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%3Akorea South - Run 2fdfb96...

Global Dialogues GD4 - Korea South

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

AI Safety & Robustness

Social interaction

Best Models (Coverage)

1.Claude Sonnet 4.5
73.0%
2.Claude Sonnet 4
73.0%
3.Claude Haiku 4.5
72.3%
4.GPT 4.1
71.3%
5.Llama 4 Maverick
71.1%

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 72.3%	2nd 73.0%	1st 73.0%	9th 69.0%	8th 69.2%	5th 71.1%	12th 67.4%	4th 71.3%	6th 69.8%	13th 64.9%	7th 69.5%	11th 68.1%	10th 68.7%
67.9%		73%	76%	81%	76%	49%	74%	72%	68%	70%	68%	53%	64%	59%
70.5%		74%	78%	77%	73%	55%	74%	67%	65%	77%	69%	70%	64%	74%
72.8%		74%	74%	80%	69%	71%	77%	69%	77%	77%	64%	73%	67%	74%
63.9%		71%	67%	70%	67%	61%	71%	63%	63%	60%	58%	58%	59%	63%
66.8%		71%	72%	76%	72%	52%	68%	69%	72%	64%	67%	62%	60%	64%
79.0%		82%	82%	80%	78%	82%	83%	73%	85%	78%	84%	89%	73%	58%
54.5%		70%	59%	59%	59%	41%	60%	39%	41%	59%	27%	59%	59%	76%
63.5%		56%	72%	72%	53%	68%	55%	53%	68%	53%	74%	69%	72%	61%
80.4%		77%	81%	86%	87%	82%	83%	74%	87%	64%	83%	83%	80%	78%
73.6%		79%	70%	50%	88%	78%	63%	57%	90%	88%	54%	84%	77%	79%
64.2%		70%	70%	68%	41%	69%	63%	57%	60%	70%	69%	67%	61%	69%
64.9%		68%	72%	69%	62%	66%	59%	68%	71%	69%	50%	64%	62%	64%
68.0%		69%	72%	74%	71%	66%	71%	62%	70%	66%	63%	66%	67%	67%
72.2%		77%	77%	77%	80%	57%	74%	77%	57%	62%	70%	77%	77%	77%
47.2%		47%	56%	51%	31%	54%	47%	41%	48%	52%	47%	43%	48%	49%
87.5%		89%	93%	86%	69%	87%	89%	90%	86%	90%	88%	89%	92%	90%
69.8%		73%	68%	69%	74%	65%	72%	79%	69%	67%	68%	69%	65%	69%
70.4%		66%	82%	76%	76%	62%	78%	66%	76%	64%	63%	66%	65%	75%
52.6%		54%	57%	50%	51%	57%	50%	51%	64%	43%	44%	53%	57%	53%
63.8%		66%	67%	61%	64%	61%	66%	66%	61%	66%	61%	68%	57%	66%
71.9%		75%	82%	83%	76%	82%	71%	66%	76%	64%	63%	70%	61%	66%
84.0%		85%	87%	81%	84%	87%	90%	85%	80%	84%	78%	82%	84%	85%
81.5%		85%	83%	83%	90%	83%	89%	79%	78%	77%	86%	87%	81%	58%
55.2%		61%	62%	60%	60%	56%	57%	54%	62%	62%	46%	39%	46%	52%
63.9%		67%	69%	68%	74%	55%	64%	62%	71%	63%	66%	51%	64%	57%
49.3%		60%	42%	41%	45%	54%	70%	41%	41%	51%	11%	54%	58%	73%
74.8%		79%	81%	82%	75%	82%	77%	67%	73%	70%	70%	75%	69%	73%
74.3%		85%	73%	74%	78%	63%	79%	79%	71%	70%	91%	80%	63%	60%
70.2%		77%	77%	77%	62%	73%	75%	70%	74%	65%	54%	77%	66%	66%
76.5%		79%	82%	82%	63%	64%	87%	82%	71%	83%	73%	74%	73%	82%
70.4%		74%	67%	66%	67%	74%	75%	75%	72%	70%	72%	75%	71%	57%
68.8%		66%	74%	74%	67%	57%	67%	69%	81%	63%	67%	67%	70%	72%
56.9%		64%	52%	52%	69%	55%	63%	69%	58%	53%	68%	53%	37%	47%
