	73%	60%	34%	61%	35%	59%
68.7%		67%	69%	69%	74%	69%	69%	65%	74%	70%	63%	71%	68%	65%
63.4%		61%	68%	75%	83%	56%	65%	77%	77%	64%	56%	50%	49%	43%
83.5%		83%	89%	80%	87%	90%	80%	79%	89%	81%	84%	77%	83%	83%
68.6%		70%	71%	55%	72%	67%	80%	75%	72%	76%	66%	72%	63%	53%
69.9%		63%	63%	74%	79%	54%	71%	74%	77%	72%	79%	71%	65%	67%
71.4%		78%	76%	60%	39%	77%	78%	72%	62%	78%	79%	79%	77%	73%
74.2%		69%	69%	65%	80%	86%	83%	78%	75%	78%	54%	89%	72%	66%
59.8%		66%	60%	54%	57%	58%	57%	57%	64%	57%	57%	62%	62%	67%