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%3Asingapore C5 - Run 266dafd...

Global Dialogues GD4 - Singapore (5 context Qs)

DTEF: Predict response distributions for Singapore. 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

Economics & Finance

Best Models (Coverage)

1.Claude Sonnet 4.5
67.1%
2.GPT 4.1
65.9%
3.Claude Sonnet 4
65.4%
4.Gemini 2.5 Flash
65.3%
5.Claude Haiku 4.5
64.6%

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 64.6%	3rd 65.4%	1st 67.1%	4th 65.3%	10th 61.6%	7th 63.9%	8th 63.4%	2nd 65.9%	6th 64.4%	13th 59.0%	9th 61.6%	11th 61.6%	12th 60.6%
53.5%		54%	65%	63%	60%	36%	48%	52%	56%	51%	51%	48%	56%	56%
57.3%		52%	54%	65%	76%	33%	54%	66%	77%	58%	55%	50%	55%	50%
79.3%		81%	81%	83%	100%	77%	79%	78%	82%	82%	72%	72%	72%	72%
56.9%		59%	54%	53%	57%	58%	58%	62%	54%	52%	59%	59%	59%	56%
53.0%		57%	59%	67%	62%	36%	51%	55%	58%	54%	48%	42%	43%	57%
69.7%		67%	73%	73%	73%	64%	73%	71%	90%	71%	71%	71%	73%	36%
73.8%		81%	82%	82%	90%	58%	80%	67%	51%	77%	63%	65%	82%	82%
53.0%		56%	51%	49%	51%	52%	53%	56%	51%	56%	51%	54%	58%	51%
52.5%		56%	43%	37%	50%	50%	61%	73%	49%	61%	52%	58%	43%	50%
71.0%		75%	80%	73%	76%	80%	73%	68%	60%	75%	69%	69%	69%	56%
73.6%		66%	76%	82%	66%	73%	76%	72%	70%	76%	73%	73%	73%	81%
78.3%		86%	86%	85%	82%	82%	71%	76%	86%	83%	65%	73%	72%	71%
51.1%		54%	51%	49%	58%	56%	48%	48%	57%	51%	51%	47%	47%	47%
61.8%		68%	68%	65%	60%	56%	67%	60%	51%	64%	60%	56%	61%	68%
39.2%		39%	37%	25%	24%	40%	46%	38%	36%	44%	49%	46%	48%	37%
47.0%		51%	51%	58%	59%	48%	44%	54%	59%	51%	18%	37%	37%	44%
49.9%		47%	44%	49%	55%	56%	56%	51%	46%	44%	50%	56%	45%	50%
60.8%		58%	57%	70%	60%	73%	58%	56%	81%	48%	58%	58%	55%	58%
66.7%		75%	80%	80%	0%	64%	77%	74%	81%	67%	72%	67%	59%	71%
76.6%		71%	78%	76%	85%	78%	78%	79%	80%	68%	90%	71%	76%	66%
73.1%		69%	60%	77%	81%	80%	71%	74%	51%	81%	77%	77%	71%	81%
83.8%		94%	86%	86%	82%	84%	89%	91%	73%	77%	70%	91%	81%	86%
59.1%		61%	69%	69%	33%	63%	63%	61%	55%	59%	64%	62%	66%	43%
22.4%		22%	37%	37%	22%	13%	30%	20%	30%	18%	18%	13%	13%	18%
53.5%		56%	52%	56%	62%	58%	64%	53%	62%	36%	54%	46%	47%	50%
63.5%		67%	56%	63%	70%	63%	65%	50%	64%	69%	73%	62%	66%	58%
53.3%		46%	56%	58%	50%	53%	55%	49%	56%	53%	57%	51%	51%	58%
68.1%		68%	76%	76%	67%	65%	70%	62%	90%	67%	62%	62%	60%	60%
61.2%		61%	68%	68%	77%	51%	66%	56%	68%	60%	53%	58%	49%	60%
67.8%		69%	77%	77%	77%	60%	64%	67%	72%	70%	60%	60%	60%	69%
77.8%		83%	76%	81%	76%	87%	82%	78%	46%	87%	78%	87%	78%	72%
50.1%		55%	39%	43%	52%	62%	54%	47%	43%	54%	54%	54%	55%	39%
