DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 Dtef Global Dialogues Gd4 Country%3Abrazil - Run 8bf9289...

Global Dialogues GD4 - Brazil

DTEF: Predict response distributions for Brazil. 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

Demographic Processes

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Sonnet 4.5
74.4%
2.Claude Sonnet 4
74.3%
3.Claude Haiku 4.5
73.4%
4.Qwen3 Next 80b A3B Instruct
72.4%
5.Gemini 2.5 Flash
72.3%

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		3rd 73.4%	2nd 74.3%	1st 74.4%	5th 72.3%	11th 70.1%	8th 71.4%	12th 69.1%	7th 71.9%	6th 72.0%	13th 67.9%	9th 71.0%	10th 70.9%	4th 72.4%
63.0%		68%	69%	73%	60%	47%	64%	60%	71%	67%	66%	58%	58%	58%
60.7%		62%	61%	72%	78%	39%	50%	57%	76%	73%	56%	60%	47%	58%
81.5%		80%	86%	81%	91%	79%	84%	75%	81%	88%	78%	78%	75%	83%
66.5%		70%	70%	70%	63%	73%	61%	62%	66%	67%	60%	69%	66%	68%
69.3%		72%	74%	84%	73%	61%	73%	66%	69%	60%	68%	66%	66%	69%
80.8%		86%	86%	86%	78%	84%	81%	77%	86%	82%	78%	81%	77%	68%
47.1%			48%	58%	46%	34%	60%	31%	44%	57%	26%	57%	46%	58%
78.6%		73%	80%	73%	71%	90%	75%	73%	79%	75%	84%	80%	81%	88%
68.7%		65%	83%	82%	54%	72%	66%	55%	67%	65%	76%	64%	77%	67%
68.5%		67%	73%	58%	42%	73%	61%	59%	58%	71%	80%	80%	83%	85%
77.4%		80%	79%	79%	65%	83%	84%	75%	73%	78%	75%	78%	76%	81%
63.2%		68%	66%	70%	63%	71%	61%	63%	59%	64%	47%	62%	62%	66%
85.8%		90%	92%	92%	89%	88%	84%	80%	85%	85%	87%	85%	75%	84%
52.8%		57%	59%	59%	58%	43%	43%	52%	52%	47%	55%	47%	56%	59%
58.7%		55%	59%	59%	47%	63%	57%	54%	62%	65%	65%	61%	57%	59%
82.9%		87%	79%	87%	91%	77%	89%	86%	89%	90%	77%	79%	70%	77%
74.2%		79%	85%	85%	80%	58%	80%	73%	79%	67%	76%	64%	62%	77%
66.0%		65%	75%	71%	63%	71%	66%	63%	61%	66%	61%	69%	64%	63%
69.8%		74%	77%	77%	69%	83%	57%	55%	70%	61%	53%	68%	80%	83%
74.1%		80%	68%	68%	73%	68%	76%	69%	78%	78%	78%	78%	73%	76%
70.2%		74%	76%	73%	67%	76%	71%	73%	65%	63%	63%	75%	68%	69%
87.0%		90%	86%	77%	86%	91%	93%	87%	84%	93%	74%	88%	84%	98%
86.9%		86%	90%	85%	91%	83%	88%	90%	86%	83%	89%	89%	90%	80%
42.9%		49%	52%	44%	49%	34%	48%	48%	42%	39%	41%	35%	40%	37%
75.9%		80%	81%	77%	58%	80%	66%	73%	72%	79%	82%	77%	76%	86%
59.7%		62%	44%	65%	58%	54%	68%	51%	60%	64%	49%	63%	69%	69%
73.4%		66%	74%	78%	80%	77%	70%	74%	78%	75%	77%	68%	73%	64%
68.3%		75%	73%	76%	70%	52%	71%	70%	77%	65%	67%	71%	56%	65%
84.5%		89%	92%	92%	92%	91%	77%	77%	76%	85%	73%	85%	80%	89%
54.1%		55%	64%	65%	59%	41%	57%	51%	60%	51%	50%	52%	42%	56%
76.3%		80%	76%	75%	75%	84%	76%	70%	74%	73%	73%	73%	79%	84%
