DTeval

A Collective Intelligence Project

Loading blueprint versions...

Please wait while we gather all the unique runs for this blueprint.

Analysis: Gd4 Ctx Dtef Global Dialogues Gd4 Country%3Asouth Africa Ctx - Run a38fd63...

Global Dialogues GD4 - South Africa (with context)

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

Efficiency & Succinctness

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
71.7%
2.GPT 4.1
71.6%
3.Claude Sonnet 4
70.9%
4.Claude Haiku 4.5
70.6%
5.Mistral Medium 3
69.3%

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		4th 70.6%	3rd 70.9%	1st 71.7%	6th 68.8%	13th 61.1%	7th 67.8%	5th 69.3%	2nd 71.6%	9th 66.9%	12th 61.3%	11th 65.1%	10th 65.6%	8th 67.7%
49.3%		41%	57%	52%	68%	31%	41%	52%	52%	52%	29%	57%	52%	57%
58.2%		63%	58%	67%	75%	33%	47%	69%	78%	58%	33%	58%	60%	58%
60.7%		58%	74%	72%	74%	65%	44%	68%	82%	42%	34%	63%	55%	58%
65.3%		76%	76%	61%	62%	60%	74%	62%	62%	62%	68%	62%	62%	62%
65.1%		75%	67%	61%	41%	59%	74%	67%	68%	60%	63%	67%	70%	74%
73.2%		69%	87%	75%	100%	67%	67%	74%	87%	66%	60%	55%	69%	75%
68.9%		91%	90%	100%	73%	45%	57%	79%	55%	45%	45%	58%	79%	79%
66.5%		69%	61%	59%	75%	50%	75%	69%	78%	75%	50%	75%	64%	64%
79.5%		74%	74%	91%	83%	79%	79%	75%	88%	75%	75%	75%	91%	74%
50.7%		50%	45%	50%	45%	62%	45%	45%	50%	49%	45%	49%	45%	79%
68.4%		78%	72%	72%	78%	56%	73%	69%	72%	66%	60%	66%	67%	60%
70.0%		65%	75%	75%	55%	74%	75%	74%	78%	67%	59%	74%	67%	72%
78.0%		78%	78%	78%	78%	78%	78%	78%	78%	78%	78%	78%	78%	78%
70.4%		89%	84%	71%	76%	64%	55%	67%	74%	74%	67%	67%	67%	60%
56.2%		73%	47%	57%	43%	82%	60%	40%	59%	54%	51%	67%	51%	47%
68.9%		78%	67%	70%	78%	60%	65%	67%	78%	63%	60%	67%	73%	70%
68.9%		75%	80%	71%	78%	52%	75%	69%	78%	65%	69%	62%	65%	57%
72.0%		80%	78%	68%	77%	80%	78%	65%	65%	82%	64%	65%	67%	67%
72.5%		70%	82%	76%	54%	82%	79%	87%	73%	70%	70%	59%	70%	70%
84.5%		96%	96%	88%	96%	52%	84%	87%	87%	87%	58%	94%	87%	87%
66.9%		67%	57%	72%	82%	66%	52%	67%	73%	67%	60%	73%	67%	67%
75.2%		84%	90%	80%	69%	63%	90%	75%	80%	69%	75%	75%	59%	69%
75.2%		74%	74%	100%	88%	68%	75%	75%	74%	60%	56%	60%	90%	83%
63.0%		76%	61%	58%	73%	69%	64%	68%	65%	59%	56%	56%	47%	67%
67.1%		74%	74%	66%	37%	64%	74%	77%	65%	69%	68%	56%	71%	77%
83.4%		85%	92%	100%	85%	85%	66%	85%	79%	85%	67%	85%	85%	85%
66.5%		74%	72%	68%	70%	60%	58%	60%	68%	70%	70%	70%	54%	70%
70.8%		81%	81%	87%	78%	52%	70%	74%	71%	70%	59%	68%	65%	65%
58.2%		60%	64%	68%	78%	50%	60%	51%	74%	46%	50%	51%	54%	51%
75.7%		70%	74%	68%	77%	60%	65%	89%	89%	84%	47%	89%	83%	89%
76.0%		77%	73%	89%	70%	83%	83%	70%	73%	74%	73%	74%	79%	70%
