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%3Asouth Africa C5 - Run d47043f...

Global Dialogues GD4 - South Africa (5 context Qs)

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

Factual Accuracy & Hallucination

Social interaction

AI Safety & Robustness

Economic Disruption & Reskilling Advice

Mental Health & Crisis Support

Child Safety & Protection

Best Models (Coverage)

1.GPT 4.1
66.9%
2.Claude Sonnet 4.5
66.2%
3.Claude 3.7 Sonnet
66.1%
4.GPT 5.1
66.0%
5.Claude Haiku 4.5
63.5%

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 3.7 Sonnet	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Large 2411	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o	GPT 4o Mini	GPT 5 Mini	GPT 5.1	GPT OSS 120b	GPT OSS 20b	Qwen3 30b A3B Instruct 2507	Qwen3 Next 80b A3B Instruct	Grok 4.1 Fast
Score		3rd 66.1%	5th 63.5%	12th 61.7%	2nd 66.2%	19th 58.1%	20th 54.9%	15th 60.8%	7th 63.0%	6th 63.0%	1st 66.9%	9th 62.8%	8th 62.9%	11th 61.9%	10th 62.5%	13th 61.5%	4th 66.0%	16th 60.8%	18th 58.9%	17th 59.7%	21st 53.9%	14th 61.0%
38.1%		51%	41%	41%	50%	49%	14%	24%	42%	35%	47%	36%	30%	41%	26%	47%	52%	51%	12%	29%	30%	52%
38.7%		45%	41%	45%	45%	73%	18%	32%	34%	47%	64%	41%	34%	47%	44%	18%	57%	18%	17%	36%	47%	9%
78.6%		82%	83%	78%	93%	76%	68%	73%	82%	82%	93%	77%	72%	78%	72%	93%	77%	72%	72%	72%	70%	86%
55.6%		62%	56%	58%	58%	62%	56%	54%	59%	61%	69%	58%	52%	58%	66%	59%	57%	37%	30%	55%	43%	57%
62.8%		72%	68%	62%	67%	63%	53%	62%	52%	72%	61%	65%	67%	70%	56%	60%	66%	55%	57%	63%	63%	64%
59.1%		64%	51%	51%	68%	66%	44%	54%	57%	57%	68%	70%	59%	70%	67%	68%	72%	59%	38%	57%	25%	76%
62.5%		77%	77%	80%	80%	76%	49%	63%	64%	60%	52%	67%	58%	50%	50%	51%	67%	45%	45%	75%	70%	57%
51.3%		59%	47%	28%	44%	47%	38%	54%	54%	58%	44%	64%	59%	46%	51%	73%	46%	63%	56%	55%	40%	52%
64.6%		58%	65%	58%	58%	66%	72%	66%	71%	71%	73%	76%	55%	54%	62%	64%	60%	74%	71%	62%	53%	67%
73.8%		82%	71%	79%	83%	82%	79%	83%	60%	58%	58%	79%	85%	82%	85%	57%	53%	71%	70%	90%	82%	61%
55.9%		55%	53%	58%	58%	69%	43%	44%	52%	58%	70%	58%	54%	40%	56%	58%	65%	67%	75%	46%	37%	58%
69.5%		84%	68%	80%	80%	84%	59%	76%	78%	71%	73%	69%	70%	76%	71%	58%	70%	64%	60%	57%	58%	54%
61.4%		60%	58%	58%	62%	91%	54%	50%	64%	57%	72%	58%	54%	58%	55%	65%	74%	77%	57%	45%	54%	67%
64.6%		73%	85%	84%	64%	84%	49%	61%	46%	52%	59%	73%	39%	60%	64%	76%	65%	44%	72%	64%	66%	76%
