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%3Achile C5 - Run b82f0e6...

Global Dialogues GD4 - Chile (5 context Qs)

DTEF: Predict response distributions for Chile. 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

Mental Health & Crisis Support

Economic Disruption & Reskilling Advice

Best Models (Coverage)

1.Claude Sonnet 4
74.3%
2.Claude Haiku 4.5
73.1%
3.Claude Sonnet 4.5
73.0%
4.Gemini 2.5 Flash
73.0%
5.GPT 4.1
72.8%

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		2nd 73.1%	1st 74.3%	3rd 73.0%	4th 73.0%	12th 68.3%	10th 70.7%	8th 71.5%	5th 72.8%	6th 71.9%	13th 67.2%	11th 70.0%	9th 71.5%	7th 71.8%
69.4%		68%	76%	78%	77%	49%	72%	73%	71%	70%	67%	65%	71%	65%
58.3%		57%	58%	60%	85%	35%	51%	61%	75%	60%	54%	57%	52%	53%
87.2%		93%	95%	93%	80%	75%	93%	91%	96%	89%	86%	86%	80%	76%
68.7%		71%	73%	72%	68%	69%	65%	62%	68%	72%	65%	68%	66%	74%
54.5%		62%	59%	57%	50%	48%	57%	57%	50%	53%	52%	53%	53%	58%
77.7%		82%	84%	79%	65%	81%	79%	82%	80%	80%	78%	82%	76%	62%
72.4%		88%	78%	78%	76%		82%	69%	67%	68%	65%	65%	68%	65%
75.4%		76%	88%	86%	55%	69%	68%	71%	77%	71%	79%	79%	79%	82%
69.1%		73%	73%	56%	70%	76%	77%	57%	70%	74%	66%	69%	71%	66%
77.4%		76%	81%	80%	75%	87%	64%	64%	79%	86%	86%	82%	82%	64%
73.9%		75%	70%	71%	75%	73%	74%	74%	72%	75%	72%	72%	79%	79%
79.8%		87%	81%	81%	80%	86%	65%	76%	86%	78%	58%	74%	94%	92%
78.0%		81%	73%	83%	74%	84%	72%	81%	73%	80%	79%	75%	80%	79%
57.4%		64%	73%	62%	50%	49%	62%	52%	51%	61%	48%	48%	63%	63%
57.1%		61%	59%	59%	40%	51%	60%	78%	59%	57%	57%	57%	47%	57%
45.0%		45%	39%	51%	70%	32%	47%	53%	56%	48%	34%	41%	34%	35%
92.1%		89%	89%	89%	87%	92%	97%	96%	92%	96%	95%	86%	92%	97%
71.7%		80%	63%	61%	78%	69%	74%	64%	61%	78%	77%	84%	73%	70%
72.9%		69%	69%	67%	78%	70%	67%	74%	71%	81%	65%	79%	81%	77%
87.0%		89%	87%	85%	90%	75%	91%	86%	94%	80%	93%	95%	88%	78%
74.0%		79%	67%	67%	78%	67%	78%	71%	65%	75%	82%	78%	80%	75%
90.3%		93%	88%	95%	89%	89%	83%	92%	94%	89%	88%	93%	89%	92%
76.8%		83%	79%	73%	74%	82%	77%	76%	79%	78%	77%	77%	84%	59%
48.2%		52%	68%	60%	58%	42%	48%	53%	56%	36%	34%	35%	38%	47%
66.6%		74%	70%	70%	67%	70%	61%	61%	77%	65%	60%	60%	66%	65%
75.4%		80%	70%	72%	77%	77%	75%	75%	72%	74%	74%	81%	81%	72%
82.8%		79%	82%	82%	75%	83%	85%	81%	83%	84%	85%	84%	87%	87%
72.8%		72%	70%	68%	76%	62%	71%	73%	75%	78%	76%	75%	76%	74%
83.2%		81%	85%	87%	86%	74%	85%	85%	87%	87%	79%	85%	82%	79%
79.0%		85%	78%	81%	81%	69%	79%	78%	80%	80%	79%	77%	79%	81%
67.3%		67%	77%	62%	60%	72%	65%	67%	67%	65%	69%	61%	73%	70%
78.8%		78%	87%	91%	88%	67%	75%	81%	86%	69%	69%	79%	72%	83%
