DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd6 C10 Dtef Global Dialogues Gd6 Country%3Abangladesh C10 - Run 90d147f...

Global Dialogues GD6 - Bangladesh (10 context Qs)

DTEF: Predict response distributions for Bangladesh. Source: Global Dialogues GD6 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd6

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

AI Safety & Robustness

Data Privacy & Bodily Autonomy

Economic Disruption & Reskilling Advice

Best Models (Coverage)

1.Claude Sonnet 4.5
71.2%
2.Claude Sonnet 4
70.8%
3.GPT 4.1
70.5%
4.Mistral Medium 3
70.0%
5.Llama 4 Maverick
69.7%

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		6th 69.7%	2nd 70.8%	1st 71.2%	10th 66.9%	13th 61.3%	5th 69.7%	4th 70.0%	3rd 70.5%	9th 68.1%	8th 68.4%	12th 65.6%	11th 66.3%	7th 68.8%
25.2%		12%	27%	42%	75%	7%	18%	27%	29%	15%	15%	18%	25%	18%
68.7%		70%	73%	73%	46%	67%	74%	78%	71%	67%	68%	70%	68%	68%
48.6%		47%	55%	60%	60%	38%	47%	47%	53%	38%	46%	50%	46%	45%
62.5%		65%	68%	65%	60%	47%	64%	68%	68%	64%	59%	64%	57%	64%
79.3%		82%	83%	75%	78%	82%	78%	78%	83%	83%	78%	71%	77%	83%
73.2%		77%	75%	78%	62%	75%	72%	75%	72%	72%	81%	72%	65%	75%
63.2%		72%	62%	62%	51%	53%	62%	66%	63%	77%	66%	59%	59%	70%
72.8%		81%	70%	79%	79%	65%	78%	74%	79%	75%	67%	61%	68%	71%
92.5%		94%	100%	76%	94%	86%	94%	100%	94%	94%	94%	82%	100%	94%
82.4%		77%	82%	82%	81%	90%	85%	86%	86%	80%	76%	78%	82%	86%
89.8%		93%	93%	82%	93%	68%	93%	92%	87%	93%	92%	93%	100%	88%
59.5%		56%	56%	52%	67%	44%	67%	67%	73%	56%	56%	56%	64%	59%
73.6%		81%	81%	81%	80%	71%	71%	71%	79%	75%	51%	66%	71%	79%
83.2%		91%	80%	91%	85%	70%	80%	80%	91%	82%	87%	81%	78%	85%
45.9%		51%	45%	51%	68%	45%	46%	68%	46%	26%	57%	19%	34%	41%
81.8%		86%	85%	92%	92%	55%	79%	92%	79%	92%	92%	79%	55%	85%
74.5%		79%	81%	81%	64%	77%	79%	83%	75%	57%	83%	83%	72%	55%
51.9%		71%	57%	52%	42%	52%	46%	52%	32%	57%	63%	52%	52%	47%
56.3%		53%	50%	55%	71%	44%	62%	65%	55%	59%	53%	53%	53%	59%
69.8%		80%	80%	72%	80%	58%	77%	77%	53%	53%	81%	58%	65%	74%
67.1%		65%	69%	69%	46%	66%	65%	67%	75%	69%	69%	73%	66%	73%
51.5%		52%	58%	60%	67%	31%	58%	66%	58%	45%	64%	34%	34%	42%
82.7%		85%	85%	87%	93%	78%	87%	86%	86%	78%	81%	73%	70%	86%
73.2%		67%	76%	74%	62%	74%	80%	70%	80%	74%	76%	75%	72%	71%
32.3%		31%	34%	41%	35%	23%	37%	35%	39%	27%	30%	27%	27%	34%
66.8%		73%	61%	61%	59%	57%	81%	72%	62%	63%	67%	74%	78%	61%
61.7%		57%	57%	56%	70%	71%	59%	59%	63%	53%	66%	59%	75%	57%
56.7%		57%	82%	75%	85%	53%	51%	63%	50%	46%	40%	26%	63%	46%
61.9%		64%	64%	55%	52%	53%	68%	68%	63%	58%	63%	73%	58%	66%
70.5%		78%	78%	81%	80%	8%	74%	64%	78%	57%	80%	91%	80%	68%
83.9%		86%	76%	70%	85%	86%	87%	87%	87%	87%	90%	93%	87%	70%
49.4%		54%	54%	54%	49%	39%	54%	49%	60%	49%	46%	44%	42%	48%
77.8%		81%	81%	86%	92%	81%	71%	66%	78%	79%	71%	75%	71%	79%
70.0%		73%	80%	72%	71%	65%	77%	73%	68%	67%	67%	65%	61%	71%
73.5%		71%	76%	70%	70%	77%	72%	79%	76%	72%	62%	80%	80%	70%
69.0%		71%	72%	72%	48%	71%	71%	72%	65%	79%	66%	69%	72%	69%
70.8%		78%	78%	78%	42%	77%	70%	62%	62%	79%	75%	67%	74%	78%
72.9%		76%	83%	72%	39%	72%	76%	72%	76%	73%	75%	73%	82%	79%
51.8%		47%	47%	53%	47%	54%	62%	54%	46%	46%	57%	56%	51%	54%