68.7%		70%	82%	74%	65%	66%	70%	59%	82%	80%	54%	65%	61%	65%
83.9%		91%	91%	91%	91%	60%	91%	91%	100%	83%	91%	69%	67%	75%
64.8%		68%	54%	78%	70%	50%	68%	69%	78%	63%	59%	63%	59%	63%
67.5%		57%	60%	72%	84%	36%	78%	69%	75%	69%	40%	68%	100%	69%
63.9%		76%	59%	60%	60%	70%	60%	60%	59%	76%	58%	47%	86%	60%
69.8%		65%	60%	61%	78%	54%	76%	71%	71%	76%	65%	76%	78%	76%
54.3%		57%	50%	50%	50%	57%	57%	57%	50%	50%	57%	57%	57%	57%
59.4%		55%	64%	71%	62%	62%	55%	54%	64%	62%	55%	60%	48%	60%
62.5%		57%	68%	83%	74%	57%	57%	75%	57%	57%	57%	57%	57%	57%
71.6%		75%	78%	83%	65%	60%	75%	75%	77%	75%	54%	78%	61%	75%
57.6%		64%	75%	52%	46%	57%	69%	64%	39%	57%	75%	42%	57%	52%
75.0%		82%	82%	82%	74%	60%	66%	77%	82%	74%	82%	58%	74%	82%
67.0%		60%	66%	65%	70%	69%	65%	62%	73%	71%	64%	65%	71%	70%
69.4%		73%	100%	70%	60%	68%	73%	66%	78%	58%	58%	58%	58%	82%
79.5%		68%	92%	80%	69%	66%	90%	77%	84%	84%	78%	80%	75%	91%
60.1%		68%	60%	66%	71%	54%	68%	54%	56%	62%	52%	52%	62%	56%
83.6%		92%	92%	83%	92%	10%	85%	92%	100%	85%	72%	92%	100%	92%
68.3%		69%	60%	72%	80%	49%	72%	62%	78%	80%	68%	69%	49%	80%
72.4%		77%	73%	78%	79%	70%	70%	71%	73%	70%	70%	70%	70%	70%
70.5%		79%	67%	66%	79%	73%	57%	67%	80%	73%	65%	65%	73%	73%
88.3%		75%	100%	78%	78%	88%	100%	92%	87%	87%	92%	87%	92%	92%
71.9%		78%	77%	77%	76%	37%	75%	78%	69%	69%	69%	69%	92%	69%
62.2%		70%	67%	57%	79%	72%	68%	61%	59%	70%	59%	45%	64%	37%
60.5%		60%	60%	60%	60%	67%	60%	60%	60%	60%	60%	60%	60%	60%
67.9%		70%	71%	59%	60%	69%	64%	70%	70%	70%	70%	70%	70%	70%
66.1%		69%	71%	75%	19%	85%	74%	87%	79%	67%	37%	69%	66%	61%
75.6%		78%	78%	78%	78%	47%	78%	78%	78%	78%	78%	78%	78%	78%
63.2%		60%	70%	70%	70%	45%	70%	60%	70%	70%	46%	70%	51%	70%
64.9%		87%	64%	80%	48%	80%	61%	73%	64%	64%	48%	64%	48%	63%
74.6%		73%	77%	77%	56%	84%	84%	68%	80%	73%	73%	73%	73%	79%
67.7%		64%	91%	81%	83%	46%	57%	78%	64%	62%	58%	69%	65%	62%
64.1%		78%	68%	68%	57%	68%	68%	78%	71%	50%	50%	50%	50%	77%
58.2%		60%	60%	63%	69%	75%	60%	71%	63%	45%	45%	56%	45%	45%
69.2%		63%	74%	73%	87%	65%	66%	76%	74%	58%	58%	60%	67%	78%
57.8%		55%	52%	65%	92%	52%	58%	78%	76%	65%	40%	31%	33%	55%
57.2%		59%	68%	68%	69%	51%	62%	68%	75%	49%	46%	36%	46%	46%
62.2%		65%	64%	55%	44%	74%	56%	63%	60%	60%	78%	65%	65%	59%
63.8%		65%	72%	63%	52%	66%	64%	62%	73%	67%	49%	73%	61%	63%
68.9%		78%	70%	79%	33%	75%	61%	61%	70%	78%	76%	75%	70%	70%
70.5%		70%	74%	79%	70%	67%	74%	70%	70%	70%	62%	70%	70%	70%
71.2%		83%	83%	73%	68%	68%	77%	56%	74%	62%	64%	74%	74%	69%
74.2%		63%	76%	100%	78%	69%	54%	100%	92%	92%	22%	66%	92%	61%
