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%3Aegypt - Run 3fb32da...

Global Dialogues GD4 - Egypt

DTEF: Predict response distributions for Egypt. 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

Best Models (Coverage)

1.GPT 4.1
65.9%
2.Claude Sonnet 4.5
65.7%
3.Gemini 2.5 Flash
65.4%
4.Mistral Medium 3
65.0%
5.Claude Haiku 4.5
64.7%

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		5th 64.7%	6th 64.2%	2nd 65.7%	3rd 65.4%	13th 59.2%	9th 63.1%	4th 65.0%	1st 65.9%	8th 63.9%	12th 60.6%	10th 62.7%	11th 62.2%	7th 63.9%
56.2%		59%	63%	71%	65%	37%	49%	57%	60%	65%	63%	45%	57%	39%
55.0%		53%	53%	53%	66%	39%	51%	57%	69%	63%	49%	53%	47%	62%
70.3%		72%	72%	72%	69%	69%	74%	72%	77%	75%	64%	62%	64%	72%
60.0%		60%	62%	62%	65%	62%	51%	64%	52%	60%	57%	60%	63%	62%
59.6%		70%	66%	67%	54%	58%	54%	57%	56%	57%	53%	60%	59%	64%
81.8%		83%	90%	90%	93%	62%	88%	93%	91%	76%	73%	93%	73%	58%
34.6%		41%	41%	40%	31%	26%	36%	28%	23%	41%	20%	40%	30%	53%
69.5%		73%	66%	67%	56%	77%	71%	65%	73%	79%	78%	65%	67%	66%
78.1%		83%	69%	69%	74%	80%	84%	81%	69%	84%	81%	84%	71%	86%
60.5%		62%	62%	62%	64%	62%	63%	55%	58%	61%	61%	59%	59%	58%
77.8%		87%	81%	81%	77%	70%	83%	79%	81%	81%	76%	76%	68%	71%
73.4%		76%	79%	79%	74%	77%	74%	71%	71%	78%	54%	71%	75%	75%
70.2%		69%	77%	69%	66%	69%	66%	71%	69%	70%	74%	67%	69%	76%
41.2%		51%	50%	54%	44%	28%	37%	36%	40%	37%	36%	36%	36%	50%
67.4%		69%	62%	62%	46%	74%	72%	69%	71%	72%	69%	73%	67%	70%
53.2%		58%	42%	56%	75%	42%	59%	60%	59%	57%	42%	43%	47%	51%
57.0%		63%	65%	65%	69%	40%	55%	60%	60%	56%	50%	48%	50%	60%
87.1%		93%	85%	82%	80%	82%	88%	86%	89%	86%	92%	91%	84%	94%
66.2%		69%	65%	60%	66%	69%	61%	65%	65%	71%	67%	69%	67%	67%
77.2%		78%	73%	73%	90%	64%	67%	76%	76%	91%	78%	81%	74%	83%
78.1%		80%	72%	81%	77%	81%	85%	81%	75%	74%	74%	80%	74%	81%
85.1%		85%	90%	90%	85%	88%	84%	82%	88%	84%	74%	81%	80%	95%
83.6%		86%	81%	84%	85%	68%	83%	91%	94%	83%	85%	91%	85%	71%
44.3%		43%	43%	43%	60%	36%	53%	55%	59%	34%	34%	34%	35%	47%
74.8%		76%	71%	72%	70%	77%	69%	82%	82%	71%	89%	72%	74%	68%
37.3%		34%	34%	35%	43%	38%	38%	39%	35%	40%	18%	52%	45%	34%
68.2%		67%	62%	71%	70%	66%	73%	73%	66%	71%	66%	69%	74%	59%
54.1%		51%	59%	69%	66%	35%	56%	59%	58%	47%	61%	54%	44%	44%
52.2%		52%	56%	69%	56%	54%	57%	46%	59%	45%	53%	47%	41%	43%
79.2%		88%	86%	88%	84%	64%	79%	85%	73%	84%	86%	68%	65%	79%
61.1%		59%	61%	57%	58%	56%	55%	62%	57%	66%	60%	70%	71%	62%
52.7%		54%	51%	56%	54%	47%	48%	56%	55%	51%	50%	54%	54%	55%
54.8%		54%	51%	66%	52%	61%	67%	61%	51%	62%	47%	52%	44%	44%
