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%3Asouth Africa - Run a38fd63...

Global Dialogues GD4 - South Africa

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

TAGS:

Global Dialogues Gd4

Instruction Following & Prompt Adherence

General Knowledge

Social interaction

AI Safety & Robustness

Economics & Finance

Demographic Processes

Best Models (Coverage)

1.GPT 4.1
61.9%
2.Claude Sonnet 4.5
61.2%
3.GPT 4.1 Mini
60.4%
4.Llama 4 Maverick
60.1%
5.Claude Haiku 4.5
60.0%

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 60.0%	8th 58.0%	2nd 61.2%	7th 58.4%	13th 53.3%	4th 60.1%	6th 59.8%	1st 61.9%	3rd 60.4%	9th 57.4%	11th 56.4%	10th 57.0%	12th 54.0%
29.2%		35%	36%	41%	37%	10%	22%	30%	36%	30%	30%	24%	28%	21%
42.9%		46%	45%	46%	64%	30%	32%	40%	61%	45%	40%	29%	33%	47%
71.9%		77%	77%	78%	66%	69%	66%	78%	78%	77%	64%	64%	64%	77%
53.7%		50%	58%	43%	50%	58%	57%	53%	57%	58%	58%	55%	58%	43%
64.7%		65%	72%	69%	62%	52%	64%	63%	64%	70%	62%	65%	66%	67%
55.8%		51%	50%	68%	72%	51%	65%	57%	68%	50%	57%	51%	52%	33%
37.6%		47%	42%	42%	35%	32%	42%	32%	32%	52%	7%	52%	32%	42%
58.9%		65%	46%	58%	72%	49%	69%	66%	80%	82%	46%	40%	47%	46%
64.6%		62%	58%	58%	72%	72%	70%	67%	65%	76%	67%	55%	56%	62%
74.2%		78%	67%	62%	58%	82%	60%	57%	75%	85%	85%	85%	86%	85%
51.8%		51%	40%	58%	86%	40%	56%	52%	58%	58%	46%	40%	46%	43%
66.3%		71%	65%	67%	71%	58%	75%	72%	66%	57%	78%	69%	57%	56%
45.8%		49%	47%	54%	40%	41%	45%	50%	58%	41%	41%	41%	47%	41%
56.5%		65%	65%	65%	65%	46%	53%	53%	60%	53%	47%	53%	46%	64%
72.0%		74%	82%	82%	68%	73%	72%	60%	61%	72%	75%	76%	69%	72%
64.5%		72%	60%	67%	76%	63%	78%	65%	78%	64%	50%	47%	59%	60%
56.9%		62%	61%	64%	70%	50%	52%	57%	58%	56%	62%	50%	48%	50%
79.0%		77%	81%	81%	72%	84%	86%	84%	83%	76%	81%	76%	73%	73%
75.4%		82%	69%	79%	76%	58%	83%	82%	80%	83%	89%	62%	69%	68%
68.5%		67%	58%	58%	73%	53%	58%	68%	73%	81%	77%	74%	69%	81%
57.8%		61%	53%	64%	64%	63%	57%	61%	65%	53%	64%	53%	55%	39%
65.8%		69%	68%	70%	63%	70%	78%	64%	52%	70%	63%	63%	63%	63%
58.4%		59%	58%	75%	58%	58%	71%	62%	62%	50%	57%	58%	55%	36%
80.0%		88%	86%	89%	85%	79%	86%	84%	89%	86%	66%	64%	69%	69%
60.5%		61%	57%	62%	48%	62%	62%	58%	60%	69%	64%	60%	62%	62%
43.8%		47%	35%	45%	50%	50%	35%	42%	45%	52%	17%	56%	46%	50%
54.8%		49%	56%	58%	58%	58%	53%	58%	62%	52%	57%	52%	55%	44%
45.4%		46%	37%	50%	51%	24%	47%	55%	50%	44%	50%	51%	52%	33%
34.8%		34%	35%	35%	27%	21%	41%	38%	41%	41%	49%	32%	29%	29%
55.2%		57%	58%	67%	56%	39%	51%	61%	56%	64%	55%	52%	52%	49%
75.6%		75%	75%	85%	75%	73%	75%	85%	85%	70%	77%	75%	77%	56%
