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 01e41f8...

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

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
66.5%
2.GPT 4.1
66.4%
3.Claude Haiku 4.5
63.6%
4.Mistral Medium 3
63.2%
5.GPT 4.1 Nano
62.7%

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 63.6%	8th 61.9%	1st 66.5%	11th 57.3%	12th 54.6%	9th 60.1%	4th 63.2%	2nd 66.4%	7th 62.1%	5th 62.7%	6th 62.4%	10th 60.1%	13th 54.5%
35.6%		41%	41%	50%	55%	14%	24%	35%	47%	36%	30%	26%	29%	35%
44.6%		45%	45%	41%	86%	18%	32%	47%	64%	47%	41%	37%	36%	41%
77.9%		83%	78%	93%	76%	67%	73%	87%	93%	77%	72%	72%	72%	70%
56.5%		56%	58%	58%	52%	56%	54%	61%	62%	58%	52%	66%	59%	43%
64.0%		64%	70%	70%	60%	53%	62%	72%	61%	67%	67%	60%	63%	63%
55.5%		51%	51%	68%	66%	44%	54%	57%	68%	51%	64%	67%	57%	23%
64.3%		77%	80%	80%	80%	49%	63%	57%	52%	62%	45%	50%	71%	70%
45.8%		46%	28%	44%	47%	38%	48%	46%	32%	80%	40%	51%	55%	40%
64.6%		65%	58%	58%	61%	71%	66%	71%	72%	76%	65%	66%	58%	53%
76.9%		68%	79%	83%	88%	74%	68%	59%	58%	85%	88%	85%	83%	82%
53.5%		53%	58%	58%	69%	43%	44%	58%	58%	58%	54%	56%	49%	37%
69.2%		68%	80%	81%	64%	59%	76%	71%	77%	77%	63%	71%	55%	58%
57.1%		58%	58%	62%	85%	51%	46%	57%	72%	58%	54%	55%	45%	41%
64.2%		85%	84%	64%	58%	49%	61%	52%	66%	66%	44%	61%	71%	73%
62.7%		57%	63%	54%	12%	66%	66%	51%	58%	76%	76%	76%	79%	81%
61.2%		64%	60%	60%	68%	58%	64%	64%	70%	64%	47%	62%	54%	60%
66.5%		71%	71%	71%	73%	64%	56%	69%	69%	69%	54%	58%	71%	69%
79.1%		84%	83%	63%	74%	83%	83%	83%	67%	81%	83%	81%	80%	83%
74.5%		73%	74%	74%	70%	62%	87%	92%	79%	71%	85%	76%	68%	58%
76.4%		92%	73%	81%	69%	53%	73%	69%	82%	100%	62%	84%	74%	81%
77.8%		75%	76%	85%	78%	72%	78%	76%	96%	76%	78%	80%	65%	76%
72.3%		80%	80%	80%	70%	70%	78%	70%	70%	70%	63%	70%	63%	76%
61.0%		58%	58%	75%	57%	48%	61%	76%	94%	44%	72%	73%	62%	15%
71.4%		85%	86%	74%	68%	69%	76%	71%	74%	64%	64%	62%	66%	69%
63.9%		59%	64%	66%	47%	63%	63%	55%	70%	71%	64%	72%	68%	69%
78.4%		85%	72%	92%	85%	79%	70%	68%	76%	73%	77%	76%	95%	71%
60.4%		40%	58%	75%	67%	59%	49%	66%	60%	58%	72%	67%	62%	52%
57.7%		67%	63%	74%	10%	37%	55%	70%	68%	68%	64%	60%	57%	57%
44.0%		49%	45%	45%	46%	32%	50%	48%	56%	38%	49%	39%	37%	38%
62.0%		65%	71%	69%	45%	46%	61%	67%	69%	64%	64%	66%	58%	61%
74.9%		75%	75%	85%	47%	69%	75%	85%	85%	75%	84%	90%	85%	44%
56.4%		54%	48%	48%	66%	58%	58%	61%	64%	54%	64%	68%	70%	20%
66.6%		68%	49%	96%	74%	54%	66%	79%	68%	73%	65%	68%	52%	54%