71.3%		64%	74%	62%	72%	66%	63%	68%	67%	69%	79%	79%	82%	82%
52.8%		50%	55%	59%	65%	47%	52%	62%	54%	62%	54%	45%	42%	39%
62.5%		64%	63%	76%	80%	52%	61%	59%	70%	61%	55%	62%	52%	58%
69.2%		66%	74%	71%	60%	78%	58%	60%	62%	63%	71%	79%	83%	75%
80.8%		84%	85%	82%	80%	83%	79%	82%	84%	79%	77%	79%	78%	78%
65.3%		67%	59%	54%	50%	78%	58%	59%	50%	68%	77%	82%	88%	59%
57.0%		46%	54%	69%	69%	62%	39%	49%	63%	61%	48%	48%	65%	68%
79.9%		80%	78%	74%	77%	87%	78%	71%	76%	92%	76%	76%	83%	91%
64.8%		56%	61%	68%	71%	69%	65%	57%	65%	66%	54%	64%	80%	66%
80.4%		85%	84%	85%	86%	67%	84%	83%	86%	79%	68%	83%	67%	88%
72.8%		69%	76%	76%	77%	78%	75%	72%	74%	75%	66%	62%	80%	67%
73.0%		70%	78%	73%	74%	70%	76%	72%	77%	73%	77%	69%	66%	74%
68.1%		61%	68%	57%	67%	66%	87%	78%	74%	69%	75%	69%	65%	49%
73.6%		79%	71%	71%	85%	82%	82%	67%	65%	70%	57%	70%	79%	79%
83.0%		88%	84%	80%	86%	79%	81%	83%	87%	85%	82%	83%	82%	79%
65.0%		70%	67%	71%	72%	59%	71%	62%	70%	64%	57%	63%	60%	59%
83.8%		82%	95%	86%	83%	69%	77%	73%	90%	93%	79%	95%	95%	73%
73.9%		77%	67%	69%	78%	81%	82%	75%	68%	70%	64%	77%	70%	83%
69.2%		73%	73%	77%	67%	75%	71%	68%	72%	68%	56%	68%	64%	68%
78.4%		81%	81%	91%	85%	92%	73%	71%	79%	73%	55%	73%	78%	87%
59.3%		59%	65%	68%	67%	44%	54%	61%	76%	62%	55%	58%	51%	51%
47.0%		44%	45%	51%	64%	42%	42%	43%	47%	51%	42%	42%	47%	51%
86.4%		89%	90%	83%	79%	90%	89%	91%	85%	87%	81%	84%	91%	84%
71.0%		75%	76%	69%	72%	67%	73%	71%	71%	66%	66%	73%	71%	73%
69.6%		68%	74%	78%	79%	61%	69%	67%	79%	68%	65%	65%	57%	75%
52.8%		49%	51%	54%	63%	34%	65%	60%	66%	46%	50%	50%	45%	53%
74.5%		74%	76%	74%	73%	79%	75%	67%	69%	75%	65%	75%	87%	80%
59.5%		66%	54%	74%	73%	42%	64%	60%	72%	66%	49%	52%	40%	62%
60.0%		62%	62%	62%	51%	74%	57%	55%	54%	57%	61%	61%	65%	59%
82.6%		81%	86%	86%	83%	82%	85%	80%	83%	88%	91%	69%	73%	87%
59.1%		61%	70%	68%	58%	44%	66%	57%	66%	50%	64%	51%	50%	63%
88.2%		92%	95%	92%	97%	95%	95%	94%	97%	82%	75%	75%	78%	80%
78.8%		82%	81%	82%	76%	84%	77%	72%	73%	75%	80%	80%	81%	82%
81.4%		80%	87%	82%	82%	83%	79%	84%	85%	84%	80%	80%	84%	68%
85.9%		88%	93%	93%	82%	86%	78%	80%	82%	95%	86%	86%	77%	91%
67.8%		69%	75%	69%	58%	78%	67%	57%	64%	76%	64%	68%	67%	70%
77.2%		77%	74%	80%	83%	81%	68%	73%	75%	81%	72%	72%	77%	91%
62.6%		69%	74%	76%	73%	68%	71%	69%	10%	76%	77%	75%	66%	10%
84.0%		89%	87%	87%	88%	74%	76%	82%	79%	88%	88%	86%	76%	92%
77.3%		82%	80%	77%	77%	80%	69%	77%	75%	71%	78%	78%	80%	81%
68.4%		76%	75%	60%	50%	72%	58%	50%	66%	70%	70%	77%	82%	83%
84.4%		82%	81%	88%	96%	81%	92%	92%	95%	76%	83%	76%	74%	81%
68.5%		72%	86%	85%	70%	57%	75%	83%	72%	57%	50%	60%	64%	60%
