DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 C10 Dtef Global Dialogues Gd4 Country%3Abrazil C10 - Run e39e379...

Global Dialogues GD4 - Brazil (10 context Qs)

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

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4
76.4%
2.Claude Sonnet 4.5
75.4%
3.Claude Haiku 4.5
74.9%
4.GPT 4.1
73.5%
5.GPT 4.1 Mini
73.4%

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 74.9%	1st 76.4%	2nd 75.4%	12th 68.6%	11th 69.9%	6th 73.2%	9th 71.9%	4th 73.5%	5th 73.4%	13th 68.2%	10th 71.0%	8th 71.9%	7th 73.1%
70.5%		74%	81%	85%	81%	47%	70%	71%	70%	62%	74%	61%	72%	68%
56.2%		46%	53%	66%	72%	30%	48%	62%	87%	59%	53%	56%	50%	48%
81.0%		86%	86%	86%	71%	79%	84%	91%	81%	88%	78%	78%	73%	72%
67.5%		70%	70%	67%	70%	67%	61%	62%	69%	68%	69%	69%	63%	73%
64.4%		63%	71%	75%	65%	56%	64%	68%	60%	58%	59%	64%	63%	71%
76.5%		77%	85%	85%	48%	78%	81%	77%	81%	87%	90%	81%	81%	43%
68.0%		77%	80%	81%	71%	63%	74%	66%	63%	62%	66%	57%	62%	62%
85.3%		83%	78%	75%	91%	84%	91%	88%	93%	92%	68%	87%	89%	90%
71.7%		68%	84%	78%	46%	75%	77%	65%	67%	63%	80%	72%	71%	86%
72.5%		73%	61%	62%	80%	75%	77%	60%	60%	76%	82%	80%	81%	75%
78.3%		81%	80%	74%	80%	80%	76%	74%	79%	80%	75%	76%	82%	81%
63.1%		70%	65%	63%	56%	72%	58%	58%	66%	67%	50%	58%	66%	71%
85.1%		88%	91%	91%	87%	80%	77%	82%	87%	86%	90%	85%	80%	82%
55.8%		72%	78%	60%	55%	42%	56%	53%	49%	57%	38%	47%	56%	63%
55.7%		51%	53%	65%	37%	56%	63%	47%	73%	51%	55%	57%	56%	60%
79.7%		81%	83%	89%	78%	67%	89%	91%	89%	82%	62%	79%	78%	68%
80.6%		89%	87%	87%	90%	83%	79%	81%	76%	83%	60%	72%	82%	79%
69.6%		75%	77%	74%	67%	67%	78%	69%	76%	73%	43%	57%	72%	77%
64.5%		59%	62%	62%	60%	69%	54%	58%	57%	67%	64%	74%	72%	80%
77.2%		85%	79%	80%	82%	60%	82%	70%	80%	83%	72%	82%	70%	78%
76.0%		82%	78%	79%	80%	78%	84%	82%	81%	83%	53%	53%	74%	81%
86.4%		93%	88%	84%	74%	90%	77%	94%	84%	81%	88%	88%	88%	94%
73.9%		74%	79%	82%	90%	77%	80%	85%	83%	77%	58%	79%	47%	50%
45.0%		49%	49%	47%	62%	32%	43%	50%	53%	35%	41%	35%	37%	52%
75.2%		81%	79%	77%	46%	79%	69%	72%	73%	78%	84%	70%	82%	87%
83.6%		82%	84%	95%	82%	82%	81%	82%	89%	82%	82%	82%	82%	82%
78.5%		86%	83%	85%	80%	70%	80%	74%	89%	78%	66%	65%	80%	85%
72.0%		77%	78%	81%	61%	52%	79%	74%	78%	77%	70%	72%	73%	64%
77.2%		76%	83%	86%	70%	86%	76%	66%	67%	72%	67%	89%	82%	83%
58.3%		61%	65%	61%	63%	49%	63%	55%	62%	56%	59%	53%	52%	59%
74.7%		83%	84%	69%	68%	80%	77%	79%	73%	78%	65%	73%	83%	59%
80.7%		87%	85%	86%	78%	68%	89%	77%	76%	80%	80%	79%	81%	83%
