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%3Aegypt C5 - Run 06f696e...

Global Dialogues GD4 - Egypt (5 context Qs)

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

AI Safety & Robustness

Social interaction

AI Bias & Fairness

Best Models (Coverage)

1.Claude Sonnet 4
65.4%
2.Mistral Medium 3
65.2%
3.GPT 4.1 Mini
65.0%
4.Claude Haiku 4.5
64.8%
5.Llama 4 Maverick
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		4th 64.8%	1st 65.4%	6th 64.5%	13th 57.9%	11th 61.1%	5th 64.7%	2nd 65.2%	7th 63.1%	3rd 65.0%	12th 59.2%	8th 63.1%	9th 62.0%	10th 61.6%
56.6%		63%	66%	78%	75%	35%	54%	52%	59%	50%	52%	48%	52%	52%
52.8%		53%	53%	53%	76%	30%	53%	58%	71%	53%	49%	49%	36%	53%
70.3%		72%	72%	70%	70%	70%	72%	67%	70%	75%	69%	69%	69%	69%
55.5%		62%	62%	62%	25%	62%	57%	45%	43%	62%	60%	47%	60%	75%
53.6%		49%	54%	45%	54%	58%	54%	59%	45%	50%	60%	50%	60%	59%
78.7%		84%	90%	90%	52%	79%	85%	78%	82%	90%	78%	93%	78%	44%
63.2%		79%	79%	79%	79%	53%	61%	59%	52%	58%	46%	61%	58%	58%
64.8%		66%	66%	66%	60%	68%	71%	74%	46%	71%	58%	65%	65%	66%
74.2%		69%	69%	69%	77%	79%	79%	84%	69%	79%	70%	80%	71%	69%
60.7%		62%	62%	62%	63%	62%	67%	60%	50%	61%	61%	61%	60%	58%
76.5%		80%	86%	86%	50%	86%	80%	78%	65%	81%	78%	80%	78%	67%
71.8%		78%	80%	59%	70%	78%	62%	69%	70%	89%	56%	77%	71%	75%
65.7%		69%	77%	66%	46%	71%	69%	56%	53%	69%	76%	66%	67%	69%
50.3%		51%	62%	64%	64%	37%	50%	44%	50%	50%	33%	49%	50%	50%
59.8%		53%	75%	46%	27%	58%	69%	65%	75%	62%	59%	69%	57%	62%
49.2%		42%	42%	59%	76%	42%	59%	44%	63%	57%	36%	43%	35%	42%
66.5%		70%	70%	70%	76%	63%	60%	67%	67%	70%	60%	62%	63%	67%
72.8%		83%	68%	54%	62%	82%	80%	69%	68%	85%	80%	72%	76%	68%
65.6%		69%	70%	56%	67%	70%	60%	65%	59%	70%	57%	67%	70%	73%
83.8%		89%	91%	92%	88%	64%	85%	73%	92%	85%	67%	90%	91%	83%
69.0%		70%	64%	52%	64%	66%	81%	69%	66%	75%	81%	70%	75%	64%
84.5%		85%	84%	100%	64%	92%	72%	82%	88%	100%	80%	82%	80%	90%
76.0%		81%	87%	84%	44%	79%	82%	87%	82%	67%	81%	83%	87%	44%
37.4%		43%	43%	38%	53%	30%	43%	43%	35%	31%	35%	29%	28%	35%
65.0%		59%	62%	75%	46%	67%	65%	74%	71%	66%	71%	72%	55%	62%
66.2%		64%	64%	79%	62%	73%	79%	64%	64%	64%	62%	64%	64%	58%
68.2%		67%	66%	74%	68%	64%	66%	70%	72%	69%	66%	71%	62%	71%
60.4%		66%	69%	60%	52%	48%	66%	59%	66%	66%	64%	64%	46%	59%
56.6%		51%	63%	63%	57%	54%	58%	55%	63%	58%	60%	52%	48%	54%
79.9%		88%	76%	71%	72%	61%	83%	88%	88%	86%	85%	80%	73%	88%
56.0%		59%	55%	57%	36%	60%	58%	62%	61%	56%	56%	58%	62%	48%
55.1%		57%	53%	56%	70%	51%	61%	60%	55%	51%	50%	54%	50%	48%
