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%3Akenya Ctx - Run 9a45dd5...

Global Dialogues GD4 - Kenya (with context)

DTEF: Predict response distributions for Kenya. 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

AI Companionship

Best Models (Coverage)

1.Claude Sonnet 4.5
83.6%
2.Claude Sonnet 4
82.8%
3.GPT 4.1
82.4%
4.Gemini 2.5 Flash
82.1%
5.Claude Haiku 4.5
81.5%

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 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 81.5%	2nd 82.8%	1st 83.6%	4th 82.1%	13th 74.4%	8th 80.1%	6th 81.4%	3rd 82.4%	7th 80.5%	12th 74.6%	10th 77.8%	11th 76.7%	9th 79.6%
74.1%		68%	78%	78%	80%	56%	69%	76%	77%	71%	75%	78%	80%	77%
77.3%		94%	83%	84%	92%	65%	76%	88%	89%	68%	61%	61%	67%	77%
73.5%		67%	75%	80%	81%	70%	77%	73%	84%	80%	62%	81%	63%	62%
86.5%		90%	83%	90%	91%	82%	93%	87%	88%	93%	85%	72%	85%	85%
77.2%		80%	84%	82%	89%	73%	85%	76%	81%	64%	63%	71%	72%	83%
83.8%		78%	89%	89%	85%	79%	83%	85%	87%	84%	76%	84%	86%	85%
65.2%		80%	83%	86%	79%	52%	60%	66%	56%	52%	52%	52%	52%	78%
72.5%		79%	67%	79%	74%	58%	75%	69%	78%	71%	83%	70%	65%	75%
82.2%		84%	83%	83%	77%	77%	86%	84%	86%	89%	82%	79%	80%	78%
65.5%		62%	73%	60%	49%	68%	60%	82%	59%	61%	70%	70%	62%	75%
84.2%		82%	95%	91%	90%	81%	86%	82%	93%	81%	78%	78%	78%	80%
88.7%		68%	87%	89%	96%	87%	93%	82%	91%	96%	95%	89%	88%	92%
85.0%		85%	85%	85%	85%	85%	85%	85%	85%	85%	85%	85%	85%	85%
71.4%		88%	86%	84%	87%	61%	47%	76%	75%	71%	66%	53%	67%	67%
76.4%		67%	84%	87%	73%	76%	74%	89%	76%	70%	74%	64%	89%	70%
85.5%		95%	91%	89%	85%	83%	92%	83%	93%	91%	57%	94%	65%	94%
63.6%		68%	69%	74%	81%	45%	65%	63%	66%	56%	62%	60%	65%	53%
85.2%		77%	83%	87%	90%	87%	84%	94%	87%	86%	75%	79%	88%	90%
85.1%		89%	89%	84%	81%	85%	89%	87%	83%	86%	81%	81%	86%	85%
64.4%		67%	63%	66%	64%	51%	71%	61%	65%	63%	77%	68%	60%	61%
89.2%		91%	90%	96%	90%	93%	84%	90%	93%	92%	72%	88%	90%	90%
91.3%		94%	87%	92%	95%	94%	90%	91%	91%	94%	94%	94%	77%	94%
89.8%		85%	94%	95%	93%	83%	89%	92%	91%	88%	86%	89%	89%	93%
75.7%		91%	71%	76%	81%	68%	76%	74%	81%	85%	70%	70%	58%	83%
75.2%		67%	81%	80%	65%	63%	76%	79%	76%	84%	73%	76%	73%	84%
83.2%		92%	82%	89%	84%	84%	57%	84%	89%	84%	84%	84%	84%	84%
82.4%		77%	85%	85%	88%	82%	85%	76%	83%	82%	79%	84%	82%	83%
75.5%		72%	78%	85%	82%	65%	70%	76%	84%	76%	73%	77%	69%	75%
78.8%		83%	86%	86%	71%	73%	84%	75%	80%	81%	77%	76%	72%	80%
85.1%		75%	87%	87%	90%	73%	83%	87%	88%	84%	86%	89%	89%	88%
88.3%		91%	87%	83%	88%	89%	84%	88%	87%	92%	91%	90%	91%	87%
84.6%		89%	90%	84%	95%	86%	81%	93%	76%	85%	75%	82%	85%	79%