62.8%		63%	57%	63%	54%	32%	71%	70%	55%	51%	58%	76%	78%	59%	76%	55%	60%	67%	65%	77%	81%	50%
60.7%		66%	64%	60%	64%	68%	60%	64%	71%	64%	70%	70%	47%	64%	62%	65%	78%	64%	45%	54%	58%	16%
66.6%		71%	71%	71%	71%	72%	64%	56%	73%	69%	64%	69%	54%	62%	58%	69%	64%	57%	72%	64%	69%	78%
77.1%		83%	84%	83%	70%	78%	83%	83%	78%	76%	65%	81%	83%	83%	80%	71%	78%	66%	65%	80%	83%	66%
74.8%		82%	73%	74%	74%	70%	67%	87%	85%	92%	75%	71%	85%	82%	76%	60%	77%	72%	73%	66%	68%	62%
79.4%		86%	81%	73%	81%	69%	53%	73%	81%	69%	82%	100%	62%	78%	84%	93%	81%	90%	89%	74%	81%	87%
75.0%		75%	75%	76%	85%	80%	72%	78%	85%	76%	84%	76%	78%	78%	79%	78%	76%	58%	36%	62%	76%	93%
71.2%		70%	80%	80%	80%	62%	70%	78%	63%	76%	68%	63%	63%	63%	70%	66%	76%	66%	76%	71%	76%	78%
61.3%		71%	58%	58%	75%	57%	48%	61%	63%	62%	87%	58%	72%	58%	73%	38%	73%	52%	69%	62%	15%	78%
71.2%		90%	85%	86%	74%	68%	69%	76%	71%	80%	65%	74%	66%	86%	62%	39%	72%	58%	61%	69%	78%	66%
63.6%		70%	59%	70%	66%	38%	60%	67%	62%	64%	65%	71%	59%	64%	64%	69%	68%	57%	70%	64%	69%	60%
76.6%		79%	85%	72%	92%	85%	79%	71%	65%	68%	76%	73%	85%	85%	76%	76%	73%	55%	72%	95%	71%	75%
65.6%		56%	40%	58%	75%	75%	57%	49%	81%	66%	60%	58%	72%	60%	63%	68%	79%	76%	82%	62%	52%	88%
64.9%		63%	67%	63%	76%	41%	37%	67%	71%	70%	76%	68%	64%	59%	60%	67%	78%	86%	78%	51%	44%	76%
42.0%		56%	49%	45%	45%	46%	32%	51%	64%	48%	62%	45%	49%	49%	39%	21%	32%	32%	25%	38%	29%	24%
62.9%		64%	71%	71%	69%	54%	48%	54%	64%	67%	69%	56%	56%	64%	66%	70%	63%	74%	67%	52%	56%	66%
74.1%		83%	75%	75%	85%	47%	69%	75%	82%	85%	85%	75%	84%	75%	90%	70%	90%	84%	46%	85%	44%	53%
55.8%		54%	54%	48%	42%	66%	58%	58%	61%	57%	67%	54%	64%	73%	68%	41%	42%	69%	68%	68%	28%	31%
68.9%		72%	67%	73%	96%	78%	50%	66%	45%	72%	73%	90%	65%	54%	66%	96%	75%	68%	69%	56%	48%	67%
48.6%		59%	50%	51%	54%	78%	49%	54%	54%	54%	63%	54%	36%	54%	47%	33%	57%	34%	31%	44%	47%	18%
50.7%		54%	40%	44%	58%	40%	40%	55%	47%	52%	78%	58%	48%	58%	56%	15%	62%	66%	56%	45%	24%	69%
66.6%		75%	67%	67%	73%	44%	68%	67%	67%	74%	73%	67%	67%	67%	74%	74%	76%	52%	71%	74%	44%	58%
41.9%		47%	46%	30%	36%	30%	44%	44%	45%	36%	47%	30%	37%	47%	44%	64%	46%	60%	13%	51%	30%	52%
41.6%		50%	48%	43%	43%	39%	35%	45%	37%	41%	40%	40%	46%	38%	39%	39%	43%	56%	30%	39%	37%	46%
55.3%		59%	54%	54%	59%	45%	49%	59%	60%	60%	59%	66%	62%	52%	64%	43%	67%	63%	67%	52%	31%	37%