68.1%		69%	72%	100%	92%	54%	63%	72%	72%	92%	47%	52%	49%	51%
51.3%		47%	47%	47%	79%	47%	47%	58%	67%	47%	43%	50%	41%	47%
60.4%		58%	63%	63%	55%	67%	57%	53%	67%	61%	60%	60%	61%	60%
68.5%		73%	60%	66%	32%	77%	80%	76%	66%	77%	81%	68%	76%	58%
68.1%		65%	70%	79%	44%	65%	73%	68%	76%	74%	67%	64%	64%	76%
49.3%		40%	48%	48%	41%	65%	29%	40%	40%	42%	52%	56%	72%	68%
67.8%		73%	69%	69%	32%	76%	71%	73%	69%	76%	74%	73%	73%	54%
47.8%		40%	50%	56%	48%	59%	33%	42%	44%	50%	55%	57%	47%	41%
58.5%		61%	60%	68%	70%	46%	63%	71%	73%	56%	45%	49%	52%	46%
61.8%		65%	65%	59%	49%	75%	65%	59%	51%	65%	44%	44%	88%	75%
50.8%		49%	49%	56%	66%	49%	48%	53%	56%	49%	46%	50%	41%	49%
41.7%		38%	43%	32%	46%	38%	56%	56%	40%	28%	49%	39%	34%	43%
67.5%		75%	71%	60%	51%	71%	72%	65%	65%	65%	71%	60%	76%	76%
64.2%		71%	70%	70%	66%	47%	79%	59%	78%	64%	41%	63%	64%	62%
67.1%		68%	61%	60%	41%	70%	62%	81%	67%	71%	75%	78%	69%	69%
85.5%		88%	86%	86%	76%	72%	85%	85%	100%	85%	85%	97%	100%	66%
72.2%		83%	74%	65%	46%	68%	74%	75%	75%	75%	64%	85%	76%	78%
66.1%		70%	72%	59%	67%	64%	60%	63%	72%	69%	59%	65%	66%	73%
64.2%		66%	68%	57%	65%	66%	61%	60%	68%	66%	58%	64%	66%	70%
50.0%		50%	55%	53%	44%	49%	49%	58%	63%	37%	42%	62%	48%	40%
73.8%		75%	80%	76%	70%	61%	78%	81%	90%	75%	56%	83%	62%	72%
39.5%		38%	38%	27%	69%	33%	44%	45%	38%	38%	35%	35%	35%	38%
76.5%		77%	83%	87%	76%	69%	77%	80%	63%	86%	81%	72%	76%	67%
66.9%		70%	70%	67%	53%	70%	70%	75%	78%	68%	55%	67%	57%	70%
27.9%		19%	34%	32%	69%	17%	31%	34%	30%	30%	9%	22%	17%	19%
55.5%		60%	65%	44%	41%	62%	60%	46%	41%	60%	60%	58%	64%	60%
47.5%		38%	38%	60%	80%	33%	56%	55%	64%	46%	35%	40%	34%	38%
56.7%		61%	61%	53%	22%	70%	62%	48%	38%	61%	66%	59%	75%	61%
55.9%		67%	52%	65%	58%	50%	59%	61%	54%	50%	54%	54%	54%	49%
68.6%		82%	89%	86%	89%	44%	67%	67%	74%	49%	58%	62%	67%	58%
58.3%		63%	62%	62%	70%	66%	76%	62%	51%	51%	45%	41%	58%	51%
79.5%		86%	84%	84%	31%	87%	83%	90%	72%	83%	82%	80%	88%	83%
67.0%		74%	65%	65%	36%	75%	81%	75%	63%	71%	80%	79%	66%	41%
62.2%		56%	57%	60%	79%	49%	73%	76%	61%	61%	57%	50%	46%	83%
62.5%		71%	66%	66%	63%	52%	82%	72%	71%	52%	65%	50%	47%	56%
70.8%		70%	67%	76%	72%	67%	72%	65%	76%	72%	57%	72%	79%	76%
72.6%		65%	66%	63%	63%	75%	63%	76%	76%	82%	79%	74%	84%	78%
61.2%		72%	58%	72%	56%	53%	56%	52%	58%	72%	62%	63%	63%	58%
57.5%		60%	56%	57%	35%	59%	60%	62%	60%	60%	55%	64%	60%	60%
58.2%		59%	59%	62%	64%	52%	59%	58%	50%	59%	61%	61%	60%	53%
79.7%		84%	84%	90%	53%	73%	74%	90%	70%	84%	85%	83%	83%	83%
42.5%		36%	44%	46%	52%	31%	41%	59%	59%	32%	32%	43%	32%	46%
