DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 Dtef Global Dialogues Gd4 Country%3Akenya - Run 9a45dd5...

Global Dialogues GD4 - Kenya

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

Demographic Processes

General Knowledge

Geographic & Local Knowledge

Economics & Finance

Best Models (Coverage)

1.GPT 4.1
78.5%
2.Claude Sonnet 4.5
77.4%
3.Claude Sonnet 4
75.5%
4.Gemini 2.5 Flash
75.4%
5.GPT 4.1 Mini
74.1%

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		6th 73.9%	3rd 75.5%	2nd 77.4%	4th 75.4%	13th 67.3%	7th 73.8%	8th 73.7%	1st 78.5%	5th 74.1%	9th 73.5%	10th 71.9%	12th 69.6%	11th 70.3%
50.2%		55%	60%	66%	58%	27%	42%	50%	70%	48%	53%	48%	34%	41%
71.1%		70%	73%	77%	83%	52%	60%	70%	83%	78%	75%	68%	62%	73%
74.8%		75%	75%	77%	80%	77%	75%	74%	70%	80%	70%	74%	70%	75%
81.8%		79%	83%	83%	77%	77%	86%	87%	93%	73%	86%	79%	77%	83%
72.8%		80%	77%	80%	71%	64%	71%	75%	66%	65%	84%	69%	73%	72%
72.8%		71%	80%	84%	78%	65%	80%	72%	85%	69%	80%	72%	63%	47%
29.7%		37%	29%	32%	30%	20%	25%	24%	32%	44%	15%	40%	26%	32%
80.4%		85%	86%	83%	74%	79%	82%	81%	86%	86%	80%	78%	58%	87%
78.5%		76%	76%	74%	78%	83%	84%	78%	83%	80%	83%	75%	65%	85%
69.0%		67%	52%	50%	49%	75%	65%	51%	61%	82%	81%	85%	87%	92%
72.5%		66%	70%	75%	91%	60%	74%	80%	93%	71%	80%	66%	54%	63%
77.8%		73%	90%	93%	85%	57%	80%	80%	90%	75%	87%	77%	62%	62%
71.3%		74%	78%	75%	75%	65%	68%	73%	84%	67%	75%	67%	61%	65%
60.0%		64%	64%	66%	72%	50%	64%	49%	69%	52%	49%	54%	64%	63%
66.1%		67%	74%	68%	45%	73%	60%	60%	54%	64%	79%	74%	81%	60%
87.8%		97%	84%	91%	91%	77%	95%	92%	96%	93%	85%	80%	77%	84%
60.3%		60%	69%	74%	74%	42%	60%	63%	64%	53%	63%	48%	49%	65%
86.3%		83%	87%	82%	86%	90%	89%	91%	83%	92%	87%	80%	90%	82%
81.7%		86%	83%	87%	77%	83%	74%	84%	64%	87%	83%	86%	83%	85%
67.3%		71%	66%	66%	67%	58%	69%	70%	70%	67%	71%	71%	64%	65%
86.2%		89%	84%	89%	89%	86%	85%	88%	87%	94%	89%	80%	80%	80%
89.2%		94%	88%	88%	87%	89%	96%	93%	91%	93%	89%	86%	84%	81%
74.2%		76%	79%	91%	81%	68%	80%	77%	90%	63%	85%	76%	51%	48%
74.0%		78%	83%	78%	77%	66%	84%	75%	75%	78%	69%	59%	66%	74%
77.1%		74%	80%	81%	65%	77%	68%	78%	76%	87%	68%	84%	82%	82%
37.5%		37%	30%	45%	40%	33%	33%	37%	47%	37%	26%	44%	40%	39%
67.0%		54%	72%	78%	75%	64%	59%	72%	79%	66%	75%	55%	56%	66%
60.4%		61%	66%	81%	65%	37%	58%	65%	81%	57%	74%	55%	43%	42%
66.8%		61%	62%	74%	75%	49%	80%	69%	82%	67%	77%	62%	59%	51%
69.4%		74%	75%	86%	84%	50%	63%	72%	82%	67%	63%	67%	51%	68%
83.2%		84%	90%	91%	90%	77%	90%	84%	87%	78%	88%	84%	80%	59%
84.5%		75%	83%	79%	90%	81%	73%	80%	71%	84%	98%	97%	94%	93%
