DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 Ctx Dtef Global Dialogues Gd4 Country%3Achile Ctx - Run 7af3c69...

Global Dialogues GD4 - Chile (with context)

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

Best Models (Coverage)

1.Claude Sonnet 4.5
80.3%
2.Claude Sonnet 4
79.7%
3.GPT 4.1
78.8%
4.Mistral Medium 3
78.3%
5.Claude Haiku 4.5
77.5%

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 77.5%	2nd 79.7%	1st 80.3%	6th 77.2%	12th 71.2%	8th 75.8%	4th 78.3%	3rd 78.8%	7th 76.7%	13th 68.4%	10th 72.1%	11th 71.8%	9th 75.8%
75.3%		70%	80%	80%	74%	68%	72%	78%	81%	73%	79%	75%	70%	79%
69.8%		82%	78%	84%	90%	55%	71%	82%	85%	60%	44%	61%	44%	71%
72.1%		70%	77%	77%	68%	76%	75%	85%	84%	64%	59%	77%	74%	51%
65.7%		75%	58%	67%	41%	75%	68%	76%	76%	67%	70%	52%	77%	52%
67.0%		70%	76%	74%	59%	63%	64%	66%	72%	67%	63%	71%	62%	64%
80.5%		84%	84%	84%	81%	83%	81%	81%	87%	78%	78%	75%	73%	78%
70.8%		83%	90%	85%	70%	61%	68%	69%	64%	65%	65%	65%	71%	65%
83.8%		84%	82%	83%	89%	88%	80%	88%	88%	90%	88%	69%	81%	79%
62.7%		70%	77%	76%	28%	79%	57%	38%	55%	49%	75%	57%	67%	87%
52.1%		56%	52%	52%	36%	71%	41%	65%	45%	51%	27%	51%	51%	79%
83.8%		85%	88%	88%	84%	78%	79%	90%	91%	84%	84%	79%	79%	81%
84.2%		80%	77%	84%	86%	80%	87%	86%	86%	86%	90%	86%	81%	86%
78.2%		78%	78%	78%	78%	80%	78%	78%	78%	78%	78%	78%	78%	78%
53.8%		52%	64%	64%	57%	45%	46%	44%	51%	64%	55%	49%	54%	54%
66.5%		68%	79%	47%	82%	49%	56%	85%	80%	70%	46%	41%	82%	79%
62.5%		62%	65%	73%	69%	48%	66%	55%	85%	83%	57%	43%	36%	71%
89.2%		96%	87%	97%	92%	72%	85%	96%	92%	92%	95%	86%	81%	88%
90.3%		94%	92%	94%	93%	87%	92%	89%	95%	97%	59%	93%	96%	93%
83.0%		78%	78%	81%	85%	77%	83%	84%	84%	85%	82%	85%	92%	85%
75.2%		78%	75%	77%	68%	54%	78%	72%	74%	85%	73%	90%	77%	77%
89.8%		83%	83%	89%	93%	89%	82%	86%	94%	96%	93%	93%	93%	93%
90.1%		86%	92%	92%	88%	89%	95%	92%	92%	88%	88%	92%	89%	88%
84.9%		88%	90%	89%	83%	82%	86%	86%	88%	82%	83%	81%	82%	84%
68.5%		79%	73%	83%	78%	48%	71%	65%	83%	78%	52%	58%	46%	76%
71.8%		60%	74%	73%	69%	74%	76%	67%	82%	78%	74%	68%	63%	76%
74.5%		78%	82%	85%	69%	74%	66%	74%	69%	78%	72%	74%	74%	74%
81.8%		81%	85%	81%	86%	86%	80%	91%	89%	75%	75%	85%	75%	75%
65.5%		55%	57%	66%	65%	68%	64%	64%	79%	67%	67%	58%	65%	77%
70.6%		78%	85%	84%	83%	68%	10%	78%	94%	81%	62%	68%	65%	62%
82.6%		79%	82%	82%	87%	78%	82%	89%	85%	80%	88%	83%	74%	85%
81.1%		83%	81%	80%	84%	80%	75%	85%	81%	81%	81%	81%	81%	81%
86.7%		92%	86%	87%	94%	83%	92%	90%	90%	90%	77%	79%	80%	87%