51.7%		50%	51%	54%	78%	54%	54%	54%	54%	54%	36%	51%	35%	47%
50.3%		40%	40%	58%	72%	40%	40%	46%	78%	53%	51%	56%	47%	33%
68.1%		67%	67%	73%	70%	68%	67%	74%	73%	66%	67%	74%	74%	45%
39.3%		46%	30%	36%	30%	44%	44%	41%	47%	30%	41%	44%	37%	41%
43.5%		48%	43%	43%	43%	39%	45%	48%	45%	46%	43%	46%	39%	37%
54.8%		54%	54%	59%	45%	49%	59%	66%	59%	59%	54%	64%	60%	31%
71.3%		78%	67%	67%	93%	66%	58%	66%	67%	69%	76%	66%	79%	75%
69.1%		71%	75%	80%	78%	62%	73%	74%	83%	75%	54%	60%	50%	63%
61.5%		66%	62%	62%	52%	74%	62%	59%	49%	62%	52%	45%	81%	74%
48.4%		49%	44%	44%	59%	37%	43%	60%	44%	51%	58%	51%	39%	50%
69.6%		72%	65%	67%	68%	73%	71%	67%	65%	63%	74%	74%	74%	72%
65.8%		72%	73%	73%	56%	53%	58%	70%	73%	73%	67%	69%	61%	57%
76.2%		66%	81%	78%	78%	73%	77%	80%	73%	77%	73%	79%	79%	77%
55.7%		62%	63%	63%	60%	48%	65%	53%	55%	48%	57%	46%	51%	53%
69.8%		70%	85%	92%	65%	54%	65%	57%	79%	79%	65%	84%	65%	48%
54.2%		63%	60%	56%	24%	54%	68%	55%	53%	53%	46%	52%	53%	68%
68.8%		72%	63%	75%	61%	63%	72%	76%	66%	61%	77%	68%	70%	70%
57.9%		54%	58%	51%	55%	42%	69%	76%	62%	51%	76%	58%	59%	42%
58.6%		64%	69%	78%	0%	59%	52%	66%	69%	58%	85%	53%	65%	44%
62.3%		71%	65%	77%	64%	33%	47%	70%	63%	66%	86%	62%	58%	48%
62.1%		70%	63%	60%	51%	55%	75%	63%	71%	58%	58%	69%	58%	56%
38.5%		41%	41%	58%	23%	26%	26%	41%	42%	41%	47%	39%	44%	31%
73.0%		74%	73%	73%	61%	70%	79%	81%	66%	81%	72%	72%	72%	75%
69.5%		69%	87%	75%	70%	62%	75%	69%	71%	66%	70%	63%	57%	69%
47.5%		46%	47%	52%	64%	42%	41%	56%	58%	47%	41%	43%	35%	46%
51.6%		50%	53%	67%	72%	40%	58%	50%	58%	54%	32%	47%	40%	50%
77.2%		86%	84%	84%	53%	79%	82%	72%	63%	81%	81%	69%	85%	84%
66.5%		68%	64%	71%	57%	69%	68%	62%	72%	72%	62%	70%	70%	60%
54.5%		66%	57%	71%	65%	33%	51%	61%	69%	39%	53%	47%	52%	44%
70.0%		77%	71%	80%	79%	74%	65%	71%	71%	68%	64%	59%	68%	63%
63.4%		67%	70%	70%	54%	59%	59%	77%	67%	58%	71%	71%	61%	40%
53.8%		48%	56%	56%	57%	44%	50%	62%	72%	50%	67%	69%	52%	16%
58.2%		56%	56%	60%	97%	36%	57%	74%	76%	60%	35%	57%	47%	46%
52.8%		55%	58%	58%	63%	37%	63%	62%	67%	43%	54%	41%	39%	47%
56.5%		60%	55%	51%	41%	59%	65%	62%	44%	51%	63%	74%	61%	48%
60.2%		64%	69%	60%	50%	62%	63%	53%	63%	66%	49%	64%	61%	58%
64.5%		80%	79%	71%	46%	62%	52%	58%	58%	75%	63%	62%	67%	65%
63.2%		67%	67%	73%	57%	60%	67%	57%	67%	61%	64%	60%	62%	60%
67.1%		69%	70%	77%	55%	62%	66%	70%	81%	70%	59%	67%	74%	52%
72.2%		74%	77%	78%	78%	64%	66%	78%	97%	73%	62%	55%	70%	66%
61.1%		66%	50%	70%	55%	67%	64%	50%	58%	59%	61%	62%	66%	66%
47.8%		53%	43%	58%	51%	48%	46%	48%	58%	39%	49%	53%	48%	28%