57.2%		56%	59%	57%	73%	53%	62%	69%	65%	55%	58%	51%	43%	43%
71.6%		69%	68%	79%	86%	69%	85%	71%	77%	71%	64%	60%	64%	68%
86.8%		93%	88%	91%	76%	88%	82%	89%	91%	88%	90%	91%	77%	84%
82.5%		78%	91%	93%	91%	68%	86%	81%	94%	78%	92%	86%	77%	57%
77.2%		68%	81%	82%	72%	74%	91%	72%	89%	86%	75%	71%	66%	77%
65.8%		54%	68%	59%	68%	77%	53%	53%	66%	59%	77%	73%	83%	66%
71.8%		69%	80%	83%	83%	64%	74%	73%	83%	67%	79%	72%	60%	46%
54.5%		50%	64%	57%	54%	59%	39%	48%	47%	55%	66%	58%	70%	42%
84.8%		88%	88%	86%	82%	76%	90%	90%	87%	87%	75%	90%	79%	84%
82.0%		83%	66%	66%	87%	80%	79%	88%	82%	80%	93%	81%	96%	85%
81.6%		91%	93%	96%	89%	60%	83%	95%	83%	90%	79%	64%	56%	82%
80.1%		78%	78%	77%	76%	89%	81%	86%	85%	83%	78%	82%	80%	68%
83.1%		85%	90%	92%	77%	77%	81%	82%	84%	85%	81%	85%	76%	85%
80.7%		83%	84%	86%	84%	64%	78%	82%	85%	85%	79%	75%	80%	84%
78.3%		84%	80%	77%	81%	80%	77%	79%	72%	78%	79%	75%	79%	77%
55.8%		53%	58%	58%	62%	41%	57%	50%	71%	57%	47%	66%	58%	47%
90.8%		95%	94%	83%	91%	96%	95%	95%	93%	93%	80%	86%	85%	95%
79.8%		83%	92%	83%	77%	69%	86%	83%	83%	78%	83%	80%	70%	71%
85.9%		92%	85%	80%	91%	86%	89%	87%	86%	87%	70%	92%	84%	88%
68.8%		67%	63%	83%	77%	65%	54%	66%	74%	69%	70%	57%	76%	74%
49.2%		43%	42%	52%	60%	49%	34%	48%	60%	57%	48%	40%	50%	56%
77.5%		73%	82%	79%	92%	68%	79%	80%	93%	75%	72%	73%	72%	70%
76.9%		79%	83%	94%	70%	62%	88%	74%	90%	80%	72%	75%	76%	57%
78.7%		73%	79%	91%	94%	66%	76%	77%	95%	75%	80%	65%	66%	86%
60.3%		67%	66%	71%	45%	52%	54%	58%	63%	66%	52%	63%	77%	50%
80.2%		82%	85%	84%	86%	74%	77%	83%	93%	78%	86%	69%	70%	75%
74.6%		73%	67%	83%	95%	67%	87%	76%	85%	76%	62%	64%	60%	75%
84.6%		84%	84%	85%	87%	85%	81%	89%	71%	87%	87%	87%	89%	84%
81.4%		90%	83%	74%	75%	86%	86%	79%	77%	81%	83%	81%	77%	86%
58.8%		63%	72%	76%	65%	37%	56%	62%	73%	48%	63%	47%	54%	48%
83.3%		91%	86%	85%	77%	88%	84%	89%	88%	82%	76%	70%	83%	84%
78.5%		75%	82%	79%	83%	67%	83%	86%	87%	76%	81%	81%	65%	75%
77.8%		69%	85%	90%	83%	65%	83%	85%	94%	75%	71%	83%	73%	55%
73.6%		64%	79%	82%	88%	57%	88%	86%	88%	69%	70%	59%	51%	76%
71.5%		75%	77%	81%	94%	52%	69%	75%	93%	66%	76%	53%	56%	63%
75.6%		82%	77%	77%	73%	74%	74%	70%	74%	72%	72%	76%	81%	81%
72.9%		70%	69%	64%	69%	74%	75%	72%	73%	77%	77%	76%	77%	75%
71.8%		77%	86%	82%	83%	62%	59%	71%	70%	77%	63%	64%	69%	70%
74.5%		77%	76%	82%	74%	66%	79%	69%	82%	80%	80%	64%	65%	75%
83.2%		85%	82%	85%	80%	92%	82%	72%	86%	89%	84%	84%	80%	81%
86.6%		85%	90%	88%	87%	83%	90%	88%	91%	84%	84%	88%	81%	87%
68.9%		57%	61%	56%	57%	78%	76%	63%	65%	73%	78%	70%	83%	79%