68.0%		66%	66%	66%	73%	75%	74%	69%	71%	71%	73%	54%	68%	58%
53.1%		61%	49%	64%	46%	56%	72%	68%	54%	63%	35%	35%	39%	48%
54.0%		55%	54%	54%	66%	52%	59%	52%	63%	54%	36%	51%	52%	54%
54.7%		63%	40%	50%	63%	46%	64%	56%	65%	70%	57%	40%	43%	54%
69.8%		73%	67%	73%	67%	66%	67%	72%	73%	76%	67%	67%	76%	64%
47.2%		49%	47%	56%	47%	48%	57%	49%	52%	55%	35%	30%	47%	41%
44.2%		40%	55%	45%	38%	48%	38%	38%	45%	39%	55%	48%	39%	46%
55.1%		54%	54%	59%	54%	54%	61%	64%	59%	54%	60%	54%	52%	37%
67.9%		56%	78%	67%	78%	63%	48%	55%	58%	72%	76%	86%	68%	78%
68.7%		74%	75%	80%	53%	62%	74%	70%	77%	72%	47%	70%	62%	77%
62.5%		64%	73%	75%	52%	75%	75%	58%	67%	67%	52%	52%	60%	42%
59.8%		63%	50%	63%	76%	51%	69%	74%	58%	79%	65%	32%	47%	50%
69.5%		74%	73%	65%	73%	69%	65%	65%	69%	67%	70%	77%	70%	67%
60.5%		58%	67%	57%	52%	57%	57%	65%	73%	63%	63%	57%	59%	58%
76.2%		72%	77%	79%	73%	77%	77%	77%	73%	77%	72%	78%	83%	76%
59.8%		62%	61%	65%	69%	61%	69%	53%	58%	56%	60%	53%	60%	51%
66.9%		64%	65%	65%	70%	57%	65%	65%	79%	65%	57%	79%	82%	57%
54.1%		53%	57%	53%	53%	57%	59%	53%	42%	53%	53%	64%	53%	53%
66.0%		73%	69%	64%	61%	54%	78%	71%	61%	61%	80%	61%	63%	62%
54.1%		64%	52%	52%	46%	42%	67%	64%	51%	49%	76%	49%	43%	48%
53.1%		57%	58%	59%	0%	50%	47%	52%	57%	52%	86%	51%	59%	62%
40.5%		42%	41%	47%	41%	29%	30%	39%	45%	45%	48%	35%	43%	41%
64.5%		61%	58%	69%	73%	61%	79%	70%	71%	58%	55%	58%	67%	58%
35.2%		34%	41%	41%	33%	16%	41%	35%	39%	41%	34%	41%	37%	25%
74.3%		77%	75%	81%	79%	64%	78%	78%	75%	64%	64%	66%	84%	81%
68.2%		67%	72%	72%	43%	68%	56%	60%	65%	87%	50%	87%	88%	72%
36.1%		37%	36%	43%	30%	30%	34%	35%	47%	30%	47%	30%	40%	30%
50.5%		53%	44%	50%	74%	34%	63%	50%	63%	50%	32%	49%	45%	50%
82.6%		84%	84%	84%	86%	83%	75%	81%	84%	81%	82%	84%	87%	79%
66.6%		70%	64%	72%	53%	69%	72%	68%	68%	70%	72%	62%	62%	64%
49.0%		51%	52%	60%	56%	32%	50%	53%	54%	32%	54%	47%	51%	45%
67.5%		70%	71%	71%	67%	70%	64%	71%	71%	67%	64%	59%	70%	63%
64.2%		74%	58%	70%	63%	58%	71%	69%	70%	71%	58%	58%	55%	60%
55.8%		51%	56%	61%	56%	52%	63%	62%	62%	55%	56%	56%	58%	38%
49.8%		47%	38%	56%	59%	41%	61%	68%	56%	43%	53%	44%	44%	38%
44.8%		55%	43%	48%	58%	33%	47%	54%	48%	36%	43%	43%	43%	32%
59.3%		59%	55%	54%	39%	56%	58%	66%	49%	63%	71%	72%	74%	55%
59.2%		60%	62%	62%	50%	64%	63%	54%	59%	55%	56%	67%	61%	56%
65.8%		75%	75%	75%	60%	60%	50%	67%	63%	67%	63%	63%	67%	71%
53.5%		59%	51%	53%	51%	50%	60%	53%	57%	59%	51%	51%	52%	48%
65.8%		69%	70%	67%	66%	71%	67%	68%	67%	75%	64%	52%	68%	52%
68.2%		62%	62%	78%	62%	62%	77%	83%	77%	62%	62%	62%	65%	73%
