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%3Abangladesh C5 - Run 8e60a35...

Global Dialogues GD4 - Bangladesh (5 context Qs)

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Efficiency & Succinctness

Social interaction

AI Safety & Robustness

Mental Health & Crisis Support

Best Models (Coverage)

1.Claude Sonnet 4.5
71.1%
2.GPT 4.1
70.9%
3.Claude Sonnet 4
70.8%
4.Mistral Medium 3
70.2%
5.Claude Haiku 4.5
70.2%

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 70.2%	3rd 70.8%	1st 71.1%	9th 66.1%	13th 62.3%	6th 69.4%	4th 70.2%	2nd 70.9%	8th 68.0%	10th 65.9%	7th 68.4%	11th 63.1%	12th 62.5%
62.5%		59%	73%	84%	78%	43%	55%	69%	66%	59%	59%	55%	54%	59%
62.8%		69%	66%	66%	61%	47%	64%	73%	59%	64%	55%	70%	55%	68%
74.8%		75%	79%	79%	69%	74%	79%	72%	69%	80%	74%	74%	69%	80%
65.5%		68%	66%	71%	70%	70%	64%	61%	59%	65%	63%	63%	68%	63%
51.6%		57%	52%	55%	66%	27%	52%	55%	63%	52%	52%	44%	44%	52%
72.7%		80%	84%	84%	82%	73%	75%	81%	71%	71%	71%	85%	50%	38%
65.4%		83%	72%	83%	65%	62%	70%	57%	55%	59%	67%	56%	59%	62%
55.8%		57%	56%	57%	61%	55%	55%	65%	36%	68%	55%	58%	49%	54%
83.2%		90%	76%	76%	89%	75%	92%	84%	77%	84%	83%	92%	87%	77%
58.9%		64%	58%	62%	60%	58%	62%	60%	60%	60%	59%	57%	53%	53%
71.7%		78%	77%	75%	41%	78%	75%	75%	80%	70%	71%	77%	71%	64%
75.2%		81%	78%	68%	78%	77%	77%	78%	88%	72%	66%	74%	66%	74%
66.5%		70%	65%	71%	69%	62%	62%	80%	73%	69%	64%	66%	57%	57%
55.7%		60%	81%	61%	70%	33%	61%	55%	51%	51%	44%	49%	47%	61%
62.3%		64%	67%	81%	44%	58%	67%	77%	82%	57%	44%	65%	44%	60%
54.5%		58%	57%	61%	59%	39%	54%	64%	56%	60%	49%	56%	50%	46%
81.5%		81%	80%	84%	88%	80%	89%	89%	80%	80%	76%	77%	76%	80%
75.4%		81%	68%	65%	77%	78%	77%	77%	70%	77%	77%	77%	77%	79%
65.0%		65%	67%	79%	69%	42%	76%	72%	84%	49%	75%	59%	59%	49%
72.6%		65%	71%	71%	76%	62%	79%	83%	71%	65%	86%	69%	73%	73%
69.9%		77%	61%	60%	61%	61%	74%	66%	66%	74%	76%	76%	76%	81%
77.2%		90%	92%	85%	79%	82%	85%	0%	85%	74%	92%	72%	72%	96%
60.8%		66%	77%	71%	49%	60%	69%	74%	75%	58%	44%	57%	54%	36%
53.0%		53%	57%	57%	60%	42%	60%	57%	57%	42%	53%	53%	42%	56%
50.2%		48%	48%	55%	32%	53%	51%	48%	51%	57%	53%	48%	53%	55%
72.0%		81%	68%	80%	75%	74%	70%	68%	70%	70%	75%	76%	65%	64%
78.2%		70%	84%	89%	84%	59%	84%	88%	80%	80%	79%	80%	79%	61%
67.8%		68%	69%	83%	67%	49%	66%	82%	83%	67%	71%	71%	49%	56%
61.5%		60%	57%	71%	72%	54%	70%	66%	73%	57%	62%	53%	51%	54%
63.4%		66%	73%	61%	59%	52%	70%	63%	78%	63%	59%	58%	59%	63%
77.0%		92%	90%	83%	49%	81%	85%	89%	85%	78%	54%	89%	83%	43%
73.5%		78%	74%	71%	79%	74%	61%	87%	75%	73%	84%	84%	68%	47%
