DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 Dtef Global Dialogues Gd4 AgeGroup%3A18 25 - Run b3baccd...

Global Dialogues GD4 - 18-25

DTEF: Predict response distributions for 18-25. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Social interaction

AI Safety & Robustness

Economics & Finance

Human AI Relationships

Best Models (Coverage)

1.Claude Sonnet 4
82.1%
2.Claude Sonnet 4.5
82.1%
3.Claude Haiku 4.5
81.8%
4.Gemini 2.5 Flash
81.3%
5.GPT 4.1 Mini
81.2%

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 81.8%	2nd 82.1%	1st 82.1%	4th 81.3%	13th 77.3%	6th 80.6%	10th 79.9%	7th 80.5%	5th 81.2%	11th 78.5%	9th 80.0%	12th 78.4%	8th 80.1%
70.1%		71%	72%	78%	83%	52%	71%	65%	82%	70%	68%	65%	67%	67%
65.3%		64%	59%	67%	66%	52%	57%	65%	82%	71%	68%	67%	63%	68%
83.1%		83%	84%	85%	82%	86%	85%	86%	82%	86%	79%	79%	79%	84%
83.8%		86%	84%	89%	85%	83%	83%	86%	85%	85%	80%	82%	80%	82%
72.7%		77%	80%	83%	74%	62%	78%	71%	72%	65%	69%	69%	71%	74%
87.2%		87%	97%	94%	92%	80%	84%	89%	98%	86%	87%	93%	82%	65%
65.5%		79%	65%	80%	85%	64%	65%	47%	53%	60%	47%	61%	65%	81%
83.6%		77%	82%	84%	78%	86%	86%	89%	83%	83%	88%	86%	76%	89%
83.8%		87%	84%	84%	76%	91%	87%	75%	91%	86%	87%	83%	73%	86%
74.2%		79%	53%	52%	64%	82%	74%	62%	74%	86%	83%	86%	80%	90%
87.7%		89%	90%	91%	86%	83%	84%	88%	89%	88%	90%	88%	82%	92%
87.0%		93%	90%	93%	93%	89%	92%	87%	90%	82%	75%	87%	80%	80%
86.2%		89%	84%	91%	88%	87%	78%	86%	86%	89%	83%	86%	85%	89%
62.1%		68%	68%	61%	71%	53%	65%	52%	57%	58%	66%	52%	67%	69%
79.5%		70%	80%	79%	78%	77%	81%	83%	81%	81%	83%	82%	81%	77%
80.0%		88%	76%	87%	91%	77%	82%	74%	83%	81%	81%	75%	72%	73%
80.5%		88%	79%	81%	84%	68%	82%	86%	85%	77%	80%	83%	76%	77%
83.4%		89%	89%	79%	84%	78%	92%	80%	73%	87%	76%	90%	85%	82%
81.2%		83%	89%	90%	84%	73%	80%	82%	88%	82%	71%	82%	74%	77%
77.8%		84%	77%	76%	76%	76%	79%	75%	80%	78%	81%	81%	74%	74%
83.6%		92%	83%	78%	78%	81%	94%	80%	73%	86%	77%	94%	85%	86%
87.5%		87%	93%	80%	92%	95%	78%	90%	78%	88%	89%	85%	86%	97%
83.8%		81%	87%	91%	89%	78%	83%	88%	90%	79%	85%	90%	77%	71%
52.2%		64%	59%	57%	46%	45%	56%	61%	56%	57%	45%	45%	37%	51%
85.3%		90%	88%	86%	87%	85%	90%	81%	88%	84%	89%	77%	80%	84%
66.1%		67%	53%	67%	76%	73%	62%	48%	57%	69%	54%	67%	82%	84%
88.5%		88%	88%	90%	90%	88%	94%	87%	83%	93%	85%	87%	85%	92%
76.8%		77%	75%	77%	92%	62%	75%	82%	87%	76%	81%	82%	65%	67%
70.2%		75%	72%	87%	76%	53%	80%	75%	76%	69%	69%	64%	62%	55%
82.4%		83%	88%	97%	82%	67%	82%	80%	91%	82%	84%	79%	71%	85%
87.4%		88%	93%	90%	83%	86%	86%	90%	92%	85%	88%	89%	87%	79%
