DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd6 Ctx Dtef Global Dialogues Gd6 Country%3Akenya Ctx - Run 7952f7c...

Global Dialogues GD6 - Kenya (with context)

DTEF: Predict response distributions for Kenya. Source: Global Dialogues GD6 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd6

AI Safety & Robustness

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Best Models (Coverage)

1.Claude Sonnet 4
82.9%
2.Claude Sonnet 4.5
82.4%
3.GPT 4.1
82.3%
4.Claude Haiku 4.5
81.9%
5.Mistral Medium 3
80.6%

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 81.9%	1st 82.9%	2nd 82.4%	9th 79.5%	13th 72.9%	6th 80.5%	5th 80.6%	3rd 82.3%	7th 80.1%	12th 74.5%	11th 79.1%	8th 79.6%	10th 79.2%
62.2%		70%	60%	56%	68%	44%	64%	69%	70%	62%	54%	64%	64%	64%
82.6%		85%	82%	93%	82%	78%	78%	85%	86%	82%	82%	83%	77%	81%
84.9%		89%	85%	87%	91%	81%	80%	86%	86%	86%	86%	81%	85%	81%
84.8%		84%	88%	80%	76%	72%	91%	97%	84%	89%	83%	82%	89%	88%
74.0%		87%	84%	76%	85%	58%	73%	69%	75%	79%	71%	63%	66%	76%
86.5%		89%	79%	82%	95%	87%	89%	86%	87%	90%	91%	83%	77%	90%
77.7%		86%	83%	78%	82%	76%	75%	69%	77%	77%	80%	70%	77%	80%
77.5%		86%	74%	71%	93%	49%	87%	74%	76%	90%	65%	88%	73%	82%
95.2%		96%	93%	96%	96%	93%	96%	96%	97%	99%	82%	99%	100%	95%
79.0%		78%	79%	77%	68%	77%	69%	86%	81%	80%	89%	89%	83%	71%
65.9%		81%	70%	76%	78%	39%	53%	59%	82%	66%	70%	71%	48%	64%
75.0%		80%	69%	61%	92%	76%	75%	83%	76%	75%	81%	64%	81%	62%
86.5%		89%	88%	92%	89%	67%	92%	88%	89%	88%	89%	81%	87%	86%
82.8%		83%	82%	81%	84%	82%	81%	85%	87%	87%	76%	83%	83%	83%
72.2%		86%	74%	70%	95%	57%	79%	67%	85%	60%	73%	43%	67%	83%
78.5%		88%	88%	88%	81%	10%	79%	78%	87%	88%	79%	88%	78%	88%
78.2%		72%	88%	77%	73%	82%	83%	76%	83%	84%	81%	72%	83%	62%
64.2%		75%	81%	77%	50%	71%	50%	57%	61%	66%	53%	54%	76%	64%
74.4%		74%	72%	81%	80%	67%	77%	86%	82%	82%	64%	70%	61%	71%
69.7%		96%	87%	82%	78%	61%	68%	67%	62%	59%	56%	56%	56%	78%
86.2%		89%	88%	86%	80%	73%	84%	91%	91%	91%	87%	86%	86%	88%
88.0%		88%	88%	88%	88%	88%	88%	88%	88%	88%	88%	88%	88%	88%
65.8%		75%	72%	72%	73%	66%	61%	71%	78%	65%	46%	51%	62%	64%
84.8%		90%	94%	91%	77%	79%	84%	83%	81%	91%	82%	92%	78%	80%
78.4%		67%	99%	97%	64%	59%	95%	91%	92%	74%	66%	82%	69%	64%
79.5%		85%	84%	81%	64%	79%	80%	81%	69%	69%	68%	88%	94%	91%
83.1%		84%	84%	85%	80%	87%	87%	86%	85%	80%	79%	80%	83%	80%
71.7%		76%	74%	79%	87%	68%	67%	71%	73%	66%	66%	66%	69%	70%
82.7%		84%	81%	75%	79%	90%	93%	83%	84%	84%	86%	82%	78%	76%
80.5%		85%	82%	82%	78%	80%	84%	85%	82%	80%	78%	91%	78%	62%
78.5%		78%	80%	79%	76%	77%	81%	79%	81%	76%	76%	84%	76%	77%
71.3%		69%	84%	81%	78%	54%	74%	80%	83%	78%	65%	60%	58%	63%
72.7%		85%	89%	87%	78%	55%	79%	71%	86%	75%	59%	66%	57%	58%
87.2%		86%	84%	85%	89%	86%	89%	87%	86%	91%	88%	88%	88%	87%
86.7%		87%	91%	90%	85%	81%	87%	83%	89%	88%	82%	86%	89%	89%
75.5%		79%	76%	77%	76%	73%	74%	78%	77%	76%	71%	75%	75%	75%
74.3%		81%	81%	73%	47%	85%	78%	73%	78%	86%	48%	73%	74%	89%
91.0%		92%	95%	95%	94%	93%	90%	96%	93%	76%	95%	94%	76%	94%
89.0%		94%	88%	90%	94%	63%	95%	95%	95%	89%	75%	89%	96%	94%
65.1%		50%	75%	82%	74%	44%	62%	69%	70%	65%	45%	72%	69%	69%
