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%3Asingapore - Run 68c5147...

Global Dialogues GD4 - Singapore

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

AI Safety & Robustness

Social interaction

Economics & Finance

AI Bias & Fairness

Best Models (Coverage)

1.Claude Sonnet 4.5
65.6%
2.GPT 4.1
65.5%
3.Claude Sonnet 4
65.1%
4.Llama 4 Maverick
64.6%
5.Gemini 2.5 Flash
64.2%

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		6th 63.8%	3rd 65.1%	1st 65.6%	5th 64.2%	8th 61.9%	4th 64.6%	9th 61.4%	2nd 65.5%	7th 63.0%	13th 59.6%	12th 60.5%	11th 61.2%	10th 61.3%
56.8%		56%	63%	63%	61%	48%	54%	54%	63%	53%	54%	53%	54%	63%
62.2%		56%	66%	66%	76%	55%	50%	52%	78%	72%	55%	61%	54%	67%
78.7%		77%	81%	81%	91%	78%	82%	76%	82%	83%	68%	72%	68%	84%
61.3%		59%	57%	59%	63%	65%	58%	63%	59%	64%	63%	62%	62%	63%
53.0%		57%	55%	72%	58%	42%	55%	49%	53%	51%	55%	42%	49%	51%
70.2%		67%	75%	75%	71%	73%	70%	67%	75%	71%	71%	71%	73%	53%
68.5%		82%	75%	75%	75%	65%	69%	52%	61%	69%	38%	72%	69%	89%
53.2%		55%	60%	52%	45%	45%	52%	54%	50%	51%	61%	51%	58%	57%
65.2%		69%	60%	55%	76%	61%	62%	69%	67%	73%	61%	67%	55%	72%
66.2%		72%	67%	53%	64%	75%	73%	60%	75%	75%	71%	69%	72%	35%
76.8%		78%	83%	83%	77%	81%	75%	72%	71%	76%	73%	76%	79%	74%
77.0%		84%	86%	85%	80%	68%	76%	76%	82%	73%	65%	76%	74%	76%
50.5%		51%	51%	54%	47%	51%	55%	51%	59%	51%	47%	47%	44%	48%
66.6%		68%	68%	68%	68%	63%	67%	63%	63%	67%	68%	67%	68%	68%
40.2%		33%	50%	47%	33%	36%	47%	35%	37%	49%	42%	41%	37%	35%
51.7%		59%	51%	59%	68%	43%	55%	55%	61%	59%	37%	37%	37%	51%
51.2%		48%	45%	45%	52%	44%	56%	56%	56%	56%	51%	46%	65%	45%
55.5%		57%	63%	61%	56%	57%	59%	53%	58%	48%	59%	58%	42%	50%
71.5%		70%	78%	80%	62%	74%	77%	71%	77%	68%	71%	72%	65%	65%
77.0%		78%	77%	81%	76%	80%	76%	75%	86%	68%	78%	76%	74%	76%
80.5%		80%	81%	86%	83%	86%	74%	80%	82%	84%	77%	77%	72%	84%
85.8%		96%	94%	84%	84%	77%	89%	89%	89%	89%	86%	89%	70%	79%
63.8%		65%	69%	68%	61%	65%	62%	64%	66%	66%	61%	60%	61%	62%
22.5%		27%	26%	26%	26%	17%	30%	22%	30%	18%	18%	13%	18%	22%
54.8%		57%	53%	50%	80%	53%	64%	51%	57%	48%	54%	43%	48%	55%
55.2%		57%	55%	54%	47%	61%	62%	57%	57%	58%	40%	51%	58%	61%
55.4%		51%	61%	62%	58%	56%	55%	49%	57%	56%	53%	53%	53%	56%
64.5%		66%	71%	77%	67%	67%	65%	63%	69%	62%	62%	49%	58%	62%
58.8%		62%	65%	64%	58%	58%	66%	54%	67%	58%	55%	54%	54%	50%
67.4%		65%	70%	70%	69%	68%	75%	63%	72%	61%	63%	61%	66%	73%
76.8%		79%	78%	69%	87%	70%	80%	80%	72%	86%	78%	78%	68%	73%
53.2%		55%	55%	61%	54%	54%	54%	50%	55%	54%	54%	54%	50%	41%