59.0%		44%	52%	35%	51%	74%	62%	57%	46%	59%	77%	68%	71%	71%
46.8%		53%	43%	43%	41%	43%	53%	49%	58%	43%	48%	43%	46%	46%
63.6%		61%	73%	61%	61%	65%	65%	60%	61%	66%	60%	65%	63%	66%
72.2%		71%	64%	68%	64%	64%	78%	84%	75%	81%	70%	64%	80%	75%
68.8%		73%	76%	72%	69%	52%	71%	73%	73%	69%	69%	69%	73%	55%
49.6%		54%	53%	53%	73%	37%	52%	52%	53%	57%	37%	37%	41%	46%
53.3%		51%	59%	65%	44%	35%	49%	53%	61%	59%	59%	59%	59%	40%
70.7%		74%	65%	65%	70%	77%	57%	63%	69%	76%	77%	76%	74%	76%
48.5%		46%	46%	44%	50%	36%	58%	58%	55%	47%	68%	44%	44%	35%
49.8%		54%	58%	67%	70%	39%	53%	49%	58%	41%	47%	41%	40%	30%
63.9%		69%	73%	63%	69%	63%	68%	62%	51%	66%	58%	73%	58%	58%
74.5%		69%	72%	83%	76%	68%	80%	77%	80%	75%	80%	72%	74%	62%
47.2%		45%	43%	50%	41%	43%	48%	48%	58%	55%	43%	43%	48%	49%
54.5%		54%	55%	47%	55%	49%	53%	58%	54%	51%	63%	59%	57%	53%
79.5%		80%	89%	86%	89%	58%	76%	81%	86%	82%	83%	63%	83%	77%
67.2%		67%	60%	63%	51%	57%	78%	75%	75%	74%	73%	78%	64%	58%
39.5%		38%	38%	38%	34%	31%	31%	38%	38%	44%	58%	50%	38%	38%
53.2%		50%	51%	51%	48%	53%	58%	54%	63%	54%	54%	51%	53%	51%
70.0%		71%	72%	70%	76%	69%	61%	67%	70%	63%	72%	74%	73%	72%
26.7%		36%	40%	29%	0%	24%	7%	19%	35%	40%	20%	57%	33%	7%
39.6%		48%	39%	41%	39%	20%	52%	46%	39%	39%	48%	40%	36%	28%
73.5%		75%	65%	70%	65%	65%	78%	80%	85%	78%	70%	78%	82%	65%
54.8%		64%	56%	56%	40%	56%	65%	60%	53%	66%	46%	51%	57%	42%
74.1%		76%	80%	76%	75%	79%	74%	72%	76%	71%	67%	69%	74%	74%
52.7%		53%	55%	49%	37%	58%	55%	54%	49%	60%	55%	55%	50%	55%
64.6%		70%	63%	76%	71%	46%	70%	67%	76%	71%	46%	62%	51%	71%
53.3%		54%	49%	49%	50%	51%	54%	58%	62%	58%	58%	51%	54%	45%
44.5%		52%	38%	43%	49%	40%	51%	36%	45%	49%	38%	45%	48%	44%
41.7%		38%	37%	53%	47%	37%	43%	40%	53%	37%	37%	37%	49%	34%
34.5%		36%	30%	40%	51%	27%	25%	37%	30%	45%	13%	43%	42%	30%
46.2%		52%	35%	57%	47%	33%	39%	47%	52%	46%	46%	55%	39%	52%
39.2%		39%	34%	44%	41%	25%	49%	44%	43%	48%	49%	33%	34%	26%
66.2%		78%	76%	77%	76%	57%	63%	59%	72%	67%	52%	57%	50%	77%
72.8%		71%	73%	74%	84%	57%	81%	78%	94%	67%	91%	70%	47%	59%
43.3%		46%	46%	46%	53%	29%	44%	39%	55%	43%	44%	43%	32%	43%
59.4%		57%	59%	60%	58%	60%	55%	59%	59%	67%	50%	71%	54%	63%
62.3%		53%	57%	69%	79%	61%	69%	67%	73%	67%	57%	47%	54%	57%
58.5%		58%	52%	67%	58%	59%	67%	58%	76%	70%	50%	45%	58%	42%
44.7%		51%	40%	50%	57%	28%	47%	54%	53%	39%	55%	39%	34%	34%
45.2%		44%	39%	47%	41%	55%	41%	50%	35%	47%	22%	58%	53%	55%
76.4%		85%	71%	76%	71%	73%	86%	79%	89%	71%	71%	71%	76%	74%
77.9%		87%	87%	83%	70%	68%	83%	75%	76%	79%	77%	68%	83%	77%
71.5%		73%	71%	76%	59%	68%	65%	78%	68%	71%	71%	71%	76%	82%