72.8%		85%	79%	81%	84%	60%	70%	83%	78%	71%	82%	64%	51%	59%
72.7%		75%	75%	88%	83%	60%	76%	76%	79%	81%	53%	81%	49%	69%
83.7%		85%	86%	89%	67%	80%	89%	85%	89%	91%	53%	92%	88%	94%
93.4%		95%	94%	94%	95%	87%	94%	94%	90%	98%	89%	95%	96%	93%
82.6%		88%	77%	76%	93%	68%	93%	77%	90%	93%	90%	85%	73%	71%
80.6%		86%	70%	85%	83%	81%	81%	69%	85%	84%	81%	81%	81%	81%
84.8%		87%	86%	92%	86%	76%	89%	85%	88%	89%	72%	84%	84%	84%
80.8%		81%	82%	78%	81%	81%	81%	81%	81%	81%	81%	81%	81%	81%
83.5%		91%	88%	80%	86%	79%	90%	88%	85%	86%	62%	92%	69%	90%
84.2%		93%	79%	93%	82%	88%	91%	91%	69%	79%	77%	75%	90%	88%
82.8%		91%	86%	90%	89%	69%	82%	87%	87%	79%	88%	69%	82%	78%
79.1%		77%	69%	76%	76%	92%	88%	84%	86%	69%	72%	83%	86%	70%
77.7%		84%	88%	88%	73%	84%	87%	68%	88%	63%	61%	74%	69%	83%
79.8%		85%	87%	88%	79%	56%	81%	82%	87%	82%	81%	78%	71%	81%
75.1%		85%	75%	57%	78%	78%	69%	79%	73%	79%	72%	80%	75%	76%
74.0%		98%	94%	88%	89%	10%	76%	68%	74%	67%	60%	66%	84%	88%
91.1%		88%	92%	96%	94%	88%	89%	95%	92%	88%	88%	94%	86%	94%
82.6%		82%	79%	89%	80%	85%	87%	80%	85%	81%	81%	81%	80%	84%
86.3%		85%	87%	87%	85%	86%	89%	89%	84%	86%	86%	86%	86%	86%
80.9%		71%	82%	86%	92%	77%	80%	82%	76%	85%	90%	79%	73%	79%
75.1%		73%	78%	85%	98%	49%	74%	74%	73%	72%	68%	79%	85%	68%
76.3%		90%	71%	79%	81%	71%	78%	76%	89%	76%	79%	73%	68%	61%
92.0%		92%	92%	92%	92%	92%	92%	92%	92%	92%	92%	92%	92%	92%
82.5%		78%	91%	91%	60%	77%	82%	91%	87%	82%	82%	84%	82%	85%
68.8%		70%	68%	66%	79%	65%	84%	73%	74%	64%	36%	71%	68%	76%
85.0%		85%	85%	85%	85%	85%	85%	85%	85%	85%	85%	85%	85%	85%
78.8%		84%	82%	87%	89%	69%	90%	89%	82%	81%	36%	81%	69%	86%
80.7%		81%	81%	81%	73%	80%	80%	84%	79%	84%	82%	83%	75%	86%
77.5%		81%	85%	85%	55%	79%	70%	78%	79%	78%	76%	85%	86%	71%
75.9%		63%	87%	86%	75%	68%	79%	84%	80%	78%	67%	73%	80%	67%
79.2%		85%	90%	89%	74%	85%	91%	77%	84%	71%	71%	71%	71%	71%
82.3%		85%	86%	88%	85%	83%	79%	81%	85%	81%	77%	77%	76%	87%
92.5%		84%	94%	92%	92%	90%	91%	97%	94%	91%	95%	95%	93%	95%
64.7%		58%	70%	67%	86%	52%	71%	78%	74%	73%	44%	52%	49%	67%
70.2%		71%	79%	76%	88%	59%	69%	86%	83%	64%	56%	55%	59%	68%
80.8%		85%	88%	74%	74%	81%	77%	75%	81%	86%	78%	85%	78%	88%
74.1%		75%	75%	70%	73%	78%	70%	73%	76%	79%	75%	76%	69%	74%
68.9%		86%	64%	77%	50%	63%	64%	64%	58%	87%	85%	72%	63%	63%
71.3%		70%	79%	74%	70%	72%	72%	70%	70%	70%	70%	70%	70%	70%
82.7%		86%	94%	90%	66%	89%	87%	68%	84%	76%	78%	84%	88%	85%
83.8%		76%	79%	93%	93%	70%	88%	94%	87%	78%	65%	88%	96%	83%
64.5%		62%	69%	64%	69%	83%	69%	63%	64%	52%	61%	70%	53%	59%