64.7%		68%	67%	68%	67%	63%	69%	68%	74%	62%	47%	66%	57%	65%
48.2%		46%	51%	51%	63%	42%	54%	53%	55%	47%	37%	44%	37%	47%
66.2%		65%	70%	73%	65%	70%	63%	59%	53%	66%	75%	62%	74%	65%
75.2%		84%	76%	76%	79%	77%	80%	79%	80%	69%	81%	77%	65%	55%
50.8%		57%	55%	37%	41%	61%	56%	56%	31%	49%	58%	51%	58%	50%
65.5%		50%	60%	64%	68%	76%	52%	52%	64%	82%	66%	61%	73%	84%
74.2%		77%	71%	68%	69%	71%	81%	68%	75%	77%	79%	74%	79%	75%
56.6%		42%	54%	51%	42%	68%	42%	50%	61%	68%	61%	61%	73%	63%
71.0%		78%	70%	84%	81%	55%	79%	75%	80%	70%	49%	69%	59%	74%
80.6%		83%	78%	84%	82%	91%	82%	82%	73%	78%	64%	82%	86%	83%
78.3%		83%	75%	77%	75%	76%	80%	82%	66%	63%	79%	90%	90%	82%
73.1%		79%	70%	70%	71%	68%	82%	81%	79%	68%	75%	76%	74%	57%
62.2%		65%	65%	70%	61%	60%	65%	58%	63%	59%	61%	58%	65%	58%
68.9%		66%	74%	72%	63%	65%	72%	74%	76%	69%	57%	63%	72%	73%
47.0%		57%	58%	62%	52%	42%	52%	42%	48%	44%	35%	40%	42%	37%
93.3%		97%	95%	97%	92%	94%	98%	94%	100%	90%	100%	81%	81%	94%
66.5%		70%	76%	76%	76%	67%	58%	63%	73%	73%	58%	58%	58%	59%
55.1%		53%	54%	59%	36%	67%	68%	53%	64%	53%	53%	53%	58%	45%
72.4%		73%	74%	73%	65%	76%	75%	74%	78%	71%	73%	75%	71%	63%
55.3%		51%	53%	64%	71%	40%	44%	55%	71%	50%	62%	52%	49%	57%
77.5%		76%	77%	76%	90%	84%	76%	73%	82%	70%	87%	68%	71%	77%
49.5%		46%	42%	42%	58%	55%	58%	48%	62%	46%	46%	35%	47%	59%
73.6%		79%	79%	76%	78%	75%	70%	74%	79%	68%	68%	64%	73%	74%
74.5%		76%	74%	80%	77%	71%	77%	77%	84%	77%	66%	66%	64%	80%
40.2%		36%	45%	41%	41%	32%	60%	47%	54%	33%	41%	31%	34%	28%
59.0%		57%	58%	57%	65%	62%	64%	58%	66%	57%	57%	58%	53%	55%
47.8%		58%	47%	56%	62%	40%	50%	50%	54%	49%	34%	34%	36%	51%
54.1%		55%	58%	58%	57%	56%	64%	52%	48%	53%	49%	55%	55%	43%
70.5%		65%	77%	65%	55%	84%	76%	66%	63%	69%	70%	73%	77%	77%
66.8%		67%	76%	74%	70%	62%	66%	60%	68%	62%	63%	67%	66%	68%
88.7%		90%	93%	96%	94%	100%	100%	88%	100%	95%	64%	80%	76%	77%
82.5%		86%	89%	92%	70%	85%	79%	75%	68%	72%	93%	87%	100%	77%
55.8%		55%	61%	61%	56%	60%	59%	48%	62%	49%	59%	56%	63%	37%
65.8%		65%	63%	71%	74%	65%	69%	64%	73%	66%	59%	57%	57%	72%
65.8%		66%	68%	67%	67%	57%	67%	67%	71%	65%	68%	65%	62%	65%
60.8%		64%	61%	59%	56%	54%	64%	53%	59%	66%	54%	62%	70%	68%
61.5%		60%	54%	49%	63%	61%	56%	63%	54%	70%	69%	57%	70%	73%
83.8%		71%	78%	78%	90%	83%	89%	90%	100%	82%	74%	87%	90%	78%
52.1%		55%	61%	54%	41%	53%	52%	47%	58%	52%	55%	50%	55%	44%
72.3%		75%	77%	71%	61%	79%	73%	59%	81%	75%	75%	71%	71%	72%
80.4%		80%	80%	80%	83%	82%	83%	83%	91%	73%	73%	72%	77%	88%
43.4%		42%	54%	55%	47%	32%	37%	46%	58%	48%	36%	40%	29%	40%