85.7%		84%	83%	88%	87%	80%	87%	86%	82%	87%	83%	88%	90%	89%
71.5%		73%	65%	84%	76%	65%	73%	84%	88%	72%	65%	61%	58%	65%
62.7%		72%	63%	71%	64%	57%	59%	60%	63%	68%	62%	66%	57%	53%
83.3%		82%	83%	80%	83%	82%	87%	84%	79%	83%	84%	85%	87%	84%
84.7%		81%	85%	87%	81%	86%	84%	88%	86%	85%	85%	86%	85%	82%
77.3%		77%	86%	62%	64%	83%	75%	74%	67%	67%	92%	87%	88%	83%
77.3%		82%	75%	67%	67%	84%	88%	75%	70%	73%	84%	87%	86%	67%
85.2%		85%	84%	83%	86%	83%	82%	87%	80%	88%	84%	84%	94%	88%
88.9%		87%	86%	91%	90%	90%	80%	91%	92%	91%	91%	90%	91%	86%
87.7%		92%	79%	89%	89%	82%	87%	94%	92%	91%	78%	98%	77%	92%
88.5%		83%	95%	95%	86%	96%	93%	90%	94%	96%	76%	75%	90%	82%
82.9%		82%	94%	91%	95%	70%	83%	91%	87%	92%	84%	68%	64%	77%
69.1%		66%	73%	63%	62%	69%	92%	83%	72%	67%	72%	72%	54%	53%
87.4%		90%	90%	92%	84%	91%	91%	86%	85%	84%	78%	85%	88%	92%
88.1%		89%	86%	89%	86%	92%	91%	89%	79%	88%	83%	87%	92%	94%
76.1%		83%	72%	69%	73%	73%	82%	80%	69%	81%	88%	74%	72%	73%
92.9%		90%	98%	98%	80%	98%	84%	84%	99%	98%	96%	96%	98%	89%
86.0%		80%	82%	82%	90%	88%	93%	87%	76%	89%	92%	84%	84%	91%
85.5%		89%	89%	86%	90%	77%	86%	92%	87%	85%	85%	83%	80%	82%
83.8%		88%	90%	90%	83%	73%	91%	91%	82%	87%	82%	87%	73%	73%
79.2%		79%	84%	88%	85%	75%	76%	83%	91%	79%	69%	78%	69%	74%
73.3%		78%	77%	77%	85%	64%	48%	63%	77%	81%	70%	77%	75%	81%
58.5%		53%	59%	63%	55%	63%	62%	63%	56%	53%	70%	54%	62%	47%
87.2%		89%	93%	89%	81%	87%	89%	90%	83%	89%	83%	89%	90%	81%
88.0%		92%	91%	87%	81%	93%	97%	86%	89%	90%	90%	84%	77%	87%
72.4%		65%	84%	73%	59%	51%	90%	78%	89%	76%	81%	66%	53%	76%
90.7%		91%	95%	94%	91%	91%	85%	86%	88%	91%	92%	91%	89%	95%
67.1%		69%	63%	81%	86%	55%	71%	61%	71%	69%	64%	63%	52%	67%
77.1%		79%	82%	81%	82%	84%	77%	70%	67%	69%	75%	78%	83%	75%
86.3%		86%	92%	94%	81%	80%	89%	83%	90%	95%	90%	83%	68%	91%
71.2%		71%	82%	83%	71%	56%	71%	74%	82%	67%	71%	64%	71%	63%
80.8%		88%	91%	87%	81%	71%	84%	81%	86%	82%	74%	74%	77%	74%
87.3%		88%	91%	91%	85%	91%	85%	83%	86%	82%	79%	91%	88%	95%
85.9%		79%	92%	92%	81%	85%	85%	89%	91%	83%	92%	92%	81%	75%
78.5%		79%	84%	86%	86%	63%	87%	93%	74%	80%	78%	63%	63%	85%
73.6%		83%	79%	80%	86%	60%	78%	79%	79%	68%	82%	61%	56%	66%
77.8%		82%	80%	76%	86%	75%	74%	70%	78%	79%	73%	72%	81%	85%
79.6%		83%	83%	85%	83%	80%	64%	81%	78%	81%	77%	82%	78%	80%
82.8%		79%	77%	82%	85%	91%	81%	84%	79%	85%	79%	84%	79%	92%
80.5%		76%	89%	86%	69%	84%	76%	64%	74%	77%	88%	88%	91%	85%
81.9%		80%	86%	81%	67%	89%	84%	68%	86%	90%	87%	82%	80%	85%
93.0%		96%	95%	95%	90%	98%	93%	89%	87%	96%	84%	95%	93%	98%
75.0%		84%	71%	72%	77%	68%	82%	88%	80%	75%	62%	75%	71%	70%