80.5%		86%	85%	87%	87%	70%	83%	94%	88%	83%	84%	58%	67%	75%
78.1%		82%	78%	90%	92%	60%	82%	82%	90%	83%	77%	81%	51%	67%
75.5%		76%	83%	81%	80%	71%	73%	76%	62%	75%	76%	77%	74%	77%
87.5%		88%	91%	87%	86%	84%	78%	93%	84%	90%	90%	87%	91%	88%
75.7%		82%	81%	82%	74%	70%	69%	76%	81%	74%	69%	82%	70%	74%
94.2%		86%	97%	97%	86%	95%	95%	95%	97%	97%	95%	95%	95%	95%
84.0%		83%	85%	85%	79%	86%	80%	83%	79%	78%	78%	90%	93%	93%
94.1%		95%	95%	83%	95%	95%	95%	95%	95%	95%	95%	95%	95%	95%
74.4%		90%	90%	64%	70%	73%	81%	89%	69%	68%	41%	87%	66%	79%
82.2%		88%	83%	97%	79%	67%	93%	78%	65%	88%	96%	71%	93%	71%
71.6%		82%	75%	82%	80%	58%	68%	80%	83%	73%	48%	58%	69%	75%
60.7%		69%	66%	55%	60%	61%	65%	61%	69%	58%	55%	71%	49%	50%
71.5%		71%	89%	76%	79%	83%	91%	86%	76%	44%	44%	47%	67%	77%
75.5%		74%	75%	75%	71%	71%	86%	79%	76%	69%	67%	74%	83%	82%
79.5%		71%	85%	80%	88%	87%	89%	79%	95%	72%	64%	70%	75%	78%
77.5%		87%	87%	73%	77%	10%	87%	77%	73%	77%	87%	87%	98%	87%
85.4%		88%	84%	90%	95%	84%	88%	84%	84%	95%	56%	95%	79%	88%
83.9%		85%	92%	81%	86%	77%	80%	84%	82%	85%	85%	85%	84%	85%
88.5%		85%	84%	87%	86%	84%	93%	97%	89%	92%	92%	86%	90%	86%
51.5%		47%	63%	82%	87%	29%	71%	45%	75%	50%	26%	29%	25%	41%
69.2%		71%	74%	75%	67%	53%	68%	67%	70%	71%	71%	71%	71%	71%
56.7%		65%	64%	76%	79%	43%	66%	53%	64%	63%	57%	46%	19%	42%
84.0%		84%	84%	84%	84%	84%	84%	84%	84%	84%	84%	84%	84%	84%
78.2%		82%	80%	84%	86%	79%	74%	89%	78%	78%	75%	68%	68%	75%
45.4%		53%	45%	47%	78%	38%	49%	56%	59%	29%	13%	36%	47%	40%
78.0%		78%	78%	78%	78%	78%	78%	78%	78%	78%	78%	78%	78%	78%
68.5%		65%	70%	82%	78%	43%	69%	63%	82%	82%	78%	68%	33%	78%
76.5%		84%	81%	82%	61%	73%	84%	81%	79%	76%	76%	77%	54%	87%
70.2%		82%	74%	70%	62%	74%	81%	61%	80%	73%	52%	79%	69%	55%
78.7%		70%	84%	95%	70%	79%	83%	88%	78%	79%	70%	73%	81%	73%
84.9%		85%	89%	88%	80%	88%	88%	91%	91%	80%	84%	80%	80%	80%
82.3%		83%	87%	85%	83%	83%	86%	87%	84%	80%	76%	76%	80%	80%
85.9%		87%	90%	87%	88%	87%	86%	85%	86%	86%	82%	82%	85%	86%
60.2%		61%	62%	74%	74%	42%	71%	66%	71%	73%	43%	42%	35%	69%
64.1%		72%	66%	67%	71%	64%	67%	77%	80%	62%	46%	44%	63%	54%
66.7%		65%	84%	76%	60%	64%	60%	61%	63%	73%	62%	65%	58%	76%
75.1%		74%	86%	79%	81%	81%	70%	74%	77%	78%	50%	75%	77%	74%
84.5%		78%	90%	92%	59%	90%	87%	93%	89%	73%	69%	91%	97%	90%
69.6%		69%	69%	77%	69%	69%	69%	69%	69%	69%	69%	69%	69%	69%
61.2%		73%	70%	77%	48%	75%	63%	32%	59%	62%	24%	89%	48%	76%
80.9%		72%	87%	90%	81%	74%	86%	91%	91%	91%	43%	72%	91%	83%
58.2%		74%	77%	73%	96%	44%	43%	72%	80%	66%	30%	26%	27%	48%