60.0%		55%	63%	63%	63%	61%	58%	51%	50%	60%	65%	60%	65%	66%
62.5%		58%	68%	68%	70%	59%	72%	56%	62%	68%	58%	58%	59%	56%
52.9%		53%	57%	56%	55%	54%	57%	48%	43%	58%	50%	58%	58%	41%
54.8%		54%	59%	52%	55%	55%	67%	58%	62%	50%	52%	44%	44%	61%
74.2%		82%	78%	78%	45%	77%	78%	72%	69%	73%	80%	83%	84%	65%
66.5%		73%	68%	66%	76%	60%	65%	67%	68%	64%	60%	60%	68%	70%
81.8%		79%	82%	88%	90%	79%	89%	88%	89%	79%	75%	75%	79%	71%
71.3%		74%	77%	85%	77%	74%	69%	74%	76%	64%	58%	71%	64%	64%
73.4%		79%	79%	80%	67%	76%	79%	71%	75%	71%	70%	74%	71%	62%
69.8%		74%	76%	77%	67%	63%	67%	74%	73%	67%	74%	67%	63%	65%
51.6%		56%	54%	53%	51%	50%	51%	55%	57%	50%	39%	51%	51%	53%
63.5%		68%	68%	70%	59%	67%	64%	60%	62%	65%	56%	63%	68%	56%
60.9%		68%	54%	59%	67%	66%	62%	60%	50%	63%	56%	55%	71%	61%
47.5%		47%	49%	48%	40%	50%	44%	48%	42%	52%	48%	57%	48%	44%
48.2%		58%	57%	61%	76%	36%	40%	42%	45%	49%	24%	24%	42%	73%
73.1%		78%	70%	73%	70%	71%	70%	63%	73%	77%	74%	73%	77%	81%
66.5%		71%	65%	70%	63%	65%	70%	66%	73%	70%	54%	63%	63%	72%
28.2%		28%	31%	29%	37%	24%	26%	21%	13%	32%	32%	30%	39%	24%
55.5%		62%	65%	56%	44%	46%	45%	51%	53%	58%	45%	62%	73%	62%
64.5%		64%	75%	74%	65%	68%	65%	61%	65%	62%	61%	61%	58%	59%
41.4%		44%	51%	42%	43%	43%	48%	36%	29%	37%	50%	34%	45%	36%
53.9%		51%	60%	56%	62%	58%	46%	43%	57%	54%	49%	57%	57%	51%
60.5%		65%	61%	58%	59%	63%	63%	59%	63%	61%	57%	61%	57%	59%
73.5%		68%	78%	74%	62%	81%	77%	71%	74%	77%	73%	73%	74%	74%
67.7%		71%	67%	77%	71%	55%	72%	69%	83%	71%	55%	61%	57%	71%
54.2%		55%	62%	62%	61%	44%	49%	53%	65%	64%	52%	52%	48%	37%
63.5%		66%	66%	78%	70%	57%	57%	67%	79%	56%	55%	62%	56%	57%
64.5%		66%	65%	69%	76%	61%	63%	63%	71%	62%	57%	57%	58%	71%
54.8%		65%	49%	57%	47%	47%	58%	49%	58%	67%	38%	51%	61%	65%
79.2%		81%	76%	76%	90%	74%	83%	80%	80%	77%	80%	75%	81%	77%
61.4%		64%	68%	73%	59%	68%	64%	63%	64%	55%	58%	58%	47%	57%
60.9%		52%	58%	57%	63%	49%	68%	70%	67%	68%	54%	68%	60%	58%
65.8%		60%	67%	72%	72%	48%	65%	68%	77%	72%	71%	67%	45%	72%
46.2%		45%	47%	55%	48%	30%	44%	51%	64%	55%	37%	37%	37%	51%
48.4%		45%	44%	44%	58%	51%	47%	51%	48%	46%	49%	51%	51%	44%
70.6%		67%	67%	74%	75%	74%	77%	65%	82%	74%	69%	65%	58%	71%
57.5%		62%	58%	50%	47%	65%	53%	50%	43%	52%	74%	65%	65%	63%
62.5%		60%	67%	67%	57%	61%	68%	61%	63%	61%	64%	58%	62%	64%
68.2%		64%	67%	69%	69%	66%	76%	66%	72%	73%	61%	66%	71%	66%
68.0%		72%	64%	71%	66%	71%	72%	65%	58%	67%	69%	71%	74%	64%
60.8%		58%	64%	67%	60%	67%	67%	74%	67%	60%	37%	60%	60%	49%
42.8%		38%	49%	37%	49%	46%	49%	34%	48%	42%	49%	49%	42%	24%