84.0%		88%	85%	85%	82%	84%	87%	88%	90%	89%	83%	77%	68%	86%
72.7%		64%	79%	80%	74%	77%	59%	64%	71%	72%	75%	79%	80%	71%
63.2%		67%	69%	66%	70%	67%	70%	67%	61%	50%	70%	70%	53%	41%
71.3%		76%	71%	71%	72%	74%	68%	68%	58%	72%	74%	71%	81%	71%
63.2%		73%	59%	72%	77%	74%	43%	51%	69%	58%	49%	48%	67%	82%
60.0%		60%	64%	62%	66%	63%	57%	52%	64%	64%	57%	59%	57%	55%
46.5%		42%	46%	47%	42%	49%	39%	40%	60%	51%	32%	41%	62%	54%
77.7%		78%	84%	71%	51%	84%	81%	73%	81%	72%	82%	88%	84%	81%
79.6%		88%	85%	87%	74%	88%	86%	82%	81%	84%	66%	66%	75%	73%
87.2%		90%	88%	88%	88%	77%	93%	88%	91%	85%	89%	84%	82%	91%
64.6%		70%	70%	62%	67%	67%	68%	72%	69%	60%	63%	64%	62%	46%
67.5%		67%	70%	72%	77%	71%	67%	64%	70%	70%	54%	66%	63%	67%
75.6%		66%	80%	78%	80%	62%	78%	80%	77%	75%	80%	81%	84%	62%
75.3%		78%	81%	81%	71%	77%	81%	77%	74%	76%	68%	72%	76%	67%
87.5%		95%	91%	88%	86%	83%	88%	88%	88%	88%	76%	92%	92%	83%
90.2%		94%	93%	79%	90%	93%	92%	88%	90%	85%	90%	100%	85%	93%
69.8%		73%	68%	74%	65%	77%	71%	65%	84%	64%	54%	77%	66%	70%
77.7%		79%	79%	77%	77%	81%	74%	78%	77%	80%	64%	87%	82%	75%
54.8%		53%	65%	63%	57%	47%	56%	53%	57%	60%	38%	56%	49%	58%
71.6%		84%	65%	78%	83%	66%	63%	73%	72%	77%	55%	66%	72%	77%
64.4%		68%	65%	71%	60%	66%	69%	64%	65%	63%	56%	58%	63%	69%
72.4%		69%	72%	81%	63%	75%	79%	80%	74%	69%	75%	78%	71%	55%
70.5%		74%	75%	60%	63%	76%	77%	70%	71%	72%	75%	71%	67%	66%
81.0%		86%	81%	93%	89%	77%	80%	77%	91%	81%	59%	82%	73%	84%
68.8%		71%	74%	79%	71%	68%	72%	58%	68%	67%	59%	74%	70%	64%
59.0%		63%	58%	72%	70%	55%	62%	60%	61%	65%	51%	47%	40%	63%
65.5%		68%	70%	70%	66%	72%	64%	57%	73%	62%	59%	66%	67%	57%
76.8%		79%	79%	79%	66%	77%	83%	74%	76%	85%	79%	75%	64%	83%
78.5%		89%	89%	90%	82%	61%	80%	84%	71%	67%	85%	68%	80%	74%
81.1%		80%	84%	88%	90%	87%	87%	87%	90%	87%	68%	70%	68%	68%
85.4%		92%	92%	92%	72%	90%	92%	82%	88%	82%	80%	88%	77%	83%
82.8%		84%	82%	80%	82%	84%	87%	91%	82%	82%	87%	84%	87%	64%
63.8%		69%	68%	74%	53%	65%	61%	49%	67%	67%	69%	65%	62%	61%
80.2%		83%	89%	87%	76%	75%	82%	67%	82%	85%	67%	85%	82%	82%
70.2%		71%	69%	73%	81%	73%	68%	64%	69%	76%	66%	66%	62%	75%
66.1%		63%	62%	64%	66%	63%	59%	73%	70%	73%	50%	77%	64%	75%
84.7%		82%	81%	91%	76%	75%	88%	90%	91%	81%	88%	90%	87%	81%
78.8%		79%	76%	76%	81%	82%	78%	76%	83%	73%	79%	80%	81%	81%
69.8%		73%	72%	72%	57%	73%	65%	62%	74%	69%	72%	75%	71%	73%
76.6%		75%	79%	79%	75%	77%	76%	77%	82%	76%	73%	75%	73%	79%
68.1%		65%	70%	77%	79%	61%	64%	75%	68%	69%	59%	69%	57%	72%