82.6%		82%	90%	90%	77%	76%	89%	87%	90%	85%	84%	81%	79%	64%
85.2%		85%	89%	88%	83%	92%	90%	78%	74%	90%	84%	85%	86%	84%
92.5%		95%	96%	97%	91%	79%	97%	92%	94%	88%	94%	92%	93%	95%
73.8%		80%	83%	84%	77%	51%	73%	68%	87%	77%	76%	73%	66%	64%
71.9%		64%	76%	70%	87%	63%	72%	72%	89%	71%	77%	64%	58%	72%
81.6%		85%	96%	90%	76%	68%	86%	79%	83%	95%	78%	78%	84%	63%
85.4%		89%	81%	81%	80%	87%	73%	84%	85%	89%	93%	89%	87%	92%
75.5%		79%	77%	87%	74%	59%	82%	82%	94%	68%	80%	77%	64%	59%
73.0%		76%	79%	86%	75%	61%	84%	79%	81%	72%	68%	65%	55%	68%
81.8%		84%	84%	83%	74%	89%	87%	82%	78%	85%	68%	78%	84%	88%
82.8%		84%	91%	89%	77%	76%	89%	87%	81%	88%	77%	84%	76%	77%
70.5%		60%	71%	72%	76%	61%	73%	68%	88%	69%	83%	70%	60%	65%
79.7%		83%	83%	86%	74%	72%	71%	84%	79%	78%	78%	83%	82%	83%
75.9%		75%	77%	77%	81%	67%	71%	80%	75%	79%	70%	83%	76%	76%
78.1%		84%	89%	86%	81%	82%	78%	75%	79%	81%	46%	70%	83%	81%
43.4%		45%	45%	45%	46%	34%	39%	42%	48%	45%	39%	45%	51%	40%
68.7%		65%	72%	72%	72%	59%	76%	65%	81%	62%	68%	62%	66%	73%
53.1%		52%	50%	51%	58%	46%	37%	50%	50%	49%	58%	59%	66%	64%
35.8%		51%	33%	34%	23%	29%	25%	29%	44%	34%	36%	39%	64%	25%
74.1%		88%	73%	91%	76%	52%	84%	80%	94%	74%	71%	69%	56%	55%
75.5%		79%	74%	69%	84%	87%	77%	76%	62%	74%	73%	73%	80%	73%
87.3%		92%	94%	94%	79%	85%	89%	84%	87%	93%	86%	87%	78%	87%
81.8%		75%	85%	83%	74%	93%	82%	73%	80%	84%	81%	84%	81%	88%
81.3%		86%	83%	75%	72%	92%	80%	73%	70%	89%	85%	86%	80%	86%
85.0%		90%	86%	87%	83%	64%	84%	88%	92%	87%	85%	93%	77%	89%
86.2%		87%	88%	90%	85%	85%	86%	92%	83%	87%	89%	89%	82%	77%
82.2%		75%	76%	75%	83%	88%	83%	86%	79%	87%	87%	87%	79%	84%
69.8%		63%	74%	81%	77%	63%	66%	63%	80%	67%	75%	54%	70%	75%
28.0%		33%	27%	27%	39%	17%	17%	33%	35%	32%	13%	29%	36%	26%
73.3%		76%	78%	82%	81%	50%	60%	70%	84%	76%	82%	79%	59%	76%
73.8%		68%	78%	94%	80%	56%	77%	71%	93%	74%	76%	73%	60%	60%
86.5%		91%	88%	88%	89%	80%	88%	88%	85%	88%	75%	88%	87%	90%
73.4%		72%	76%	82%	57%	64%	87%	81%	77%	77%	83%	65%	61%	72%
66.8%		64%	64%	73%	89%	45%	71%	68%	81%	71%	67%	62%	53%	60%
65.4%		71%	54%	73%	72%	67%	66%	53%	68%	57%	38%	72%	78%	81%
67.6%		62%	68%	67%	62%	71%	79%	71%	86%	74%	60%	60%	56%	63%
77.7%		82%	79%	70%	69%	86%	75%	73%	70%	76%	85%	84%	82%	79%
46.9%		44%	47%	57%	56%	32%	47%	53%	56%	48%	57%	48%	35%	30%
42.6%		36%	36%	34%	39%	51%	39%	45%	45%	39%	33%	53%	55%	49%
84.9%		91%	86%	85%	91%	71%	87%	86%	96%	82%	89%	87%	74%	79%
88.5%		88%	90%	94%	94%	75%	96%	86%	96%	94%	88%	84%	88%	78%
89.2%		91%	85%	92%	80%	88%	90%	89%	91%	92%	87%	92%	89%	94%