73.1%		75%	78%	67%	72%	93%	66%	58%	70%	75%	67%	75%	78%	67%	71%	72%	75%	81%	73%	78%	75%	70%
67.4%		75%	71%	75%	80%	66%	59%	73%	75%	78%	83%	63%	54%	80%	62%	77%	73%	71%	66%	50%	63%	22%
58.0%		67%	66%	62%	62%	52%	76%	62%	58%	59%	49%	52%	52%	52%	45%	58%	51%	45%	45%	88%	74%	44%
52.4%		53%	49%	44%	44%	56%	41%	43%	50%	47%	44%	50%	58%	32%	65%	68%	67%	65%	71%	47%	44%	63%
68.4%		72%	72%	72%	71%	67%	74%	71%	71%	67%	63%	63%	70%	64%	74%	58%	63%	64%	73%	72%	72%	64%
69.7%		73%	72%	73%	73%	67%	53%	64%	69%	70%	84%	67%	67%	73%	73%	67%	74%	74%	77%	61%	57%	75%
75.9%		80%	66%	81%	78%	87%	73%	76%	72%	80%	80%	73%	73%	70%	79%	59%	85%	76%	77%	81%	77%	70%
56.0%		76%	62%	63%	63%	78%	45%	65%	69%	53%	55%	53%	60%	55%	46%	44%	57%	37%	50%	48%	53%	44%
71.9%		72%	70%	85%	95%	57%	54%	65%	65%	57%	79%	79%	65%	85%	84%	65%	79%	67%	95%	65%	48%	79%
55.9%		52%	62%	60%	56%	24%	54%	68%	55%	55%	53%	55%	53%	55%	55%	62%	68%	61%	44%	53%	68%	60%
67.6%		61%	73%	69%	75%	61%	57%	72%	69%	76%	73%	61%	77%	69%	71%	56%	65%	69%	63%	70%	70%	62%
55.4%		52%	54%	52%	51%	46%	42%	69%	74%	71%	51%	51%	75%	67%	58%	41%	52%	57%	67%	49%	42%	42%
56.6%		63%	62%	69%	78%	0%	57%	52%	69%	63%	62%	58%	66%	69%	58%	55%	44%	78%	21%	64%	39%	62%
61.3%		58%	64%	65%	77%	64%	33%	44%	55%	70%	65%	64%	93%	56%	76%	73%	64%	74%	20%	58%	48%	66%
57.4%		71%	66%	63%	60%	53%	59%	65%	60%	63%	71%	58%	58%	58%	73%	33%	64%	33%	33%	63%	56%	45%
43.0%		41%	41%	41%	47%	19%	26%	26%	46%	41%	42%	41%	47%	41%	41%	70%	52%	53%	54%	44%	25%	65%
72.7%		81%	74%	75%	73%	61%	67%	69%	68%	72%	70%	81%	72%	72%	75%	76%	79%	52%	87%	75%	81%	67%
72.9%		78%	69%	87%	75%	96%	62%	75%	68%	69%	75%	63%	73%	78%	56%	68%	88%	95%	80%	54%	62%	59%
47.2%		47%	46%	47%	58%	58%	42%	38%	51%	56%	58%	47%	41%	47%	43%	35%	52%	61%	46%	41%	30%	47%
50.0%		56%	50%	44%	67%	72%	37%	58%	48%	50%	67%	50%	41%	50%	47%	50%	57%	30%	61%	40%	50%	25%
73.3%		74%	86%	84%	77%	47%	79%	82%	77%	74%	64%	81%	81%	84%	66%	50%	74%	72%	56%	85%	84%	62%
68.5%		70%	69%	64%	71%	45%	71%	68%	72%	69%	72%	72%	61%	64%	70%	68%	75%	69%	80%	70%	60%	78%
59.8%		72%	66%	57%	70%	60%	33%	51%	64%	61%	69%	39%	63%	69%	40%	83%	68%	70%	57%	47%	43%	73%
67.2%		70%	73%	70%	71%	70%	74%	65%	77%	71%	68%	70%	61%	71%	59%	59%	70%	51%	52%	77%	63%	70%
64.7%		70%	69%	58%	70%	51%	59%	59%	62%	76%	67%	58%	71%	58%	71%	65%	73%	76%	75%	65%	40%	66%
55.7%		69%	48%	56%	58%	28%	50%	50%	55%	62%	72%	50%	67%	56%	69%	74%	69%	42%	71%	33%	18%	72%