51.5%		49%	55%	63%	64%	39%	51%	60%	58%	49%	38%	53%	45%	45%
64.2%		59%	66%	68%	86%	52%	74%	77%	70%	64%	55%	62%	50%	51%
76.2%		90%	71%	72%	83%	82%	81%	68%	55%	67%	83%	68%	83%	87%
74.9%		82%	86%	76%	81%	74%	76%	77%	79%	76%	59%	80%	75%	53%
83.9%		91%	85%	88%	87%	82%	85%	80%	84%	73%	86%	69%	88%	93%
66.2%		57%	70%	70%	72%	61%	51%	61%	72%	65%	66%	64%	73%	79%
76.9%		84%	82%	69%	44%	86%	79%	87%	82%	82%	80%	80%	86%	59%
73.2%		64%	72%	80%	78%	76%	65%	64%	70%	71%	77%	76%	81%	77%
79.2%		85%	78%	91%	78%	61%	84%	87%	91%	80%	62%	82%	66%	84%
72.9%		80%	76%	71%	69%	82%	77%	74%	58%	70%	66%	62%	79%	84%
69.2%		72%	74%	74%	66%	62%	72%	74%	70%	69%	62%	71%	69%	64%
67.8%		59%	64%	64%	72%	59%	82%	69%	74%	64%	81%	69%	64%	61%
71.4%		70%	75%	66%	77%	86%	81%	56%	64%	62%	69%	60%	71%	91%
77.5%		88%	77%	83%	77%	69%	75%	75%	80%	83%	69%	75%	79%	77%
65.3%		70%	68%	72%	74%	60%	74%	70%	70%	66%	41%	58%	62%	64%
80.0%		78%	100%	100%	63%	69%	78%	75%	97%	85%	74%	79%	71%	71%
77.4%		78%	79%	76%	76%	82%	79%	80%	76%	70%	77%	77%	70%	86%
68.0%		65%	73%	77%	75%	75%	62%	62%	65%	72%	61%	68%	62%	67%
73.9%		71%	68%	87%	80%	77%	73%	65%	75%	82%	54%	73%	76%	80%
62.2%		71%	71%	75%	68%	52%	73%	74%	68%	50%	42%	59%	54%	51%
55.3%		58%	66%	69%	77%	48%	43%	53%	56%	61%	43%	36%	54%	55%
83.8%		83%	86%	82%	64%	80%	89%	87%	84%	88%	88%	88%	86%	85%
73.0%		74%	78%	69%	75%	75%	75%	70%	73%	74%	68%	75%	72%	71%
70.2%		72%	74%	80%	81%	62%	73%	74%	69%	67%	66%	66%	64%	64%
40.4%		29%	49%	34%	72%	27%	41%	45%	57%	41%	18%	35%	32%	45%
71.0%		75%	74%	67%	55%	72%	69%	64%	65%	70%	73%	76%	84%	79%
58.8%		60%	56%	72%	85%	42%	61%	66%	68%	65%	45%	52%	41%	52%
60.8%		67%	65%	57%	54%	80%	65%	48%	47%	56%	64%	53%	70%	65%
77.0%		82%	91%	77%	45%	72%	84%	77%	69%	83%	81%	76%	81%	83%
65.4%		66%	73%	67%	65%	55%	67%	68%	75%	62%	66%	64%	59%	63%
89.3%		92%	95%	95%	84%	87%	90%	100%	100%	82%	76%	89%	86%	85%
77.1%		79%	79%	75%	81%	79%	70%	73%	81%	79%	77%	77%	81%	71%
77.2%		81%	82%	79%	73%	78%	77%	79%	83%	76%	83%	77%	85%	51%
84.5%		88%	92%	92%	54%	81%	89%	77%	81%	92%	83%	91%	90%	88%
64.3%		60%	72%	65%	41%	74%	67%	48%	59%	65%	73%	73%	69%	70%
79.7%		88%	84%	84%	72%	85%	74%	82%	70%	88%	69%	76%	77%	87%
70.1%		72%	70%	71%	69%	72%	75%	71%	63%	70%	65%	73%	67%	73%
79.9%		87%	87%	78%	69%	79%	70%	64%	79%	88%	88%	80%	85%	85%
76.2%		82%	80%	78%	56%	89%	81%	74%	87%	69%	72%	72%	71%	79%
68.1%		73%	63%	66%	37%	74%	76%	61%	46%	66%	89%	67%	82%	85%
76.3%		84%	88%	91%	53%	75%	68%	91%	86%	91%	61%	76%	72%	56%
68.9%		72%	79%	71%	83%	57%	66%	85%	77%	66%	38%	70%	54%	78%
