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 AgeGroup%3A18 25 C5 - Run 140f727...

Global Dialogues GD4 - 18-25 (5 context Qs)

DTEF: Predict response distributions for 18-25. 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

Demographic Processes

Best Models (Coverage)

1.Gemini 2.5 Flash
82.0%
2.Claude Sonnet 4.5
81.8%
3.Claude Sonnet 4
81.7%
4.Claude Haiku 4.5
81.2%
5.GPT 4.1 Mini
80.8%

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 81.2%	3rd 81.7%	2nd 81.8%	1st 82.0%	11th 77.3%	9th 79.1%	7th 79.7%	6th 80.8%	5th 80.8%	12th 76.3%	8th 79.6%	10th 78.6%	13th 76.1%
65.7%		65%	70%	78%	84%	51%	60%	60%	73%	56%	64%	61%	75%	57%
62.0%		65%	59%	68%	78%	34%	54%	62%	83%	65%	57%	65%	58%	58%
84.4%		79%	90%	92%	85%	86%	90%	82%	79%	86%	81%	82%	79%	86%
82.8%		86%	86%	86%	84%	87%	83%	83%	85%	77%	78%	80%	80%	82%
70.1%		72%	76%	78%	74%	60%	74%	74%	66%	63%	68%	68%	64%	74%
81.7%		84%	80%	91%	88%	80%	78%	86%	97%	78%	82%	89%	81%	48%
69.4%		86%	79%	81%	79%	62%	81%	62%	63%	63%	51%	55%	58%	82%
79.4%		87%	66%	62%	78%	81%	81%	82%	78%	85%	90%	84%	74%	84%
82.9%		91%	81%	81%	82%	90%	87%	81%	92%	88%	74%	83%	75%	73%
79.9%		76%	79%	85%	87%	89%	70%	60%	68%	77%	89%	86%	89%	84%
83.7%		87%	89%	88%	88%	87%	78%	84%	88%	76%	88%	88%	80%	67%
86.4%		89%	83%	90%	93%	89%	83%	83%	88%	93%	74%	88%	88%	82%
83.3%		86%	82%	85%	72%	88%	74%	85%	85%	86%	83%	88%	87%	82%
61.9%		69%	72%	69%	57%	58%	67%	52%	59%	57%	54%	53%	69%	69%
72.5%		63%	77%	81%	63%	68%	73%	70%	74%	77%	77%	72%	71%	77%
75.5%		89%	76%	86%	92%	65%	73%	83%	79%	79%	59%	70%	67%	64%
86.3%		85%	82%	93%	87%	88%	88%	88%	83%	91%	80%	83%	85%	89%
80.5%		84%	83%	72%	84%	78%	82%	71%	70%	89%	77%	84%	86%	86%
82.5%		83%	86%	87%	87%	84%	80%	80%	86%	86%	72%	87%	76%	78%
76.8%		83%	76%	79%	76%	77%	80%	79%	83%	73%	72%	75%	74%	72%
80.8%		82%	84%	78%	86%	78%	83%	72%	72%	84%	81%	89%	77%	85%
88.3%		89%	94%	86%	83%	94%	74%	92%	89%	93%	89%	85%	93%	87%
73.8%		71%	77%	84%	88%	78%	77%	82%	86%	66%	56%	76%	80%	38%
55.1%		66%	58%	60%	55%	52%	56%	57%	58%	53%	53%	47%	40%	61%
85.2%		90%	88%	88%	83%	91%	87%	81%	91%	77%	89%	80%	79%	84%
83.5%		92%	80%	81%	89%	92%	77%	79%	84%	80%	85%	78%	86%	83%
88.5%		76%	87%	89%	90%	83%	94%	88%	85%	94%	85%	94%	95%	91%
78.5%		77%	74%	81%	87%	63%	76%	89%	78%	84%	83%	82%	77%	69%
76.7%		77%	87%	88%	76%	69%	81%	79%	77%	75%	80%	71%	65%	72%
83.9%		84%	97%	91%	90%	71%	84%	82%	93%	83%	80%	76%	81%	79%
82.8%		86%	84%	87%	91%	86%	84%	85%	88%	82%	74%	89%	85%	55%
81.8%		84%	63%	86%	85%	80%	84%	83%	84%	84%	85%	89%	90%	67%