58.5%		56%	56%	47%	60%	76%	36%	62%	58%	74%	79%	60%	51%	60%	53%	70%	63%	51%	53%	38%	46%	79%
55.8%		60%	55%	58%	58%	59%	42%	58%	69%	71%	67%	58%	54%	58%	43%	58%	58%	62%	26%	43%	47%	67%
55.9%		51%	58%	60%	50%	34%	55%	70%	54%	62%	48%	48%	69%	62%	74%	55%	50%	62%	59%	61%	48%	43%
60.5%		59%	64%	69%	60%	54%	62%	63%	61%	53%	63%	67%	49%	69%	64%	60%	61%	60%	50%	64%	58%	60%
66.5%		63%	80%	63%	71%	58%	62%	52%	45%	58%	71%	75%	79%	63%	67%	75%	75%	60%	68%	71%	65%	75%
64.0%		73%	67%	67%	73%	57%	59%	67%	63%	59%	80%	61%	68%	67%	60%	49%	68%	53%	64%	63%	60%	67%
65.7%		75%	74%	70%	77%	55%	61%	52%	64%	70%	81%	70%	63%	70%	67%	67%	76%	72%	35%	60%	52%	69%
75.3%		77%	76%	66%	78%	77%	64%	62%	83%	78%	97%	73%	77%	78%	62%	77%	78%	67%	82%	70%	66%	94%
56.4%		64%	66%	50%	70%	34%	74%	64%	50%	50%	57%	65%	61%	50%	62%	51%	40%	50%	44%	77%	66%	39%
48.2%		56%	53%	43%	58%	44%	48%	46%	46%	48%	58%	39%	49%	43%	53%	33%	52%	60%	56%	48%	23%	56%
60.4%		65%	64%	73%	68%	41%	73%	68%	55%	53%	54%	61%	66%	61%	66%	49%	61%	56%	44%	67%	73%	50%
75.0%		74%	73%	75%	75%	76%	68%	81%	65%	81%	67%	81%	82%	81%	78%	73%	78%	83%	60%	81%	75%	67%
70.1%		67%	72%	72%	71%	57%	55%	70%	72%	72%	74%	77%	75%	75%	74%	70%	75%	61%	66%	71%	77%	70%
49.0%		50%	49%	53%	53%	78%	40%	38%	45%	44%	53%	50%	50%	37%	54%	67%	65%	52%	19%	48%	32%	53%
60.9%		69%	59%	59%	70%	39%	48%	53%	62%	61%	70%	70%	65%	59%	62%	75%	62%	65%	65%	54%	44%	67%
69.0%		63%	74%	56%	56%	64%	76%	63%	74%	70%	77%	70%	77%	76%	76%	74%	77%	56%	82%	72%	76%	40%
51.0%		65%	49%	48%	42%	48%	27%	54%	66%	48%	65%	41%	64%	48%	48%	36%	57%	62%	51%	40%	36%	75%
56.3%		67%	58%	62%	61%	66%	45%	63%	68%	55%	73%	58%	53%	58%	41%	46%	64%	51%	47%	44%	45%	58%
65.9%		63%	74%	73%	76%	68%	65%	76%	58%	67%	58%	63%	58%	58%	73%	53%	70%	66%	56%	58%	73%	77%
72.8%		81%	65%	72%	81%	61%	67%	72%	85%	77%	75%	80%	73%	80%	75%	80%	75%	51%	75%	73%	54%	76%
51.7%		62%	53%	43%	58%	55%	48%	46%	46%	48%	69%	43%	53%	43%	53%	52%	58%	58%	56%	48%	32%	62%
59.9%		67%	67%	62%	69%	36%	51%	48%	66%	52%	70%	55%	75%	55%	63%	70%	59%	66%	75%	49%	43%	59%
74.0%		76%	80%	84%	71%	76%	66%	80%	73%	83%	78%	75%	72%	78%	74%	65%	75%	68%	67%	76%	76%	61%
64.1%		61%	68%	60%	60%	45%	53%	76%	50%	64%	63%	67%	68%	60%	79%	84%	77%	73%	64%	64%	45%	66%
47.7%		62%	54%	38%	51%	39%	31%	38%	51%	38%	65%	51%	78%	50%	54%	45%	53%	55%	36%	58%	31%	23%