84.5%		88%	84%	81%	84%	90%	86%	94%	88%	80%	79%	78%	78%	89%
86.4%		87%	89%	94%	83%	80%	88%	86%	87%	81%	74%	97%	89%	88%
90.2%		87%	93%	86%	88%	96%	87%	85%	95%	91%	81%	94%	93%	96%
85.6%		82%	91%	88%	84%	72%	86%	89%	85%	91%	81%	82%	94%	88%
85.2%		82%	88%	88%	94%	76%	84%	90%	90%	81%	94%	79%	79%	83%
91.8%		92%	92%	92%	92%	90%	92%	92%	92%	92%	92%	92%	92%	92%
73.8%		71%	78%	83%	71%	71%	81%	74%	75%	71%	71%	71%	71%	71%
91.2%		90%	90%	93%	88%	94%	96%	83%	95%	96%	83%	88%	93%	96%
78.9%		83%	90%	84%	83%	64%	80%	89%	90%	87%	73%	73%	62%	68%
87.2%		87%	89%	90%	85%	90%	94%	87%	78%	83%	88%	87%	88%	88%
82.0%		86%	81%	72%	80%	84%	79%	83%	87%	86%	78%	81%	81%	88%
84.7%		82%	89%	93%	93%	76%	84%	92%	93%	80%	78%	78%	79%	84%
72.8%		72%	86%	73%	82%	89%	75%	83%	76%	73%	58%	58%	64%	58%
74.8%		88%	70%	69%	69%	67%	79%	72%	72%	88%	74%	68%	75%	81%
72.1%		81%	78%	83%	85%	62%	76%	76%	74%	76%	60%	60%	60%	66%
75.7%		77%	83%	91%	90%	44%	48%	91%	90%	83%	86%	69%	58%	74%
69.5%		73%	76%	75%	86%	62%	67%	71%	70%	78%	37%	68%	69%	71%
65.4%		76%	84%	76%	84%	59%	46%	64%	70%	76%	76%	48%	48%	43%
68.7%		86%	84%	83%	70%	58%	69%	72%	66%	61%	47%	37%	87%	73%
83.8%		80%	88%	87%	84%	80%	79%	80%	92%	88%	88%	73%	89%	81%
63.5%		61%	68%	70%	61%	69%	68%	57%	58%	62%	70%	61%	59%	61%
82.3%		73%	85%	82%	75%	70%	88%	87%	94%	92%	92%	86%	73%	73%
83.4%		93%	89%	88%	70%	88%	91%	91%	86%	85%	56%	73%	80%	94%
88.4%		88%	91%	96%	81%	84%	87%	92%	94%	81%	73%	92%	95%	95%
82.8%		91%	84%	82%	77%	70%	89%	85%	88%	85%	70%	89%	79%	88%
84.8%		83%	91%	90%	92%	82%	81%	87%	86%	93%	74%	72%	79%	93%
81.4%		75%	87%	88%	89%	75%	80%	84%	89%	90%	51%	83%	91%	76%
78.5%		75%	86%	87%	72%	67%	78%	74%	78%	76%	91%	93%	72%	72%
84.9%		88%	91%	87%	92%	72%	80%	79%	83%	76%	87%	92%	92%	85%
73.7%		92%	84%	83%	87%	48%	59%	70%	85%	76%	79%	71%	60%	64%
76.5%		77%	74%	80%	84%	74%	79%	73%	83%	77%	79%	71%	71%	72%
83.6%		90%	82%	85%	87%	78%	84%	86%	86%	85%	85%	83%	71%	85%
81.4%		85%	75%	79%	91%	83%	75%	92%	87%	91%	76%	74%	74%	76%
74.2%		76%	71%	77%	87%	59%	73%	79%	86%	73%	89%	57%	68%	69%
73.3%		62%	67%	67%	83%	70%	84%	81%	75%	85%	52%	88%	61%	78%
82.8%		85%	84%	87%	92%	61%	83%	90%	88%	85%	88%	77%	82%	74%
78.3%		78%	80%	79%	81%	75%	76%	81%	75%	81%	67%	84%	80%	81%
82.6%		89%	87%	87%	88%	69%	92%	80%	93%	91%	57%	94%	67%	80%
85.2%		89%	85%	87%	87%	82%	87%	83%	86%	87%	83%	83%	84%	84%
90.6%		93%	91%	91%	88%	91%	90%	95%	87%	92%	89%	90%	91%	90%
84.5%		88%	87%	88%	87%	66%	87%	85%	87%	88%	83%	74%	92%	87%
74.9%		70%	75%	79%	70%	93%	73%	68%	70%	70%	69%	70%	78%	89%