81.5%		80%	85%	85%	84%	81%	86%	88%	85%	86%	70%	78%	77%	75%
53.4%		50%	51%	61%	82%	48%	57%	63%	65%	55%	35%	45%	40%	42%
65.2%		78%	76%	63%	65%	60%	66%	61%	61%	61%	61%	66%	64%	66%
77.3%		76%	79%	65%	77%	80%	73%	79%	72%	83%	84%	73%	83%	81%
64.8%		65%	73%	73%	61%	55%	62%	70%	69%	65%	57%	65%	62%	65%
65.9%		60%	72%	71%	80%	67%	61%	52%	72%	60%	51%	63%	69%	79%
75.4%		78%	82%	64%	66%	84%	71%	69%	72%	70%	86%	63%	86%	89%
55.3%		43%	49%	62%	52%	60%	45%	48%	57%	63%	63%	60%	65%	52%
73.8%		77%	77%	84%	73%	63%	77%	87%	84%	75%	59%	65%	65%	73%
83.2%		88%	90%	90%	72%	92%	74%	85%	67%	83%	73%	73%	97%	97%
68.4%		67%	68%	68%	61%	63%	70%	78%	65%	73%	66%	73%	71%	66%
53.9%		52%	57%	56%	51%	48%	61%	57%	56%	43%	53%	56%	61%	50%
79.8%		83%	86%	86%	80%	81%	81%	77%	80%	76%	78%	74%	80%	76%
84.9%		75%	89%	93%	79%	76%	85%	86%	92%	88%	81%	78%	91%	91%
77.5%		80%	83%	80%	83%	71%	81%	82%	78%	71%	76%	76%	75%	72%
88.5%		96%	95%	98%	80%	79%	89%	84%	95%	95%	77%	98%	92%	73%
83.5%		93%	85%	77%	74%	79%	86%	82%	84%	71%	91%	91%	80%	93%
68.3%		66%	66%	72%	84%	76%	60%	60%	68%	66%	56%	76%	74%	64%
78.9%		80%	78%	74%	86%	78%	71%	77%	85%	83%	65%	84%	82%	83%
37.0%		36%	36%	46%	61%	27%	35%	40%	42%	38%	23%	36%	28%	33%
66.6%		67%	73%	77%	65%	68%	64%	65%	66%	67%	65%	59%	63%	67%
44.8%		43%	46%	43%	69%	35%	43%	51%	43%	44%	46%	38%	41%	41%
73.0%		76%	80%	66%	71%	76%	78%	75%	77%	69%	61%	69%	71%	80%
83.0%		88%	87%	82%	75%	72%	89%	91%	83%	89%	72%	78%	82%	91%
37.4%		25%	43%	43%	78%	22%	42%	37%	42%	36%	35%	36%	18%	29%
66.5%		70%	67%	64%	67%	66%	64%	61%	61%	70%	57%	71%	74%	72%
40.7%		40%	40%	45%	60%	26%	43%	44%	47%	42%	30%	37%	33%	42%
70.3%		75%	69%	71%	58%	88%	73%	61%	59%	70%	73%	67%	73%	77%
70.1%		73%	73%	76%	82%	58%	72%	71%	83%	85%	57%	57%	66%	58%
79.3%		83%	84%	94%	87%	53%	82%	81%	86%	74%	77%	71%	80%	79%
86.8%		85%	98%	94%	82%	91%	97%	89%	97%	88%	70%	79%	78%	81%
75.2%		82%	82%	76%	46%	79%	78%	74%	74%	76%	76%	78%	77%	80%
76.2%		82%	79%	72%	75%	81%	78%	78%	77%	78%	71%	76%	82%	62%
69.0%		72%	68%	70%	79%	58%	74%	84%	68%	79%	59%	54%	53%	79%
73.2%		76%	76%	76%	81%	60%	77%	82%	71%	76%	75%	64%	66%	72%
71.6%		78%	83%	83%	67%	74%	60%	68%	77%	73%	60%	63%	64%	81%
76.1%		78%	73%	75%	74%	68%	74%	75%	74%	81%	81%	77%	82%	77%
91.5%		92%	92%	93%	92%	90%	95%	93%	93%	89%	92%	91%	90%	87%
70.5%		69%	71%	65%	74%	78%	66%	58%	80%	60%	71%	76%	70%	79%
80.5%		82%	82%	68%	85%	89%	79%	66%	78%	74%	88%	82%	87%	86%
83.0%		91%	87%	93%	63%	64%	82%	89%	94%	89%	86%	86%	83%	72%
46.1%		44%	57%	59%	53%	44%	48%	61%	59%	40%	31%	34%	32%	37%