58.2%		56%	47%	65%	83%	47%	69%	62%	69%	58%	47%	50%	45%	59%
57.5%		46%	63%	61%	58%	63%	49%	48%	63%	57%	60%	61%	56%	63%
77.1%		77%	77%	66%	77%	77%	67%	89%	67%	86%	85%	78%	79%	77%
65.1%		74%	69%	58%	66%	68%	52%	59%	72%	64%	64%	67%	64%	69%
37.7%		28%	35%	48%	40%	47%	25%	29%	31%	32%	56%	44%	44%	31%
71.9%		78%	69%	69%	76%	58%	71%	77%	66%	74%	74%	73%	80%	70%
41.5%		30%	39%	38%	40%	49%	29%	39%	35%	44%	54%	47%	57%	39%
64.7%		71%	65%	76%	68%	46%	72%	78%	73%	63%	45%	66%	53%	65%
74.8%		76%	83%	83%	78%	92%	84%	70%	75%	76%	59%	59%	75%	63%
59.0%		65%	49%	68%	59%	42%	60%	60%	68%	68%	62%	50%	54%	62%
51.9%		53%	49%	45%	52%	47%	65%	53%	65%	56%	68%	49%	43%	30%
68.7%		70%	65%	65%	72%	72%	72%	68%	71%	66%	67%	63%	69%	73%
65.0%		70%	75%	75%	68%	47%	62%	62%	78%	67%	43%	59%	64%	75%
72.3%		75%	72%	65%	63%	82%	63%	77%	65%	75%	73%	85%	79%	66%
82.6%		82%	85%	85%	88%	76%	74%	72%	85%	85%	80%	96%	100%	66%
75.0%		75%	73%	65%	74%	75%	79%	77%	75%	80%	68%	85%	74%	75%
66.2%		70%	68%	66%	68%	62%	66%	67%	69%	64%	56%	68%	66%	71%
64.0%		68%	68%	65%	64%	66%	63%	58%	64%	65%	57%	65%	64%	65%
52.2%		48%	50%	55%	65%	42%	56%	63%	65%	50%	56%	37%	48%	44%
66.6%		52%	66%	74%	85%	63%	52%	69%	67%	66%	64%	67%	75%	66%
40.3%		38%	38%	38%	44%	35%	46%	42%	56%	40%	35%	40%	34%	38%
76.1%		78%	76%	85%	56%	76%	78%	68%	76%	86%	89%	77%	77%	67%
62.5%		64%	70%	70%	74%	44%	70%	64%	70%	57%	54%	53%	53%	70%
56.5%		51%	54%	54%	58%	36%	74%	65%	75%	52%	60%	42%	57%	57%
61.1%		60%	65%	60%	47%	59%	60%	60%	48%	70%	60%	66%	68%	71%
49.0%		45%	38%	58%	73%	38%	56%	60%	60%	38%	38%	40%	39%	54%
60.3%		61%	61%	61%	59%	78%	54%	57%	61%	61%	48%	59%	63%	61%
58.2%		64%	52%	63%	58%	50%	59%	70%	57%	56%	56%	54%	54%	63%
65.7%		69%	74%	82%	74%	43%	66%	71%	76%	57%	65%	61%	61%	55%
60.3%		63%	68%	61%	63%	70%	66%	64%	65%	67%	50%	48%	48%	51%
83.0%		85%	82%	82%	78%	88%	81%	80%	78%	82%	81%	89%	86%	87%
72.8%		74%	83%	71%	70%	65%	79%	77%	70%	71%	79%	71%	71%	66%
58.2%		43%	43%	60%	75%	49%	74%	76%	77%	57%	56%	46%	39%	62%
58.8%		71%	59%	69%	71%	47%	65%	67%	56%	48%	68%	48%	48%	48%
69.0%		73%	72%	74%	68%	67%	62%	64%	67%	67%	64%	70%	77%	72%
68.9%		62%	61%	51%	55%	70%	67%	71%	76%	75%	82%	70%	82%	74%
65.8%		72%	72%	72%	72%	56%	53%	72%	56%	72%	60%	67%	59%	72%
68.7%		71%	68%	60%	71%	66%	73%	69%	75%	64%	62%	68%	72%	74%
58.8%		63%	60%	59%	60%	57%	57%	69%	54%	59%	56%	55%	63%	52%
84.0%		81%	84%	90%	85%	83%	84%	83%	90%	78%	85%	83%	83%	83%
50.7%		66%	58%	68%	57%	10%	47%	55%	66%	47%	44%	52%	38%	51%