56.1%		66%	66%	68%	81%	37%	52%	59%	59%	45%	50%	37%	50%	59%
60.1%		61%	72%	68%	59%	44%	53%	59%	66%	61%	72%	59%	48%	59%
55.2%		63%	63%	55%	42%	60%	42%	58%	58%	53%	55%	55%	60%	53%
54.9%		45%	48%	45%	71%	72%	50%	44%	44%	44%	48%	61%	71%	71%
66.5%		74%	78%	81%	81%	47%	68%	62%	75%	63%	60%	47%	60%	69%
62.6%		63%	57%	60%	59%	77%	47%	56%	57%	75%	49%	75%	69%	70%
52.2%		53%	44%	59%	69%	27%	55%	60%	66%	66%	44%	44%	47%	44%
76.9%		79%	80%	77%	49%	81%	76%	69%	79%	87%	78%	95%	71%	79%
62.2%		55%	63%	63%	64%	63%	60%	52%	64%	67%	65%	64%	64%	64%
73.2%		76%	77%	77%	79%	65%	80%	70%	76%	67%	77%	67%	68%	73%
73.9%		76%	77%	79%	77%	62%	76%	78%	76%	76%	74%	75%	65%	70%
55.2%		53%	57%	56%	81%	39%	63%	51%	60%	53%	51%	49%	49%	55%
72.0%		77%	70%	77%	74%	72%	73%	69%	77%	72%	72%	69%	72%	62%
72.5%		79%	64%	64%	39%	68%	74%	62%	69%	91%	75%	100%	74%	83%
61.2%		70%	59%	70%	100%	50%	70%	51%	70%	59%	46%	55%	46%	49%
71.5%		72%	70%	71%	72%	65%	72%	65%	72%	72%	75%	71%	80%	72%
62.8%		61%	64%	79%	90%	21%	60%	75%	81%	70%	37%	37%	67%	75%
76.8%		78%	79%	79%	78%	61%	81%	75%	78%	81%	75%	70%	70%	93%
75.1%		84%	83%	90%	57%	57%	84%	87%	70%	81%	77%	57%	70%	79%
82.5%		85%	92%	86%	66%	74%	100%	86%	86%	86%	83%	73%	77%	79%
75.5%		72%	75%	73%	88%	65%	82%	81%	85%	67%	75%	75%	75%	69%
66.1%		75%	75%	69%	60%	62%	63%	65%	73%	62%	64%	60%	67%	64%
70.1%		67%	78%	66%	62%	64%	78%	70%	74%	65%	78%	72%	68%	69%
54.8%		65%	46%	46%	47%	44%	54%	50%	57%	61%	66%	54%	60%	63%
68.7%		74%	68%	75%	24%	79%	68%	75%	70%	68%	68%	75%	74%	75%
72.4%		78%	78%	78%	68%	67%	78%	68%	78%	72%	68%	72%	68%	68%
77.5%		82%	75%	81%	26%	86%	91%	81%	75%	90%	76%	79%	86%	80%
78.7%		81%	88%	81%	80%	67%	76%	100%	85%	74%	74%	65%	78%	74%
78.6%		73%	73%	72%	89%	72%	86%	84%	89%	60%	85%	74%	84%	81%
83.0%		100%	86%	85%	44%	78%	91%	88%	85%	100%	74%	71%	86%	91%
71.8%		0%	81%	83%	49%	83%	81%	79%	89%	86%	79%	75%	81%	67%
66.0%		69%	65%	56%	68%	80%	54%	63%	61%	74%	52%	65%	71%	80%
63.2%		62%	63%	62%	81%	55%	60%	56%	53%	66%	70%	57%	62%	74%
59.5%		54%	65%	50%	44%	47%	57%	79%	70%	58%	73%	59%	47%	71%
69.0%		75%	75%	73%	14%	65%	73%	70%	59%	89%	74%	77%	83%	70%
70.6%		75%	71%	71%	71%	71%	66%	60%	78%	71%	71%	71%	71%	71%
67.8%		71%	63%	67%	51%	68%	74%	70%	65%	67%	70%	76%	74%	65%
98.0%		98%	98%	98%	98%	98%	98%	98%	98%	98%	98%	98%	98%	98%
66.5%		60%	72%	84%	37%	59%	74%	79%	81%	58%	72%	63%	56%	70%
75.6%		85%	85%	65%	63%	80%	71%	70%	75%	86%	77%	86%	67%	73%
56.5%		61%	66%	73%	81%	23%	66%	55%	60%	66%	44%	34%	39%	66%
74.8%		72%	60%	81%	81%	56%	59%	81%	81%	68%	90%	81%	81%	81%
81.8%		90%	87%	100%	92%	67%	75%	79%	82%	75%	82%	69%	75%	90%
59.0%		59%	67%	71%	68%	38%	67%	76%	67%	52%	72%	41%	41%	48%
63.5%		65%	63%	74%	59%	65%	71%	69%	69%	50%	68%	61%	56%	56%
83.4%		84%	98%	84%	65%	76%	81%	71%	71%	96%	98%	83%	81%	96%
74.5%		75%	83%	88%	90%	53%	75%	80%	75%	75%	81%	63%	65%	65%
65.2%		79%	67%	70%	73%	58%	75%	67%	70%	57%	56%	65%	52%	59%
70.1%		68%	69%	79%	68%	63%	69%	79%	79%	70%	70%	71%	58%	68%
63.5%		51%	67%	63%	70%	72%	72%	60%	70%	63%	51%	63%	56%	67%
87.8%		93%	81%	93%	91%	75%	79%	88%	85%	93%	93%	91%	86%	93%
76.7%		78%	74%	78%	80%	74%	74%	82%	80%	74%	83%	76%	74%	70%