78.5%		84%	80%	87%	91%	61%	75%	92%	86%	84%	75%	78%	64%	64%
63.5%		65%	66%	65%	85%	58%	57%	75%	62%	66%	60%	59%	55%	53%
80.2%		82%	82%	68%	79%	80%	80%	85%	79%	77%	83%	81%	88%	78%
81.2%		85%	85%	85%	89%	86%	83%	81%	86%	77%	66%	88%	86%	59%
84.1%		85%	80%	77%	87%	81%	82%	85%	84%	86%	82%	88%	89%	87%
76.7%		82%	72%	67%	64%	84%	84%	82%	67%	75%	90%	84%	82%	64%
79.9%		81%	83%	80%	87%	83%	81%	87%	78%	82%	63%	84%	89%	61%
81.5%		94%	93%	87%	91%	85%	83%	10%	87%	91%	68%	90%	92%	89%
83.1%		86%	90%	91%	84%	72%	84%	89%	89%	86%	70%	77%	73%	89%
87.3%		95%	95%	95%	76%	95%	94%	93%	76%	94%	80%	80%	82%	80%
68.7%		68%	66%	72%	59%	64%	64%	76%	80%	73%	73%	63%	63%	72%
71.8%		74%	72%	73%	66%	69%	86%	82%	69%	65%	82%	67%	64%	64%
86.5%		91%	92%	91%	83%	89%	85%	77%	92%	86%	91%	73%	88%	86%
84.3%		85%	89%	89%	84%	77%	74%	86%	81%	92%	70%	85%	90%	94%
77.3%		80%	73%	74%	83%	81%	79%	81%	75%	75%	82%	74%	74%	74%
85.9%		90%	98%	98%	80%	73%	83%	73%	99%	80%	82%	98%	90%	73%
87.7%		95%	93%	85%	85%	94%	75%	95%	80%	85%	90%	87%	89%	87%
85.8%		87%	90%	87%	78%	81%	93%	94%	86%	92%	76%	89%	81%	82%
85.9%		92%	92%	87%	89%	82%	95%	91%	77%	85%	87%	87%	76%	77%
75.8%		78%	79%	75%	83%	65%	74%	80%	86%	73%	70%	78%	72%	72%
75.3%		84%	79%	84%	88%	68%	60%	78%	75%	78%	61%	77%	82%	65%
57.7%		67%	61%	58%	55%	57%	60%	64%	47%	60%	61%	59%	60%	41%
85.8%		76%	92%	90%	74%	85%	89%	88%	86%	89%	84%	89%	94%	80%
87.6%		93%	89%	90%	83%	77%	92%	89%	92%	95%	88%	79%	79%	93%
56.8%		45%	67%	63%	72%	47%	63%	58%	60%	61%	45%	61%	48%	48%
88.6%		91%	88%	92%	93%	90%	80%	83%	84%	89%	86%	91%	94%	91%
64.4%		62%	65%	70%	85%	54%	63%	70%	66%	70%	56%	58%	54%	64%
76.2%		79%	82%	83%	72%	86%	78%	70%	65%	69%	78%	67%	82%	79%
84.4%		83%	88%	93%	85%	79%	90%	83%	87%	96%	81%	83%	82%	67%
71.8%		74%	80%	81%	79%	52%	67%	69%	81%	62%	72%	66%	79%	71%
85.0%		86%	90%	87%	80%	96%	88%	90%	94%	84%	74%	73%	86%	77%
85.2%		88%	85%	88%	92%	89%	80%	83%	88%	82%	82%	92%	86%	73%
75.1%		76%	81%	85%	83%	71%	78%	79%	86%	74%	60%	80%	83%	40%
81.3%		82%	83%	79%	97%	75%	77%	93%	78%	85%	72%	80%	72%	84%
76.2%		83%	74%	79%	95%	62%	74%	86%	78%	80%	87%	64%	61%	68%
82.5%		92%	77%	81%	88%	87%	81%	86%	81%	83%	68%	78%	82%	89%
79.4%		77%	83%	85%	82%	82%	64%	84%	78%	81%	80%	85%	78%	73%
81.8%		79%	77%	79%	84%	83%	82%	71%	84%	87%	84%	84%	85%	84%
79.2%		75%	89%	73%	69%	84%	77%	62%	79%	77%	87%	78%	87%	93%
82.4%		88%	89%	81%	73%	83%	85%	76%	87%	88%	80%	87%	80%	74%
88.8%		89%	94%	87%	81%	92%	91%	85%	81%	92%	94%	95%	90%	83%
77.6%		76%	86%	85%	82%	67%	81%	87%	82%	73%	72%	75%	66%	77%