65.8%		66%	76%	59%	76%	65%	63%	50%	65%	64%	61%	64%	65%	81%
66.6%		64%	77%	73%	58%	73%	69%	60%	56%	73%	66%	67%	65%	65%
73.4%		76%	75%	77%	75%	83%	70%	68%	72%	66%	71%	71%	71%	79%
79.7%		87%	80%	82%	69%	63%	85%	86%	82%	84%	79%	79%	83%	77%
65.9%		67%	67%	65%	42%	67%	67%	68%	66%	64%	66%	66%	77%	75%
76.5%		83%	81%	64%	85%	82%	79%	75%	74%	64%	67%	83%	73%	84%
89.6%		90%	90%	93%	89%	93%	95%	92%	86%	89%	88%	85%	93%	82%
75.0%		78%	73%	78%	79%	89%	64%	70%	77%	78%	50%	72%	80%	87%
78.6%		81%	83%	70%	46%	85%	73%	77%	67%	86%	86%	89%	88%	91%
90.2%		98%	84%	91%	85%	83%	86%	94%	87%	95%	93%	93%	83%	100%
86.3%		80%	94%	79%	85%	91%	91%	88%	97%	80%	80%	87%	92%	78%
59.9%		61%	65%	55%	60%	62%	62%	55%	57%	63%	52%	59%	60%	68%
64.9%		68%	75%	71%	65%	62%	63%	60%	63%	64%	53%	62%	68%	70%
81.4%		84%	74%	76%	77%	83%	76%	80%	76%	83%	90%	89%	86%	84%
57.0%		62%	71%	71%	80%	48%	49%	56%	56%	45%	28%	46%	59%	70%
76.8%		71%	82%	79%	87%	71%	79%	75%	78%	77%	62%	76%	82%	79%
75.8%		69%	74%	82%	83%	65%	76%	85%	77%	77%	74%	76%	77%	71%
50.9%		66%	82%	69%	76%	30%	35%	46%	57%	64%	31%	31%	36%	39%
69.5%		71%	81%	77%	44%	66%	77%	74%	77%	73%	68%	65%	52%	78%
73.7%		71%	64%	66%	79%	75%	73%	71%	70%	76%	69%	81%	81%	82%
57.5%		62%	63%	56%	62%	64%	59%	50%	52%	53%	51%	53%	62%	61%
78.1%		87%	90%	75%	91%	73%	70%	72%	73%	77%	77%	73%	78%	79%
64.6%		61%	63%	64%	65%	68%	56%	52%	63%	70%	67%	68%	70%	73%
84.8%		90%	94%	81%	56%	85%	90%	80%	81%	81%	94%	88%	91%	91%
56.8%		53%	66%	64%	78%	32%	57%	65%	71%	61%	45%	47%	50%	49%
62.2%		67%	63%	63%	70%	55%	52%	50%	60%	67%	45%	56%	81%	79%
57.7%		54%	67%	83%	44%	46%	57%	74%	64%	53%	47%	63%	46%	52%
87.8%		84%	86%	87%	94%	81%	86%	91%	84%	89%	89%	85%	91%	95%
76.4%		76%	76%	68%	80%	78%	81%	69%	76%	76%	76%	77%	79%	81%
87.5%		81%	86%	84%	94%	81%	89%	93%	80%	82%	97%	86%	95%	89%
69.9%		66%	57%	73%	65%	86%	63%	64%	68%	76%	50%	72%	85%	84%
80.3%		90%	76%	83%	71%	69%	75%	81%	94%	92%	80%	80%	70%	83%
47.8%		57%	38%	16%	88%	39%	48%	67%	66%	62%	31%	41%	33%	36%
66.2%		66%	62%	75%	84%	41%	61%	71%	81%	73%	60%	62%	60%	65%
71.5%		72%	72%	79%	74%	76%	72%	67%	73%	72%	60%	74%	69%	69%
75.5%		74%	74%	85%	72%	76%	72%	86%	74%	78%	77%	77%	72%	65%
74.9%		85%	88%	88%	77%	70%	65%	69%	72%	67%	71%	71%	73%	78%
82.2%		83%	86%	81%	80%	75%	83%	86%	84%	79%	87%	88%	86%	71%
70.2%		69%	74%	73%	82%	66%	74%	73%	72%	72%	72%	61%	63%	61%
77.1%		77%	81%	72%	75%	77%	76%	78%	73%	76%	76%	78%	86%	77%
74.0%		65%	78%	76%	87%	76%	76%	78%	78%	73%	63%	77%	69%	66%
61.0%		65%	57%	56%	71%	70%	54%	54%	58%	58%	57%	61%	69%	63%