67.0%		70%	69%	59%	63%	71%	68%	69%	70%	65%	65%	66%	71%	65%
75.0%		78%	85%	81%	34%	79%	84%	79%	74%	78%	77%	77%	73%	76%
68.0%		73%	69%	66%	55%	70%	70%	63%	67%	69%	71%	71%	69%	71%
84.1%		79%	86%	82%	60%	78%	89%	81%	80%	94%	94%	87%	89%	94%
84.2%		93%	95%	80%	47%	92%	90%	79%	78%	91%	87%	88%	85%	90%
76.7%		77%	79%	68%	85%	77%	84%	73%	79%	68%	71%	77%	75%	84%
89.4%		96%	85%	87%	82%	79%	90%	93%	97%	94%	90%	89%	87%	93%
75.2%		72%	85%	82%	77%	77%	71%	69%	67%	78%	63%	81%	81%	74%
78.1%		84%	79%	79%	58%	89%	77%	61%	67%	77%	90%	86%	80%	88%
85.9%		88%	94%	89%	90%	89%	81%	84%	77%	87%	83%	83%	78%	94%
72.6%		85%	67%	57%	74%	76%	78%	75%	70%	65%	78%	75%	66%	78%
77.9%		82%	83%	75%	79%	80%	78%	71%	75%	79%	79%	82%	78%	72%
62.6%		65%	64%	56%	58%	69%	66%	61%	62%	69%	49%	58%	70%	67%
65.2%		68%	66%	60%	51%	69%	70%	60%	62%	69%	58%	68%	73%	73%
59.6%		55%	75%	67%	64%	58%	55%	65%	63%	52%	29%	47%	70%	75%
84.4%		93%	97%	94%	86%	78%	89%	81%	91%	83%	52%	84%	83%	86%
75.4%		73%	72%	76%	80%	61%	84%	82%	73%	81%	77%	83%	72%	66%
53.4%		66%	58%	66%	67%	37%	48%	51%	48%	82%	50%	40%	55%	26%
70.3%		75%	86%	81%	45%	63%	62%	80%	64%	64%	65%	64%	77%	88%
78.8%		79%	80%	79%	85%	76%	78%	77%	76%	84%	82%	81%	75%	73%
60.5%		62%	65%	53%	43%	71%	64%	59%	52%	58%	62%	62%	63%	73%
82.3%		85%	86%	88%	82%	79%	79%	82%	76%	86%	80%	75%	88%	84%
71.7%		74%	75%	76%	49%	72%	71%	68%	72%	76%	76%	76%	73%	74%
82.6%		90%	91%	91%	64%	72%	86%	84%	81%	82%	86%	79%	85%	83%
79.9%		78%	82%	81%	77%	59%	80%	91%	78%	84%	80%	86%	80%	83%
80.1%		86%	82%	73%	84%	77%	72%	72%	93%	96%	75%	78%	70%	83%
64.2%		70%	74%	91%	38%	67%	63%	64%	85%	60%	57%	60%	47%	58%
78.7%		82%	83%	86%	75%	74%	79%	79%	81%	76%	75%	78%	76%	79%
76.4%		82%	73%	80%	78%	77%	72%	77%	65%	77%	81%	69%	81%	81%
71.8%		69%	74%	70%	89%	64%	73%	74%	77%	73%	58%	74%	69%	70%
73.1%		73%	74%	73%	0%	80%	67%	73%	71%	83%	81%	86%	94%	95%
67.8%		74%	77%	80%	37%	61%	70%	70%	79%	65%	66%	66%	51%	86%
66.5%		76%	62%	74%	86%	45%	58%	76%	93%	72%	42%	67%	62%	51%
69.0%		63%	67%	80%	81%	40%	67%	73%	86%	78%	61%	67%	59%	75%
72.9%		70%	74%	74%	74%	72%	76%	69%	73%	75%	75%	65%	78%	73%
81.9%		88%	87%	77%	65%	79%	86%	89%	78%	89%	77%	86%	81%	83%
67.4%		65%	71%	75%	67%	72%	67%	63%	73%	60%	68%	57%	66%	72%
73.2%		72%	72%	69%	75%	71%	74%	74%	78%	72%	79%	77%	75%	64%
79.2%		72%	78%	82%	93%	73%	86%	77%	81%	86%	82%	75%	70%	74%
74.6%		83%	84%	74%	45%	84%	75%	68%	80%	77%	79%	78%	78%	65%
70.8%		66%	77%	77%	88%	67%	65%	74%	74%	67%	59%	76%	66%	64%
70.4%		68%	72%	59%	73%	83%	66%	59%	61%	77%	75%	59%	81%	82%