45.9%		47%	37%	49%	49%	62%	49%	49%	36%	36%	47%	50%	49%	37%
62.8%		60%	68%	60%	74%	53%	76%	57%	60%	74%	53%	60%	62%	60%
63.4%		72%	72%	76%	60%	68%	72%	60%	64%	60%	45%	60%	55%	60%
71.0%		82%	70%	70%	69%	72%	75%	65%	70%	59%	82%	60%	67%	82%
65.2%		62%	67%	73%	46%	74%	63%	66%	76%	76%	66%	66%	46%	66%
62.8%		62%	63%	70%	84%	54%	62%	64%	84%	58%	52%	54%	58%	52%
60.4%		60%	60%	60%	60%	65%	60%	60%	60%	60%	60%	60%	60%	60%
53.2%		50%	50%	66%	50%	50%	58%	58%	60%	50%	50%	50%	50%	50%
63.8%		71%	63%	76%	73%	71%	50%	63%	55%	49%	55%	73%	76%	55%
69.1%		74%	74%	82%	82%	54%	68%	74%	76%	74%	75%	52%	68%	45%
82.2%		100%	79%	60%	80%	55%	91%	90%	91%	90%	89%	84%	69%	90%
72.8%		80%	59%	66%	60%	62%	77%	82%	82%	80%	77%	80%	65%	76%
64.1%		74%	65%	70%	52%	55%	76%	50%	56%	78%	53%	81%	62%	61%
60.4%		67%	66%	65%	59%	65%	53%	57%	65%	59%	52%	59%	59%	59%
76.5%		74%	62%	90%	55%	80%	100%	78%	74%	83%	75%	62%	82%	80%
71.8%		62%	58%	62%	79%	84%	76%	80%	82%	75%	82%	59%	59%	75%
75.5%		100%	100%	78%	80%	24%	69%	78%	89%	64%	78%	69%	72%	80%
64.7%		68%	75%	75%	78%	50%	75%	78%	59%	61%	54%	49%	56%	63%
55.8%		57%	67%	52%	47%	54%	65%	62%	66%	54%	62%	38%	41%	61%
60.0%		74%	74%	74%	42%	65%	23%	56%	61%	67%	52%	56%	75%	61%
55.0%		54%	58%	65%	62%	51%	50%	54%	65%	57%	46%	45%	62%	46%
69.2%		67%	67%	80%	68%	76%	87%	59%	67%	67%	59%	59%	59%	85%
64.2%		58%	67%	67%	75%	52%	63%	69%	69%	69%	69%	61%	58%	58%
72.7%		83%	83%	83%	60%	79%	83%	70%	62%	78%	57%	67%	63%	77%
53.9%		53%	60%	51%	53%	57%	57%	47%	58%	53%	53%	53%	53%	53%
70.9%		76%	87%	83%	64%	49%	76%	68%	82%	67%	67%	67%	61%	75%
61.8%		64%	64%	64%	62%	59%	62%	70%	55%	52%	57%	67%	62%	66%
57.8%		56%	56%	46%	78%	46%	60%	58%	60%	50%	70%	46%	63%	62%
64.3%		69%	69%	69%	84%	44%	61%	66%	66%	69%	61%	62%	58%	58%
81.5%		89%	92%	95%	85%	67%	68%	85%	78%	66%	85%	84%	81%	85%
53.0%		68%	58%	60%	60%	24%	40%	49%	68%	60%	54%	54%	47%	47%
53.5%		57%	42%	71%	57%	58%	57%	39%	57%	39%	70%	47%	47%	54%
79.4%		89%	74%	91%	90%	57%	84%	100%	89%	76%	78%	90%	24%	90%
78.5%		70%	84%	92%	76%	73%	67%	91%	100%	73%	73%	73%	76%	73%
58.0%		47%	60%	66%	67%	34%	53%	61%	70%	60%	41%	60%	75%	60%
62.7%		54%	58%	63%	78%	63%	63%	66%	63%	60%	45%	71%	69%	62%
86.6%		100%	100%	100%	76%	67%	75%	91%	92%	84%	100%	74%	75%	92%
61.8%		63%	64%	64%	63%	53%	60%	72%	64%	66%	33%	64%	66%	72%
73.4%		82%	85%	54%	76%	52%	76%	82%	82%	85%	36%	87%	76%	81%
79.8%		66%	79%	76%	85%	68%	71%	85%	77%	85%	85%	90%	85%	85%
68.6%		74%	78%	78%	64%	77%	74%	60%	64%	60%	60%	70%	73%	60%
82.4%		91%	61%	61%	91%	48%	91%	80%	91%	91%	91%	91%	92%	92%
71.2%		70%	74%	74%	70%	63%	70%	74%	70%	70%	85%	70%	70%	65%