64.5%		66%	66%	64%	64%	72%	65%	59%	61%	63%	63%	63%	61%	71%
76.7%		77%	84%	81%	77%	77%	75%	72%	74%	82%	73%	75%	74%	76%
68.5%		72%	70%	71%	67%	69%	69%	71%	69%	66%	64%	71%	65%	66%
81.6%		88%	85%	83%	78%	64%	90%	79%	83%	87%	87%	77%	76%	84%
82.2%		89%	89%	73%	66%	97%	80%	75%	74%	88%	83%	88%	89%	77%
70.9%		77%	69%	65%	76%	79%	72%	64%	70%	61%	62%	76%	75%	76%
93.7%		96%	95%	94%	95%	96%	85%	95%	93%	96%	93%	94%	96%	90%
75.4%		81%	77%	84%	75%	79%	79%	68%	80%	74%	61%	73%	73%	76%
77.4%		87%	85%	70%	66%	88%	73%	65%	67%	80%	82%	80%	80%	83%
85.1%		87%	86%	91%	80%	88%	94%	89%	75%	89%	71%	83%	84%	89%
70.2%		73%	75%	69%	75%	77%	66%	70%	57%	64%	59%	74%	72%	82%
81.9%		85%	86%	81%	80%	86%	80%	80%	76%	84%	82%	82%	82%	81%
63.4%		65%	67%	67%	66%	66%	59%	58%	57%	65%	53%	66%	65%	70%
70.8%		74%	71%	69%	74%	71%	69%	66%	70%	71%	65%	72%	73%	76%
61.8%		65%	69%	71%	78%	66%	50%	52%	62%	64%	33%	52%	65%	76%
85.2%		92%	88%	89%	81%	75%	84%	79%	86%	88%	94%	72%	91%	89%
77.9%		77%	74%	78%	79%	68%	83%	78%	85%	80%	76%	83%	71%	81%
38.6%		37%	43%	37%	51%	35%	33%	27%	36%	39%	39%	37%	55%	33%
71.7%		80%	73%	75%	66%	60%	71%	69%	80%	65%	74%	75%	75%	69%
79.8%		83%	77%	84%	80%	65%	84%	83%	87%	81%	85%	77%	73%	79%
61.4%		61%	61%	63%	56%	67%	65%	65%	56%	53%	62%	62%	66%	61%
77.8%		72%	82%	68%	75%	81%	71%	67%	79%	75%	81%	85%	90%	86%
72.2%		73%	76%	76%	71%	75%	66%	68%	72%	73%	73%	74%	72%	69%
86.3%		93%	91%	91%	87%	82%	87%	89%	85%	86%	79%	86%	78%	88%
84.8%		90%	85%	91%	84%	65%	87%	88%	89%	88%	76%	92%	75%	93%
74.5%		73%	83%	75%	82%	73%	65%	72%	76%	84%	66%	66%	80%	73%
62.5%		63%	70%	77%	63%	61%	59%	67%	71%	59%	60%	58%	49%	56%
74.5%		70%	81%	81%	82%	69%	74%	73%	79%	76%	75%	75%	61%	73%
48.2%		59%	37%	48%	51%	37%	55%	42%	41%	53%	36%	56%	60%	51%
74.8%		74%	72%	70%	83%	68%	73%	74%	76%	79%	79%	74%	78%	73%
85.6%		88%	85%	80%	87%	88%	85%	79%	84%	86%	84%	86%	89%	92%
74.5%		81%	84%	82%	86%	59%	83%	74%	83%	65%	51%	66%	72%	82%
70.2%		76%	66%	78%	82%	47%	78%	73%	90%	78%	68%	60%	51%	65%
75.0%		73%	73%	83%	90%	50%	84%	75%	89%	85%	67%	72%	64%	70%
62.1%		70%	69%	75%	0%	60%	68%	69%	72%	64%	49%	64%	74%	73%
85.2%		87%	89%	88%	79%	89%	88%	85%	89%	85%	81%	81%	76%	91%
56.8%		60%	56%	52%	49%	63%	50%	51%	48%	47%	63%	66%	69%	65%
76.2%		72%	76%	76%	79%	68%	82%	79%	82%	79%	70%	83%	74%	70%
65.9%		65%	63%	71%	70%	57%	73%	59%	62%	75%	57%	64%	75%	66%
79.2%		80%	81%	81%	80%	87%	80%	69%	73%	80%	79%	79%	82%	79%
69.2%		59%	79%	80%	81%	62%	64%	80%	75%	67%	51%	74%	70%	57%
71.8%		68%	70%	65%	75%	90%	76%	71%	73%	69%	69%	69%	75%	63%