75.1%		70%	70%	70%	69%	83%	77%	80%	70%	70%	75%	72%	81%	89%
58.2%		59%	59%	59%	65%	55%	59%	61%	61%	58%	52%	56%	52%	61%
68.8%		72%	72%	72%	69%	76%	65%	66%	64%	73%	65%	69%	65%	67%
67.7%		76%	69%	81%	76%	49%	64%	71%	77%	65%	72%	65%	61%	54%
67.8%		66%	68%	68%	63%	68%	71%	72%	68%	68%	76%	67%	65%	62%
71.5%		70%	79%	72%	67%	78%	67%	73%	71%	76%	61%	73%	73%	69%
74.6%		75%	78%	80%	75%	70%	85%	76%	70%	72%	77%	73%	75%	64%
63.9%		58%	68%	61%	62%	78%	54%	55%	63%	66%	59%	66%	68%	73%
52.2%		56%	62%	55%	54%	50%	56%	49%	56%	56%	50%	45%	43%	46%
82.6%		90%	85%	72%	80%	83%	87%	82%	81%	85%	71%	90%	85%	83%
70.4%		73%	74%	72%	74%	58%	72%	69%	72%	77%	58%	71%	70%	75%
76.5%		80%	78%	78%	72%	62%	77%	81%	78%	78%	77%	85%	72%	77%
55.9%		53%	59%	59%	65%	66%	48%	47%	53%	50%	50%	50%	65%	62%
56.8%		56%	56%	66%	65%	41%	58%	57%	62%	52%	57%	56%	57%	56%
63.5%		72%	70%	70%	77%	74%	56%	61%	63%	61%	26%	56%	61%	78%
75.8%		83%	76%	79%	77%	71%	77%	71%	70%	79%	73%	72%	79%	79%
53.8%		55%	51%	51%	51%	51%	51%	54%	63%	51%	51%	51%	56%	64%
30.0%		28%	24%	19%	25%	14%	18%	26%	56%	25%	25%	25%	32%	73%
53.2%		60%	52%	56%	37%	46%	46%	54%	57%	61%	52%	67%	61%	42%
60.6%		65%	66%	62%	63%	60%	60%	64%	60%	58%	52%	58%	60%	60%
53.9%		57%	52%	52%	44%	64%	55%	56%	60%	53%	53%	53%	50%	52%
52.6%		47%	50%	50%	52%	46%	49%	52%	76%	42%	54%	52%	52%	62%
61.3%		63%	62%	67%	56%	61%	59%	57%	59%	64%	64%	59%	64%	62%
66.7%		66%	66%	72%	63%	64%	70%	72%	77%	60%	69%	54%	63%	71%
76.8%		87%	71%	77%	85%	52%	79%	80%	82%	80%	69%	71%	80%	85%
70.3%		64%	78%	71%	80%	67%	56%	61%	73%	71%	60%	71%	81%	81%
58.2%		67%	69%	69%	61%	48%	61%	57%	70%	61%	56%	53%	37%	48%
80.5%		80%	75%	84%	77%	75%	82%	82%	85%	75%	76%	80%	89%	87%
57.6%		60%	55%	55%	63%	49%	47%	62%	56%	59%	53%	68%	66%	56%
65.1%		64%	62%	62%	64%	63%	70%	71%	69%	61%	63%	62%	66%	69%
56.5%		56%	49%	56%	50%	50%	62%	55%	65%	59%	65%	63%	52%	52%
78.4%		81%	91%	91%	79%	66%	70%	77%	89%	77%	56%	74%	76%	92%
54.8%		54%	55%	56%	64%	49%	64%	52%	43%	60%	67%	53%	55%	40%
41.2%		36%	36%	47%	61%	22%	43%	41%	57%	43%	35%	36%	34%	45%
64.0%		65%	69%	70%	80%	59%	55%	64%	66%	69%	32%	65%	67%	71%
53.5%		55%	54%	56%	44%	59%	51%	58%	38%	58%	66%	54%	49%	54%
63.7%		65%	68%	51%	65%	65%	52%	73%	55%	53%	77%	68%	65%	71%
61.5%		57%	60%	74%	79%	39%	59%	68%	65%	59%	64%	72%	47%	56%
40.4%		38%	37%	32%	45%	47%	34%	39%	31%	45%	20%	52%	45%	60%
79.5%		79%	75%	80%	66%	78%	80%	85%	80%	80%	82%	82%	87%	80%
66.7%		58%	76%	79%	58%	77%	70%	81%	61%	67%	56%	73%	61%	50%
68.2%		69%	74%	71%	66%	63%	68%	68%	75%	64%	49%	68%	70%	81%