69.3%		70%	77%	79%	74%	70%	71%	58%	74%	60%	63%	67%	66%	72%
67.9%		69%	73%	73%	61%	78%	73%	58%	61%	78%	61%	67%	72%	59%
60.7%		65%	67%	65%	58%	66%	63%	51%	61%	58%	60%	63%	55%	57%
71.8%		78%	81%	81%	73%	55%	81%	73%	65%	72%	72%	73%	68%	62%
73.2%		80%	80%	80%	54%	78%	80%	72%	72%	77%	70%	72%	69%	68%
68.1%		66%	69%	72%	67%	69%	75%	68%	69%	70%	67%	66%	67%	60%
89.1%		93%	85%	85%	93%	94%	82%	88%	95%	88%	85%	91%	94%	85%
65.2%		67%	75%	75%	66%	70%	57%	61%	75%	64%	46%	60%	64%	67%
59.6%		67%	58%	58%	36%	75%	71%	56%	64%	56%	52%	53%	68%	61%
90.3%		89%	95%	94%	89%	94%	100%	89%	80%	94%	90%	81%	87%	92%
74.8%		84%	80%	79%	76%	72%	74%	79%	69%	71%	69%	76%	75%	69%
67.7%		76%	72%	74%	50%	72%	69%	61%	73%	65%	63%	70%	68%	67%
66.0%		61%	73%	80%	64%	75%	60%	60%	68%	64%	57%	62%	65%	69%
75.8%		73%	71%	71%	69%	87%	78%	73%	73%	78%	74%	73%	80%	85%
66.7%		70%	76%	78%	84%	71%	53%	61%	64%	70%	32%	55%	70%	83%
81.4%		91%	81%	71%	69%	80%	71%	72%	72%	91%	91%	87%	91%	91%
58.6%		53%	54%	58%	63%	48%	61%	65%	60%	64%	58%	65%	53%	60%
36.2%		35%	37%	37%	48%	31%	26%	23%	37%	36%	35%	35%	53%	37%
53.9%		65%	58%	53%	30%	49%	50%	50%	63%	52%	46%	69%	58%	58%
69.2%		77%	73%	73%	73%	70%	76%	72%	72%	66%	56%	69%	66%	57%
66.1%		70%	73%	68%	74%	73%	69%	60%	59%	64%	69%	51%	62%	67%
81.9%		82%	93%	80%	74%	86%	70%	72%	91%	80%	86%	76%	87%	88%
55.4%		58%	61%	67%	38%	50%	56%	43%	81%	56%	54%	56%	56%	44%
69.8%		65%	76%	65%	73%	79%	71%	61%	64%	70%	70%	73%	70%	70%
75.8%		80%	80%	80%	72%	58%	84%	80%	75%	81%	73%	77%	67%	78%
68.2%		58%	83%	80%	73%	60%	62%	61%	80%	74%	58%	61%	65%	71%
54.8%		53%	61%	66%	51%	56%	51%	51%	65%	58%	56%	46%	48%	51%
77.8%		76%	79%	83%	83%	76%	77%	78%	78%	79%	82%	67%	75%	79%
47.5%		70%	42%	47%	57%	46%	51%	35%	35%	45%	22%	46%	56%	66%
58.4%		66%	53%	66%	59%	40%	51%	57%	70%	66%	60%	63%	52%	56%
72.4%		78%	82%	78%	79%	74%	75%	70%	68%	70%	66%	70%	64%	67%
80.2%		57%	77%	71%	82%	87%	88%	81%	81%	84%	78%	90%	90%	77%
63.3%		61%	61%	61%	77%	44%	77%	76%	70%	68%	60%	61%	40%	67%
69.0%		72%	75%	72%	74%	51%	76%	72%	64%	76%	65%	67%	60%	73%
64.3%		66%	70%	70%	71%	64%	70%	56%	63%	70%	46%	62%	64%	64%
80.8%		79%	81%	81%	88%	86%	77%	81%	81%	81%	82%	83%	69%	81%
70.8%		80%	76%	76%	41%	81%	69%	57%	65%	60%	76%	73%	83%	84%
72.7%		83%	76%	76%	78%	72%	81%	73%	67%	81%	65%	73%	61%	59%
50.7%		50%	43%	43%	39%	55%	56%	39%	51%	54%	46%	63%	57%	63%
79.5%		87%	88%	88%	64%	78%	90%	72%	88%	75%	75%	77%	80%	72%
62.6%		66%	66%	69%	71%	71%	66%	75%	67%	59%	37%	58%	66%	43%
73.4%		71%	83%	83%	73%	70%	77%	58%	79%	76%	68%	77%	69%	70%