59.2%		59%	65%	71%	67%	53%	56%	62%	65%	67%	47%	53%	53%	52%
44.9%		41%	51%	47%	77%	36%	44%	55%	56%	50%	29%	37%	29%	32%
74.4%		78%	84%	77%	80%	72%	76%	71%	58%	66%	74%	75%	78%	78%
72.2%		79%	81%	77%	79%	67%	79%	71%	81%	68%	56%	81%	79%	41%
65.4%		65%	64%	65%	57%	72%	68%	60%	62%	73%	61%	66%	70%	67%
68.5%		65%	60%	77%	64%	66%	58%	58%	73%	74%	81%	67%	63%	84%
78.5%		83%	77%	75%	77%	85%	77%	79%	77%	77%	82%	85%	79%	67%
60.6%		47%	60%	60%	46%	59%	47%	55%	73%	77%	68%	73%	61%	62%
69.0%		65%	73%	82%	82%	57%	68%	78%	91%	70%	49%	70%	49%	63%
76.9%		82%	78%	78%	58%	91%	78%	82%	63%	82%	78%	69%	86%	75%
71.5%		76%	65%	71%	76%	70%	71%	85%	59%	76%	69%	69%	73%	70%
72.8%		70%	68%	70%	80%	70%	76%	76%	77%	68%	76%	78%	69%	68%
64.7%		64%	66%	76%	61%	63%	63%	55%	74%	68%	66%	58%	66%	61%
69.6%		64%	72%	76%	65%	63%	72%	69%	73%	78%	60%	69%	72%	72%
46.5%		57%	51%	62%	55%	30%	52%	42%	46%	40%	43%	42%	43%	42%
92.9%		95%	90%	95%	94%	94%	100%	94%	100%	95%	88%	81%	94%	88%
65.5%		69%	69%	79%	61%	76%	58%	65%	73%	58%	58%	58%	65%	62%
61.2%		65%	69%	69%	62%	61%	68%	56%	66%	56%	59%	57%	57%	51%
72.3%		71%	82%	77%	76%	68%	76%	75%	66%	71%	75%	71%	61%	71%
48.2%		48%	51%	72%	37%	39%	36%	67%	53%	42%	44%	50%	44%	44%
70.7%		76%	77%	77%	91%	58%	75%	68%	73%	71%	56%	62%	69%	66%
42.6%		49%	42%	50%	55%	36%	42%	50%	39%	38%	39%	38%	38%	38%
74.4%		78%	80%	79%	78%	77%	74%	67%	79%	74%	64%	74%	75%	68%
68.5%		69%	74%	79%	66%	60%	69%	71%	70%	74%	64%	66%	58%	71%
33.9%		29%	28%	40%	67%	26%	33%	30%	41%	41%	21%	39%	20%	26%
59.3%		57%	58%	58%	58%	63%	58%	60%	77%	58%	58%	58%	51%	57%
43.7%		44%	44%	54%	69%	31%	40%	51%	54%	44%	27%	34%	34%	42%
61.4%		61%	64%	63%	54%	65%	68%	48%	61%	68%	64%	61%	64%	57%
74.6%		74%	76%	76%	63%	84%	79%	69%	63%	63%	75%	80%	84%	84%
65.2%		68%	74%	73%	67%	53%	62%	63%	68%	65%	63%	61%	68%	62%
89.5%		93%	91%	91%	94%	86%	88%	91%	100%	91%	78%	90%	90%	81%
86.8%		86%	100%	84%	68%	93%	100%	82%	72%	100%	80%	87%	100%	76%
48.3%		51%	63%	53%	56%	56%	52%	49%	63%	40%	45%	45%	36%	19%
65.3%		65%	67%	67%	83%	64%	66%	65%	65%	68%	55%	59%	58%	67%
63.8%		66%	60%	69%	68%	60%	68%	68%	67%	67%	58%	53%	62%	64%
62.9%		64%	62%	59%	57%	60%	70%	63%	62%	71%	55%	63%	67%	65%
56.0%		53%	51%	47%	58%	59%	46%	67%	58%	67%	44%	65%	56%	57%
86.9%		94%	94%	90%	66%	95%	90%	80%	80%	87%	86%	87%	94%	87%
59.2%		57%	64%	56%	62%	65%	58%	42%	64%	55%	59%	61%	65%	62%
74.8%		79%	81%	75%	73%	80%	73%	59%	100%	79%	69%	71%	72%	62%
76.5%		77%	82%	82%	62%	73%	65%	80%	91%	82%	73%	73%	82%	73%
41.5%		38%	43%	50%	48%	32%	37%	51%	51%	45%	29%	47%	34%	34%