79.7%		78%	80%	80%	84%	83%	82%	68%	85%	82%	83%	77%	81%	73%
82.5%		76%	93%	84%	68%	92%	90%	78%	65%	86%	81%	88%	83%	89%
83.2%		84%	90%	88%	80%	93%	80%	78%	75%	78%	78%	87%	84%	86%
86.4%		91%	84%	92%	91%	79%	83%	81%	88%	86%	90%	87%	80%	91%
82.8%		86%	78%	83%	79%	85%	76%	84%	85%	87%	82%	86%	85%	81%
85.2%		83%	89%	85%	83%	86%	86%	82%	85%	85%	82%	83%	93%	85%
89.5%		88%	88%	88%	87%	99%	87%	89%	91%	90%	95%	90%	84%	88%
89.8%		93%	85%	88%	93%	95%	94%	96%	93%	98%	77%	94%	84%	77%
83.9%		88%	94%	94%	71%	75%	89%	85%	91%	86%	84%	78%	79%	77%
86.6%		87%	90%	90%	90%	89%	76%	90%	89%	89%	82%	83%	85%	86%
83.2%		76%	88%	78%	87%	82%	87%	85%	82%	85%	87%	87%	86%	72%
82.2%		82%	81%	82%	84%	86%	80%	80%	87%	79%	85%	89%	83%	71%
69.8%		68%	68%	67%	71%	72%	70%	65%	60%	69%	63%	76%	79%	79%
76.6%		78%	77%	77%	82%	74%	72%	73%	71%	82%	70%	79%	80%	81%
72.5%		72%	86%	86%	88%	62%	66%	69%	68%	72%	55%	57%	71%	90%
83.8%		88%	88%	87%	90%	80%	69%	75%	84%	76%	90%	83%	92%	87%
75.7%		69%	68%	79%	91%	66%	78%	79%	82%	81%	75%	78%	65%	73%
60.9%		55%	92%	92%	71%	49%	53%	62%	52%	70%	45%	47%	62%	42%
73.8%		80%	78%	78%	44%	78%	60%	83%	79%	65%	61%	88%	86%	80%
85.2%		86%	82%	84%	88%	78%	91%	91%	81%	91%	89%	90%	78%	79%
65.5%		66%	69%	67%	65%	74%	67%	60%	57%	58%	66%	55%	72%	75%
83.9%		87%	83%	87%	89%	83%	82%	79%	87%	86%	80%	80%	92%	76%
91.6%		89%	92%	87%	94%	94%	88%	90%	89%	91%	96%	91%	94%	96%
86.4%		80%	90%	91%	72%	79%	94%	90%	80%	80%	93%	90%	88%	96%
77.8%		87%	78%	87%	96%	53%	76%	84%	90%	81%	65%	75%	63%	76%
80.4%		85%	83%	75%	85%	77%	77%	80%	85%	90%	62%	72%	90%	84%
79.2%		78%	82%	79%	83%	85%	79%	82%	89%	73%	77%	77%	65%	80%
86.2%		83%	84%	85%	87%	75%	88%	86%	80%	93%	96%	84%	86%	94%
91.8%		95%	97%	97%	90%	91%	86%	90%	94%	86%	95%	88%	92%	92%
83.2%		86%	89%	85%	86%	70%	74%	85%	92%	91%	80%	90%	76%	77%
83.7%		86%	81%	82%	89%	84%	88%	91%	83%	88%	71%	91%	76%	78%
83.2%		66%	72%	88%	86%	72%	91%	90%	92%	89%	90%	79%	76%	91%
76.2%		92%	65%	26%	91%	63%	76%	95%	95%	88%	63%	79%	81%	76%
60.4%		61%	60%	65%	61%	29%	63%	73%	77%	70%	57%	59%	53%	57%
68.7%		61%	63%	60%	86%	79%	81%	64%	67%	77%	50%	83%	61%	61%
84.6%		92%	79%	92%	87%	83%	87%	87%	90%	90%	91%	77%	73%	72%
88.1%		89%	88%	84%	86%	84%	86%	86%	88%	89%	87%	90%	94%	94%
80.5%		92%	87%	84%	83%	74%	81%	78%	90%	81%	75%	91%	64%	66%
85.2%		81%	89%	86%	87%	87%	87%	92%	87%	86%	82%	85%	81%	78%
87.6%		90%	87%	91%	94%	94%	85%	85%	88%	93%	84%	90%	86%	72%
87.8%		89%	87%	87%	82%	89%	91%	94%	91%	97%	65%	93%	88%	89%
75.1%		73%	79%	62%	79%	81%	71%	66%	63%	81%	74%	81%	84%	82%