55.2%		58%	52%	71%	85%	46%	51%	70%	61%	52%	46%	49%	33%	44%
47.6%		54%	54%	45%	74%	29%	51%	56%	56%	48%	35%	47%	31%	39%
60.0%		52%	64%	68%	60%	61%	60%	59%	67%	63%	58%	63%	52%	53%
58.8%		60%	61%	57%	61%	60%	59%	59%	55%	62%	59%	58%	55%	59%
66.5%		74%	60%	60%	52%	70%	68%	71%	60%	68%	71%	77%	74%	59%
56.4%		43%	50%	43%	55%	75%	50%	51%	52%	41%	72%	70%	71%	60%
67.9%		78%	79%	80%	58%	67%	68%	82%	85%	60%	53%	86%	59%	28%
47.0%		41%	44%	44%	47%	55%	31%	41%	47%	44%	63%	68%	51%	35%
78.8%		85%	88%	80%	69%	58%	89%	92%	69%	85%	69%	77%	76%	88%
83.5%		92%	80%	85%	78%	76%	80%	86%	94%	91%	91%	86%	66%	80%
47.1%		46%	49%	56%	44%	43%	44%	49%	43%	45%	59%	51%	33%	50%
53.5%		49%	57%	42%	55%	49%	63%	55%	52%	42%	58%	58%	58%	57%
63.2%		66%	64%	64%	65%	63%	62%	63%	64%	69%	60%	65%	60%	57%
86.2%		77%	94%	91%	90%	80%	88%	89%	90%	89%	70%	90%	91%	81%
70.7%		72%	74%	69%	59%	66%	70%	74%	74%	74%	70%	71%	73%	73%
87.5%		99%	85%	74%	92%	88%	85%	92%	96%	92%	85%	88%	85%	76%
80.5%		88%	88%	88%	46%	85%	73%	82%	88%	83%	77%	88%	81%	79%
61.3%		59%	65%	69%	73%	45%	66%	64%	62%	48%	74%	60%	56%	56%
61.6%		60%	64%	72%	56%	53%	70%	67%	65%	56%	68%	59%	50%	61%
57.5%		60%	64%	60%	27%	64%	61%	54%	72%	61%	46%	63%	60%	55%
68.7%		66%	77%	75%	81%	46%	67%	66%	77%	52%	89%	71%	66%	60%
55.9%		60%	56%	46%	74%	44%	56%	60%	65%	60%	56%	64%	44%	42%
60.0%		63%	74%	82%	45%	59%	53%	55%	62%	63%	74%	67%	46%	37%
69.9%		73%	77%	72%	52%	66%	78%	69%	87%	68%	62%	68%	62%	75%
47.5%		41%	50%	50%	63%	42%	43%	51%	49%	49%	40%	49%	41%	49%
75.4%		77%	77%	80%	77%	73%	77%	74%	77%	76%	69%	74%	69%	80%
45.5%		42%	44%	50%	72%	26%	47%	52%	50%	44%	36%	43%	34%	52%
74.4%		81%	81%	81%	54%	72%	78%	68%	60%	76%	79%	79%	79%	79%
67.8%		77%	60%	69%	73%	56%	78%	81%	73%	69%	62%	62%	66%	56%
60.5%		65%	74%	62%	62%	40%	62%	60%	71%	57%	65%	55%	65%	48%
89.7%		91%	98%	94%	90%	92%	90%	94%	98%	86%	85%	68%	95%	85%
61.7%		64%	66%	69%	66%	61%	58%	67%	70%	50%	62%	67%	58%	44%
78.2%		85%	96%	87%	85%	74%	89%	91%	85%	78%	46%	79%	85%	37%
70.2%		69%	76%	75%	48%	60%	78%	70%	97%	81%	70%	70%	52%	67%
60.5%		63%	60%	67%	78%	42%	64%	79%	64%	59%	63%	54%	42%	52%
69.9%		72%	70%	81%	78%	68%	64%	62%	81%	78%	63%	70%	51%	71%
64.0%		58%	71%	74%	68%	66%	72%	61%	59%	59%	55%	67%	51%	71%
90.5%		85%	94%	97%	92%	81%	86%	91%	85%	89%	94%	91%	94%	97%
59.8%		60%	67%	62%	58%	63%	60%	50%	63%	62%	58%	58%	58%	58%
73.5%		76%	74%	74%	56%	76%	74%	72%	80%	78%	76%	76%	79%	64%
83.2%		89%	90%	90%	73%	81%	80%	90%	79%	84%	76%	85%	85%	80%
68.6%		78%	79%	68%	52%	51%	80%	72%	77%	66%	58%	81%	64%	66%