65.2%		68%	63%	60%	63%	71%	71%	56%	63%	63%	65%	65%	68%	72%
66.4%		68%	68%	72%	60%	71%	71%	57%	62%	72%	66%	66%	66%	64%
53.4%		59%	61%	53%	44%	56%	57%	50%	43%	50%	50%	58%	58%	55%
59.5%		61%	61%	61%	67%	50%	58%	67%	67%	61%	50%	55%	55%	61%
81.4%		84%	84%	79%	77%	87%	84%	83%	66%	82%	83%	83%	84%	82%
68.8%		76%	72%	70%	72%	68%	66%	63%	77%	66%	60%	66%	68%	71%
83.4%		85%	85%	88%	95%	78%	85%	88%	79%	81%	81%	79%	84%	76%
74.7%		77%	87%	93%	74%	74%	71%	73%	87%	75%	62%	74%	61%	63%
75.3%		81%	83%	82%	61%	74%	77%	71%	86%	76%	70%	70%	73%	75%
69.9%		76%	68%	75%	69%	67%	67%	74%	73%	67%	63%	73%	69%	68%
51.5%		51%	55%	51%	48%	51%	51%	55%	50%	51%	51%	51%	55%	49%
64.6%		66%	68%	68%	68%	69%	63%	63%	60%	64%	63%	64%	64%	60%
63.5%		63%	64%	63%	67%	67%	67%	63%	58%	66%	56%	65%	62%	65%
56.9%		68%	54%	51%	64%	62%	52%	52%	51%	57%	52%	60%	62%	55%
50.1%		54%	57%	57%	76%	35%	49%	50%	55%	43%	24%	43%	49%	59%
70.2%		81%	74%	73%	65%	63%	65%	61%	73%	70%	74%	67%	83%	63%
66.6%		65%	65%	65%	86%	57%	68%	67%	77%	70%	60%	60%	60%	66%
45.2%		45%	61%	62%	63%	24%	45%	52%	55%	63%	39%	39%	39%	0%
57.2%		58%	54%	54%	37%	69%	50%	66%	58%	65%	37%	71%	58%	67%
66.5%		65%	75%	77%	65%	65%	66%	65%	72%	65%	61%	62%	65%	62%
47.6%		56%	51%	52%	43%	58%	51%	37%	31%	38%	50%	47%	47%	58%
60.6%		61%	66%	69%	66%	63%	62%	49%	66%	57%	62%	57%	66%	44%
60.5%		61%	61%	58%	58%	61%	63%	64%	66%	59%	57%	59%	57%	63%
76.0%		74%	78%	83%	52%	80%	84%	74%	81%	74%	73%	77%	77%	81%
65.8%		72%	67%	83%	81%	38%	64%	71%	81%	70%	54%	55%	54%	66%
61.9%		66%	58%	58%	87%	44%	52%	52%	72%	77%	52%	52%	52%	83%
60.5%		58%	73%	86%	37%	63%	57%	64%	69%	59%	54%	54%	54%	59%
56.7%		45%	62%	63%	65%	55%	53%	68%	48%	53%	56%	57%	56%	56%
73.3%		82%	77%	77%	68%	75%	69%	72%	77%	66%	77%	66%	82%	65%
81.5%		81%	76%	80%	91%	67%	83%	86%	89%	81%	77%	81%	86%	81%
63.5%		64%	73%	73%	61%	59%	64%	64%	73%	67%	58%	59%	51%	59%
63.3%		50%	54%	73%	63%	61%	68%	74%	68%	67%	54%	54%	63%	74%
58.0%		60%	33%	33%	77%	48%	59%	70%	77%	70%	42%	51%	57%	77%
43.7%		47%	42%	50%	59%	22%	42%	51%	58%	44%	36%	37%	36%	44%
45.1%		45%	45%	42%	51%	51%	47%	41%	43%	45%	35%	53%	41%	47%
63.1%		65%	49%	72%	91%	65%	62%	65%	73%	68%	56%	49%	56%	49%
72.4%		70%	74%	74%	71%	74%	73%	63%	81%	74%	74%	74%	68%	71%
64.9%		66%	68%	67%	57%	67%	68%	68%	81%	69%	58%	61%	65%	49%
72.9%		73%	65%	65%	76%	74%	74%	84%	73%	74%	76%	74%	65%	75%
65.8%		64%	70%	64%	58%	68%	68%	68%	55%	70%	68%	68%	68%	66%
62.3%		45%	68%	65%	67%	67%	65%	72%	70%	65%	41%	67%	61%	57%
47.7%		60%	49%	42%	65%	54%	40%	31%	34%	49%	49%	49%	49%	49%