72.9%		80%	69%	69%	25%	82%	78%	82%	70%	86%	74%	75%	82%	76%
58.2%		59%	59%	61%	61%	56%	61%	61%	61%	62%	56%	56%	48%	55%
67.8%		70%	72%	72%	50%	69%	72%	72%	60%	72%	69%	69%	62%	72%
73.2%		76%	84%	84%	72%	49%	68%	76%	76%	76%	67%	80%	67%	76%
62.9%		68%	59%	59%	48%	67%	67%	65%	47%	68%	73%	71%	65%	61%
70.0%		70%	65%	57%	72%	80%	77%	66%	70%	66%	61%	73%	84%	69%
74.2%		63%	89%	85%	70%	85%	70%	76%	64%	70%	70%	68%	85%	70%
57.6%		59%	62%	50%	54%	70%	50%	55%	49%	69%	37%	57%	69%	68%
53.3%		55%	62%	61%	35%	57%	53%	52%	64%	55%	50%	50%	44%	55%
82.6%		93%	85%	85%	62%	75%	76%	91%	81%	85%	83%	90%	83%	85%
66.1%		72%	68%	58%	67%	60%	64%	70%	67%	69%	58%	63%	68%	75%
74.7%		80%	75%	75%	77%	82%	73%	76%	61%	70%	75%	80%	80%	67%
52.4%		48%	59%	47%	55%	55%	49%	53%	46%	59%	38%	51%	59%	62%
58.0%		58%	64%	66%	65%	44%	54%	57%	66%	58%	57%	55%	53%	57%
61.2%		60%	70%	59%	70%	79%	59%	61%	59%	61%	34%	45%	59%	79%
72.1%		75%	73%	73%	79%	77%	79%	79%	61%	73%	39%	77%	73%	79%
56.0%		51%	51%	63%	70%	46%	58%	65%	69%	51%	51%	51%	51%	51%
40.8%		59%	70%	56%	32%	16%	54%	51%	56%	58%	27%	25%	27%	0%
63.2%		55%	79%	69%	38%	71%	66%	74%	74%	61%	38%	79%	43%	74%
57.9%		66%	60%	53%	37%	58%	60%	59%	59%	66%	54%	61%	60%	60%
53.3%		58%	55%	52%	33%	64%	59%	49%	46%	52%	55%	53%	65%	52%
55.0%		57%	50%	50%	50%	50%	59%	59%	53%	52%	55%	52%	59%	69%
59.3%		62%	62%	61%	46%	62%	55%	57%	55%	62%	61%	57%	64%	67%
68.1%		74%	72%	72%	62%	56%	64%	73%	77%	66%	65%	64%	68%	72%
69.8%		71%	71%	76%	63%	54%	74%	89%	79%	72%	54%	74%	59%	71%
66.1%		75%	53%	53%	68%	69%	61%	69%	54%	83%	56%	56%	81%	81%
47.8%		46%	57%	59%	38%	59%	59%	59%	59%	46%	44%	59%	37%	0%
78.8%		84%	84%	77%	53%	83%	81%	87%	74%	81%	75%	83%	79%	84%
71.3%		81%	88%	67%	67%	64%	74%	74%	81%	74%	62%	67%	64%	64%
62.4%		56%	69%	58%	61%	52%	66%	62%	58%	65%	71%	62%	69%	62%
53.3%		53%	52%	52%	54%	40%	60%	55%	58%	49%	60%	59%	49%	52%
75.2%		79%	90%	91%	25%	62%	77%	77%	77%	92%	74%	75%	66%	92%
63.2%		73%	56%	56%	70%	60%	73%	72%	40%	67%	60%	71%	67%	56%
37.2%		36%	36%	41%	56%	15%	36%	43%	50%	46%	26%	35%	28%	36%
57.8%		53%	53%	60%	63%	73%	57%	53%	53%	60%	46%	67%	53%	60%
56.8%		54%	54%	62%	64%	56%	54%	65%	61%	54%	54%	54%	53%	54%
71.2%		77%	68%	68%	66%	68%	65%	75%	61%	88%	77%	69%	71%	72%
68.8%		76%	83%	70%	52%	56%	79%	64%	83%	83%	78%	75%	56%	39%
68.2%		64%	58%	64%	62%	83%	67%	59%	66%	64%	75%	70%	72%	83%
75.0%		84%	75%	75%	46%	82%	77%	83%	59%	80%	80%	82%	83%	69%
68.1%		63%	64%	79%	70%	82%	67%	67%	61%	67%	56%	77%	61%	71%
54.4%		59%	51%	49%	48%	59%	56%	60%	50%	52%	52%	52%	57%	62%