57.0%		62%	50%	51%	59%	65%	47%	60%	50%	69%	63%	54%	51%	51%	66%	72%	65%	64%	26%	56%	54%	63%
67.1%		60%	71%	58%	64%	68%	66%	83%	88%	84%	72%	59%	68%	67%	72%	67%	70%	57%	67%	69%	28%	72%
43.9%		57%	57%	40%	57%	0%	38%	42%	32%	42%	52%	40%	61%	42%	49%	34%	39%	29%	75%	68%	44%	24%
53.4%		53%	57%	52%	52%	56%	25%	52%	65%	48%	59%	44%	56%	56%	43%	63%	67%	69%	69%	25%	40%	70%
71.0%		74%	80%	76%	76%	61%	69%	72%	76%	78%	67%	78%	71%	78%	78%	39%	79%	66%	56%	82%	72%	63%
50.6%		53%	38%	38%	53%	40%	50%	46%	54%	56%	53%	49%	46%	56%	62%	56%	58%	59%	67%	47%	25%	57%
72.5%		79%	76%	78%	80%	38%	78%	75%	87%	69%	83%	67%	76%	79%	76%	68%	76%	47%	68%	74%	79%	69%
49.0%		47%	46%	55%	43%	31%	61%	53%	50%	51%	37%	48%	55%	55%	55%	43%	47%	55%	42%	56%	55%	43%
62.0%		71%	62%	63%	79%	83%	45%	71%	73%	62%	76%	77%	60%	62%	60%	56%	73%	27%	54%	50%	62%	37%
53.5%		53%	49%	51%	52%	41%	56%	52%	51%	57%	62%	50%	55%	49%	59%	58%	56%	59%	64%	51%	37%	62%
46.4%		54%	57%	49%	47%	0%	54%	43%	54%	44%	49%	49%	56%	49%	36%	36%	32%	62%	62%	41%	49%	52%
57.0%		45%	52%	53%	77%	55%	44%	50%	56%	65%	60%	50%	50%	50%	59%	68%	63%	74%	61%	44%	53%	67%
79.4%		92%	81%	69%	82%	85%	81%	72%	81%	73%	78%	75%	85%	72%	70%	98%	90%	73%	61%	82%	82%	85%
54.9%		64%	58%	47%	52%	46%	28%	39%	52%	39%	64%	64%	42%	58%	55%	79%	64%	63%	55%	52%	52%	79%
45.0%		52%	36%	38%	42%	52%	23%	38%	55%	52%	41%	36%	64%	44%	41%	37%	50%	47%	70%	31%	25%	70%
67.3%		73%	80%	81%	79%	57%	58%	63%	66%	62%	75%	71%	52%	52%	52%	96%	79%	57%	42%	52%	79%	87%
70.4%		73%	79%	37%	47%	68%	63%	78%	79%	79%	94%	97%	54%	57%	70%	87%	77%	67%	70%	64%	45%	94%
41.5%		50%	46%	46%	48%	62%	18%	46%	43%	43%	60%	52%	36%	43%	44%	49%	47%	13%	25%	34%	43%	24%
59.6%		54%	53%	63%	54%	60%	67%	63%	63%	61%	63%	58%	59%	63%	63%	54%	65%	52%	56%	56%	65%	60%
63.7%		72%	61%	53%	77%	77%	59%	49%	62%	67%	73%	57%	66%	57%	54%	77%	66%	69%	70%	54%	50%	67%
53.2%		52%	42%	42%	52%	47%	45%	53%	53%	55%	52%	58%	58%	58%	56%	59%	57%	63%	65%	56%	42%	52%
56.8%		70%	58%	58%	80%	67%	36%	41%	63%	56%	66%	72%	55%	50%	51%	70%	66%	50%	62%	34%	28%	60%
79.5%		77%	79%	76%	82%	73%	87%	72%	82%	73%	90%	82%	85%	77%	82%	76%	78%	69%	90%	82%	82%	76%
77.5%		78%	85%	71%	89%	48%	75%	73%	77%	76%	89%	71%	85%	89%	85%	86%	88%	84%	85%	76%	42%	75%
74.6%		83%	85%	75%	75%	64%	77%	72%	76%	75%	76%	76%	88%	68%	67%	67%	79%	73%	66%	80%	83%	61%
81.3%		89%	83%	89%	89%	71%	67%	83%	80%	86%	78%	83%	83%	71%	82%	92%	89%	85%	85%	76%	71%	75%