77.2%		79%	83%	79%	76%	83%	69%	79%	74%	69%	76%	79%	79%	78%
69.3%		74%	71%	74%	73%	61%	75%	65%	69%	68%	68%	68%	64%	71%
79.1%		84%	89%	93%	83%	80%	80%	80%	87%	70%	37%	78%	76%	91%
78.7%		81%	82%	75%	78%	79%	78%	82%	80%	82%	73%	77%	79%	77%
78.2%		74%	81%	81%	75%	82%	75%	86%	81%	78%	75%	78%	75%	76%
84.0%		84%	84%	84%	84%	84%	84%	84%	84%	84%	84%	84%	84%	84%
83.8%		80%	90%	95%	80%	80%	90%	83%	92%	80%	80%	80%	80%	80%
89.2%		94%	93%	95%	94%	79%	90%	87%	87%	86%	87%	94%	87%	86%
77.5%		91%	81%	68%	72%	80%	81%	84%	66%	82%	60%	82%	80%	80%
90.7%		90%	94%	96%	91%	87%	96%	96%	83%	83%	95%	92%	81%	95%
85.2%		58%	87%	93%	85%	86%	92%	87%	89%	94%	82%	85%	84%	85%
72.2%		79%	71%	73%	66%	68%	66%	74%	71%	74%	77%	69%	77%	74%
72.3%		77%	84%	82%	76%	73%	82%	78%	79%	78%	56%	56%	63%	56%
80.2%		82%	78%	83%	80%	83%	82%	78%	78%	84%	69%	74%	88%	83%
71.6%		81%	91%	94%	81%	39%	71%	74%	61%	84%	78%	57%	57%	63%
77.3%		89%	83%	85%	85%	67%	89%	88%	88%	89%	44%	60%	53%	85%
65.8%		64%	63%	70%	86%	75%	55%	71%	53%	75%	66%	55%	65%	58%
71.1%		79%	82%	80%	84%	56%	47%	75%	70%	85%	84%	62%	51%	69%
65.2%		75%	79%	66%	50%	75%	53%	71%	61%	62%	36%	70%	73%	76%
76.0%		75%	73%	73%	74%	81%	76%	76%	83%	80%	76%	73%	74%	74%
59.5%		65%	59%	73%	48%	57%	75%	54%	45%	63%	40%	54%	63%	77%
80.1%		75%	82%	84%	79%	79%	88%	95%	84%	77%	69%	81%	74%	74%
74.2%		74%	80%	76%	68%	77%	73%	60%	64%	73%	79%	79%	82%	79%
85.5%		82%	85%	82%	90%	84%	82%	86%	85%	86%	86%	83%	91%	90%
66.0%		82%	81%	82%	81%	39%	76%	73%	82%	53%	35%	66%	53%	55%
73.2%		82%	83%	80%	82%	63%	57%	80%	67%	80%	82%	52%	70%	73%
67.5%		70%	75%	86%	62%	42%	80%	80%	76%	75%	42%	48%	84%	57%
76.0%		70%	76%	82%	72%	81%	76%	79%	78%	72%	78%	72%	73%	79%
77.4%		76%	76%	79%	73%	75%	80%	78%	76%	75%	78%	84%	78%	78%
86.8%		82%	82%	89%	84%	81%	83%	95%	82%	94%	81%	95%	91%	90%
82.0%		85%	83%	76%	79%	84%	84%	82%	81%	84%	78%	85%	80%	85%
82.9%		85%	84%	86%	87%	71%	83%	85%	92%	87%	83%	83%	70%	82%
55.5%		66%	51%	62%	75%	31%	42%	68%	71%	62%	52%	41%	49%	52%
73.0%		75%	80%	84%	86%	59%	75%	89%	82%	62%	52%	73%	80%	52%
71.4%		67%	73%	70%	67%	71%	80%	73%	72%	77%	65%	73%	71%	69%
72.7%		78%	82%	76%	85%	63%	72%	82%	84%	87%	50%	52%	68%	66%
86.4%		86%	93%	88%	86%	87%	83%	88%	87%	92%	68%	89%	89%	87%
80.6%		85%	86%	75%	78%	86%	76%	79%	81%	78%	85%	70%	83%	86%
74.5%		69%	79%	68%	74%	68%	85%	91%	81%	74%	74%	61%	74%	71%
79.0%		78%	78%	82%	84%	83%	77%	84%	82%	79%	69%	78%	77%	76%
87.3%		97%	88%	97%	97%	75%	97%	88%	97%	97%	75%	79%	51%	97%
74.5%		69%	83%	86%	69%	77%	75%	73%	69%	69%	69%	69%	69%	91%