65.3%		72%	68%	61%	41%	68%	71%	63%	62%	77%	67%	61%	67%	71%
81.2%		91%	88%	73%	59%	73%	88%	86%	67%	88%	92%	75%	87%	88%
64.8%		68%	64%	66%	52%	61%	64%	69%	61%	61%	71%	71%	70%	65%
74.7%		79%	79%	78%	78%	58%	78%	81%	79%	78%	69%	74%	62%	78%
69.1%		72%	73%	66%	30%	77%	77%	67%	72%	78%	70%	70%	78%	68%
69.5%		72%	80%	89%	62%	72%	62%	66%	66%	72%	74%	69%	73%	47%
79.6%		89%	75%	75%	72%	73%	75%	80%	94%	85%	70%	87%	75%	85%
77.7%		84%	80%	69%	78%	79%	72%	73%	85%	91%	67%	79%	73%	80%
64.9%		66%	79%	79%	64%	51%	73%	71%	76%	59%	66%	54%	56%	50%
86.2%		90%	85%	85%	82%	82%	92%	92%	89%	77%	92%	83%	75%	96%
65.8%		66%	75%	66%	61%	57%	71%	66%	62%	72%	61%	73%	67%	59%
51.4%		56%	55%	57%	58%	54%	51%	55%	58%	51%	38%	52%	47%	36%
66.2%		75%	64%	58%	74%	62%	62%	67%	62%	70%	56%	70%	72%	68%
61.2%		62%	59%	56%	63%	62%	55%	65%	55%	63%	64%	70%	64%	58%
76.1%		77%	81%	81%	70%	65%	81%	74%	81%	79%	81%	65%	87%	67%
67.8%		79%	71%	79%	55%	57%	55%	61%	73%	71%	78%	62%	79%	61%
66.0%		63%	68%	72%	73%	48%	71%	85%	61%	58%	67%	67%	59%	66%
74.2%		76%	64%	80%	95%	62%	84%	89%	84%	86%	74%	74%	74%	22%
66.4%		65%	69%	72%	31%	68%	68%	76%	86%	78%	53%	65%	61%	71%
74.8%		80%	78%	78%	77%	74%	81%	81%	71%	81%	76%	68%	61%	67%
55.3%		55%	55%	50%	50%	64%	61%	48%	50%	50%	58%	55%	62%	61%
64.8%		63%	56%	78%	60%	59%	66%	79%	66%	66%	73%	76%	56%	44%
68.8%		74%	80%	78%	30%	76%	63%	59%	85%	76%	70%	71%	63%	70%
82.8%		90%	90%	90%	46%	70%	80%	90%	73%	91%	90%	85%	85%	96%
61.8%		63%	62%	66%	97%	34%	61%	69%	78%	62%	38%	65%	52%	57%
72.3%		75%	78%	62%	77%	73%	73%	68%	76%	80%	73%	60%	70%	75%
57.9%		63%	65%	70%	22%	66%	65%	59%	70%	68%	44%	63%	36%	62%
64.8%		52%	68%	78%	84%	59%	70%	63%	67%	63%	59%	60%	59%	60%
82.5%		94%	83%	80%	94%	77%	86%	74%	88%	88%	94%	78%	70%	67%
86.1%		92%	97%	85%	89%	69%	91%	86%	85%	92%	68%	94%	85%	86%
70.4%		72%	73%	70%	82%	58%	79%	79%	65%	64%	79%	70%	59%	65%
68.8%		71%	74%	83%	58%	51%	78%	69%	78%	78%	69%	54%	54%	77%
69.5%		81%	66%	64%	70%	70%	56%	87%	80%	72%	64%	78%	56%	59%
59.3%		66%	56%	56%	80%	37%	55%	69%	78%	64%	40%	53%	60%	57%
58.7%		47%	67%	58%	65%	67%	67%	58%	51%	53%	48%	66%	58%	58%
73.1%		71%	74%	77%	73%	70%	68%	83%	90%	74%	70%	70%	62%	68%
75.8%		75%	70%	84%	75%	69%	78%	83%	70%	78%	81%	83%	70%	70%
54.8%		58%	54%	75%	66%	44%	67%	51%	67%	53%	61%	50%	40%	26%
76.2%		75%	83%	75%	82%	73%	80%	83%	80%	75%	75%	76%	68%	66%
67.1%		70%	69%	66%	69%	83%	70%	63%	64%	70%	65%	63%	67%	53%
72.5%		74%	69%	66%	71%	79%	74%	80%	69%	69%	56%	91%	75%	69%
70.2%		73%	74%	69%	73%	67%	75%	66%	65%	70%	69%	67%	70%	75%