63.3%		64%	73%	68%	41%	73%	68%	53%	54%	66%	66%	65%	59%	73%
74.7%		73%	75%	75%	54%	68%	81%	85%	76%	81%	72%	78%	78%	75%
68.8%		72%	72%	68%	53%	55%	71%	72%	65%	72%	73%	74%	74%	73%
50.6%		49%	53%	53%	78%	40%	41%	44%	60%	53%	50%	54%	49%	34%
58.1%		59%	59%	70%	46%	48%	53%	61%	67%	59%	65%	62%	62%	44%
68.7%		74%	56%	54%	63%	76%	63%	63%	70%	76%	76%	76%	70%	76%
48.8%		49%	48%	42%	58%	27%	54%	53%	65%	47%	73%	42%	40%	36%
55.1%		58%	62%	62%	53%	45%	63%	55%	73%	58%	51%	47%	44%	45%
67.3%		77%	73%	76%	59%	65%	71%	67%	61%	68%	58%	63%	58%	79%
71.6%		62%	72%	76%	61%	67%	72%	77%	80%	80%	80%	78%	73%	53%
49.4%		53%	43%	58%	55%	48%	46%	48%	62%	43%	53%	53%	48%	32%
57.5%		68%	62%	69%	31%	44%	51%	52%	70%	60%	75%	63%	55%	47%
77.7%		80%	84%	72%	76%	66%	80%	74%	78%	83%	80%	74%	83%	80%
63.5%		68%	60%	60%	45%	53%	76%	64%	64%	67%	75%	86%	62%	45%
49.2%		54%	51%	56%	31%	31%	38%	38%	62%	51%	78%	54%	58%	38%
57.0%		50%	51%	59%	65%	47%	60%	64%	63%	54%	54%	67%	56%	51%
64.8%		55%	46%	64%	84%	66%	83%	84%	67%	43%	74%	74%	69%	34%
44.2%		57%	40%	57%	0%	38%	42%	42%	52%	40%	61%	49%	56%	40%
47.1%		57%	44%	52%	44%	25%	48%	51%	59%	48%	61%	43%	40%	40%
74.2%		74%	65%	76%	61%	69%	72%	78%	80%	78%	79%	78%	82%	72%
48.5%		38%	38%	53%	57%	49%	46%	56%	53%	56%	62%	52%	44%	26%
72.8%		76%	78%	80%	44%	78%	70%	69%	79%	67%	76%	77%	74%	79%
51.1%		46%	55%	49%	43%	59%	53%	51%	48%	48%	48%	53%	56%	55%
65.0%		62%	66%	79%	83%	45%	71%	62%	76%	62%	60%	67%	50%	62%
52.4%		49%	51%	62%	51%	56%	52%	51%	50%	50%	55%	59%	57%	38%
45.8%		56%	49%	64%	0%	42%	43%	44%	43%	49%	56%	48%	52%	49%
50.6%		52%	53%	77%	0%	45%	50%	65%	57%	50%	50%	62%	44%	53%
76.2%		81%	69%	82%	67%	81%	72%	73%	72%	75%	85%	69%	82%	82%
50.8%		58%	47%	52%	56%	28%	39%	39%	64%	58%	65%	55%	52%	47%
40.3%		43%	36%	42%	53%	23%	44%	52%	52%	36%	52%	41%	25%	25%
63.8%		80%	81%	85%	0%	59%	68%	64%	73%	71%	59%	52%	61%	77%
65.2%		79%	53%	47%	74%	75%	10%	82%	97%	92%	60%	70%	64%	45%
43.6%		46%	46%	48%	62%	19%	43%	43%	55%	46%	40%	42%	34%	43%
62.0%		53%	63%	65%	63%	62%	65%	63%	63%	63%	62%	63%	56%	65%
61.8%		61%	53%	77%	91%	54%	49%	71%	60%	57%	60%	54%	66%	50%
49.4%		42%	42%	52%	47%	45%	51%	55%	61%	42%	51%	56%	56%	42%
47.9%		58%	58%	66%	0%	36%	47%	61%	66%	66%	52%	51%	34%	28%
80.5%		79%	76%	82%	75%	87%	72%	73%	90%	82%	85%	82%	82%	82%
75.2%		85%	71%	89%	48%	75%	74%	86%	89%	71%	83%	85%	76%	46%
76.8%		85%	75%	75%	70%	77%	67%	75%	79%	76%	96%	67%	77%	79%
81.0%		89%	89%	89%	83%	62%	83%	86%	89%	71%	83%	82%	76%	71%