80.3%		77%	84%	80%	80%	83%	80%	78%	75%	82%	73%	82%	84%	86%
84.2%		81%	89%	86%	86%	92%	89%	83%	74%	83%	81%	82%	82%	87%
83.2%		84%	87%	88%	82%	86%	78%	87%	80%	81%	74%	87%	86%	81%
87.2%		91%	90%	94%	92%	77%	90%	86%	92%	88%	89%	90%	78%	77%
88.0%		89%	91%	89%	87%	92%	83%	89%	90%	87%	88%	88%	79%	92%
83.4%		87%	89%	83%	84%	87%	82%	83%	77%	76%	79%	85%	87%	85%
92.5%		98%	93%	92%	88%	93%	91%	94%	86%	95%	95%	95%	99%	84%
88.5%		96%	94%	88%	95%	78%	94%	97%	92%	86%	73%	89%	85%	84%
82.6%		87%	92%	87%	85%	76%	89%	86%	85%	81%	79%	79%	69%	79%
85.5%		88%	87%	87%	87%	84%	91%	88%	78%	85%	82%	74%	88%	92%
84.2%		96%	88%	75%	88%	81%	85%	83%	79%	88%	79%	87%	88%	78%
87.3%		86%	87%	87%	89%	85%	83%	91%	86%	90%	87%	90%	84%	90%
67.5%		68%	68%	67%	62%	74%	65%	67%	57%	69%	62%	62%	80%	77%
79.9%		82%	77%	78%	89%	80%	73%	79%	72%	83%	70%	90%	85%	81%
74.3%		71%	85%	85%	92%	87%	63%	66%	61%	66%	45%	66%	83%	96%
83.2%		91%	88%	76%	84%	75%	69%	78%	83%	88%	90%	76%	95%	89%
76.1%		74%	71%	72%	75%	77%	79%	76%	83%	81%	84%	70%	67%	80%
44.1%		31%	50%	51%	32%	40%	44%	41%	37%	46%	45%	46%	62%	48%
75.1%		79%	73%	63%	91%	67%	57%	67%	76%	66%	75%	88%	92%	82%
83.9%		88%	86%	87%	89%	67%	93%	89%	86%	91%	87%	82%	76%	70%
64.1%		64%	66%	67%	61%	73%	68%	69%	59%	57%	55%	68%	61%	65%
82.1%		79%	88%	87%	68%	84%	79%	74%	80%	81%	76%	91%	90%	90%
90.9%		92%	92%	83%	93%	92%	91%	93%	90%	90%	91%	91%	91%	93%
88.8%		93%	90%	81%	83%	93%	89%	93%	87%	90%	93%	91%	89%	82%
81.2%		85%	77%	90%	95%	57%	81%	84%	88%	87%	79%	79%	75%	79%
75.2%		80%	84%	71%	74%	69%	76%	73%	81%	80%	57%	72%	84%	76%
79.1%		81%	82%	83%	82%	72%	82%	80%	88%	81%	73%	74%	75%	75%
90.2%		88%	90%	93%	94%	88%	86%	90%	95%	96%	94%	89%	81%	89%
68.8%		81%	64%	72%	79%	66%	63%	52%	58%	75%	52%	66%	86%	81%
88.4%		85%	89%	90%	95%	89%	82%	84%	91%	89%	92%	93%	85%	85%
83.8%		86%	81%	84%	89%	69%	88%	91%	89%	89%	81%	90%	77%	76%
85.5%		75%	88%	75%	91%	75%	94%	92%	93%	88%	88%	74%	87%	92%
87.1%		92%	97%	97%	91%	76%	88%	95%	96%	92%	83%	79%	62%	84%
64.4%		59%	64%	75%	67%	47%	62%	67%	73%	76%	68%	63%	53%	63%
80.3%		88%	83%	82%	79%	81%	80%	80%	80%	86%	65%	78%	80%	82%
88.8%		88%	83%	89%	90%	95%	89%	88%	89%	95%	95%	89%	73%	91%
82.1%		86%	87%	70%	74%	84%	76%	76%	73%	80%	88%	90%	94%	89%
87.2%		92%	89%	88%	91%	77%	91%	86%	92%	91%	83%	90%	85%	79%
71.5%		65%	56%	70%	78%	76%	69%	57%	66%	74%	76%	75%	86%	82%
88.4%		89%	94%	93%	76%	89%	92%	88%	88%	85%	86%	90%	93%	86%
90.5%		94%	94%	87%	98%	80%	90%	83%	93%	97%	73%	97%	94%	97%
72.5%		71%	75%	75%	69%	74%	71%	71%	66%	74%	75%	75%	81%	66%