66.5%		70%	71%	71%	70%	62%	65%	72%	70%	62%	63%	67%	61%	60%
71.1%		87%	81%	81%	63%	70%	48%	76%	79%	71%	40%	75%	76%	77%
77.7%		68%	73%	76%	85%	86%	87%	83%	76%	85%	56%	86%	77%	72%
88.2%		93%	91%	91%	91%	79%	93%	92%	93%	86%	65%	93%	90%	90%
90.1%		90%	93%	91%	94%	93%	94%	87%	94%	87%	87%	94%	90%	77%
83.2%		86%	80%	93%	93%	62%	79%	86%	86%	91%	91%	86%	78%	71%
92.9%		95%	93%	93%	94%	87%	95%	92%	93%	94%	94%	87%	94%	97%
88.5%		89%	89%	87%	91%	87%	90%	88%	87%	91%	88%	89%	92%	83%
85.8%		90%	88%	81%	88%	84%	88%	85%	83%	84%	83%	87%	88%	86%
87.0%		87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%	87%
64.6%		68%	58%	64%	68%	48%	67%	66%	68%	70%	61%	70%	62%	70%
81.5%		86%	90%	88%	76%	78%	87%	83%	84%	80%	68%	78%	75%	86%
71.9%		82%	68%	67%	57%	68%	74%	70%	65%	81%	74%	60%	88%	81%
79.5%		84%	92%	81%	57%	80%	88%	87%	95%	79%	81%	80%	70%	59%
77.3%		73%	77%	79%	76%	79%	77%	67%	81%	75%	80%	80%	81%	80%
84.2%		82%	88%	79%	65%	68%	92%	84%	88%	82%	86%	96%	96%	89%
83.6%		86%	90%	88%	89%	51%	82%	83%	85%	84%	86%	89%	87%	87%
71.0%		78%	70%	82%	82%	61%	79%	77%	87%	66%	44%	63%	63%	71%
85.1%		88%	87%	88%	83%	85%	80%	84%	88%	86%	81%	90%	83%	83%
91.0%		91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%	91%
80.4%		72%	95%	93%	84%	59%	88%	88%	90%	71%	68%	76%	93%	68%
84.5%		84%	89%	85%	82%	73%	85%	81%	83%	87%	86%	85%	88%	90%
71.2%		65%	74%	82%	50%	70%	74%	72%	51%	85%	77%	65%	79%	81%
83.6%		81%	84%	83%	84%	88%	81%	86%	86%	80%	84%	80%	88%	82%
89.5%		86%	93%	93%	91%	95%	91%	90%	92%	77%	83%	90%	92%	91%
77.6%		71%	91%	96%	73%	70%	72%	89%	78%	72%	61%	59%	94%	83%
78.5%		66%	76%	70%	93%	80%	73%	87%	82%	79%	73%	85%	80%	76%
82.5%		83%	82%	85%	74%	82%	81%	84%	85%	83%	82%	79%	88%	84%
86.8%		85%	85%	87%	91%	84%	96%	97%	79%	93%	76%	84%	86%	85%
62.2%		69%	65%	52%	41%	68%	68%	56%	57%	47%	70%	69%	75%	72%
83.2%		68%	82%	88%	87%	85%	81%	79%	86%	82%	87%	92%	79%	86%
82.2%		84%	88%	87%	83%	81%	82%	80%	82%	58%	83%	88%	90%	83%
66.2%		71%	71%	69%	30%	62%	77%	71%	78%	71%	40%	73%	75%	73%
81.5%		81%	89%	95%	83%	75%	73%	71%	83%	81%	81%	80%	91%	76%
74.4%		83%	74%	76%	76%	75%	69%	59%	75%	76%	76%	76%	76%	76%
73.5%		75%	74%	78%	68%	71%	70%	75%	67%	74%	77%	79%	74%	73%
89.3%		91%	91%	91%	91%	69%	91%	91%	91%	91%	91%	91%	91%	91%
80.8%		78%	83%	79%	88%	68%	86%	85%	89%	88%	66%	85%	80%	75%
79.8%		87%	83%	86%	86%	72%	82%	75%	84%	79%	79%	79%	73%	72%
80.5%		89%	89%	89%	85%	61%	83%	77%	83%	85%	77%	63%	83%	83%
81.9%		83%	79%	89%	89%	72%	93%	93%	93%	89%	18%	89%	89%	89%
68.3%		73%	77%	77%	78%	54%	65%	69%	76%	60%	69%	64%	59%	67%
87.0%		88%	88%	88%	88%	75%	88%	88%	88%	88%	88%	88%	88%	88%
81.8%		75%	85%	86%	81%	89%	83%	79%	85%	80%	78%	82%	78%	83%
77.8%		87%	88%	90%	56%	58%	68%	69%	81%	89%	79%	84%	88%	75%
86.8%		87%	87%	87%	87%	86%	87%	87%	87%	87%	86%	87%	86%	87%
79.4%		85%	86%	84%	75%	67%	90%	90%	77%	91%	54%	81%	78%	74%
87.3%		83%	92%	90%	89%	85%	89%	79%	88%	93%	79%	82%	94%	92%
87.5%		85%	93%	91%	86%	93%	84%	90%	91%	85%	85%	85%	85%	85%
86.6%		85%	87%	93%	85%	85%	87%	86%	93%	85%	85%	85%	85%	85%
71.2%		83%	73%	46%	85%	71%	75%	64%	75%	71%	76%	64%	60%	82%