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 Gender%3Afemale - Run 9d1932f...

Global Dialogues GD4 - Female

DTEF: Predict response distributions for Female. 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

General Knowledge

Best Models (Coverage)

1.Claude Haiku 4.5
81.7%
2.GPT 4.1
81.6%
3.Claude Sonnet 4
81.5%
4.Llama 4 Maverick
81.4%
5.Claude Sonnet 4.5
81.3%

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		1st 81.7%	3rd 81.5%	5th 81.3%	6th 81.2%	12th 77.4%	4th 81.4%	10th 78.9%	2nd 81.6%	7th 80.8%	13th 76.6%	9th 79.4%	11th 78.0%	8th 80.4%
66.6%		71%	69%	75%	64%	47%	67%	67%	61%	76%	73%	64%	66%	66%
67.6%		72%	67%	67%	90%	51%	55%	65%	88%	73%	63%	65%	57%	66%
80.6%		80%	75%	87%	88%	82%	83%	80%	80%	81%	77%	78%	76%	81%
81.2%		85%	86%	91%	76%	83%	80%	76%	85%	82%	77%	74%	79%	81%
66.6%		73%	74%	78%	69%	55%	68%	68%	69%	63%	62%	62%	58%	67%
86.7%		88%	90%	90%	89%	82%	85%	91%	91%	89%	93%	93%	75%	71%
55.7%		68%	56%	56%	58%	53%	57%	51%	46%	56%	35%	52%	68%	68%
77.9%		75%	76%	69%	72%	87%	77%	66%	82%	74%	77%	85%	89%	84%
82.1%		86%	80%	80%	77%	86%	92%	80%	71%	83%	89%	84%	72%	87%
79.2%		85%	58%	59%	60%	90%	76%	56%	91%	93%	94%	94%	83%	91%
84.3%		86%	88%	89%	73%	82%	86%	81%	87%	88%	83%	86%	81%	86%
89.0%		96%	93%	92%	87%	85%	97%	97%	95%	90%	71%	89%	82%	83%
86.8%		86%	89%	89%	85%	88%	88%	85%	89%	87%	87%	87%	81%	88%
66.5%		69%	69%	73%	66%	65%	68%	69%	65%	57%	67%	58%	68%	70%
73.1%		66%	77%	74%	68%	70%	81%	69%	78%	76%	80%	72%	64%	75%
81.8%		88%	74%	92%	92%	70%	87%	83%	90%	85%	72%	85%	70%	76%
85.2%		87%	83%	84%	96%	79%	88%	90%	87%	77%	88%	83%	78%	88%
89.2%		88%	95%	94%	93%	90%	93%	84%	93%	88%	75%	92%	85%	90%
84.3%		87%	91%	83%	88%	80%	83%	80%	95%	81%	69%	88%	82%	89%
73.2%		75%	69%	68%	75%	68%	68%	77%	70%	75%	80%	80%	71%	76%
85.8%		90%	92%	90%	90%	85%	88%	81%	93%	80%	70%	89%	81%	86%
89.8%		89%	90%	90%	90%	95%	96%	95%	85%	93%	76%	85%	93%	91%
84.5%		81%	83%	88%	88%	84%	83%	88%	88%	81%	88%	88%	82%	76%
57.4%		63%	74%	74%	58%	45%	63%	57%	68%	59%	54%	41%	42%	48%
84.9%		83%	85%	91%	86%	85%	87%	80%	92%	87%	82%	79%	83%	84%
62.1%		66%	50%	47%	62%	71%	72%	58%	49%	67%	45%	65%	76%	79%
86.3%		72%	88%	87%	93%	92%	88%	95%	85%	88%	84%	84%	83%	83%
79.2%		74%	80%	83%	92%	58%	82%	88%	77%	77%	87%	78%	70%	84%
80.5%		88%	88%	85%	88%	64%	88%	84%	87%	79%	78%	78%	72%	68%
79.3%		80%	87%	90%	79%	71%	82%	79%	77%	80%	79%	77%	65%	85%
89.9%		90%	94%	88%	88%	93%	90%	91%	95%	92%	88%	88%	88%	84%
82.2%		87%	88%	75%	85%	79%	79%	71%	79%	81%	80%	87%	86%	91%
81.5%		91%	87%	98%	96%	72%	83%	87%	80%	80%	86%	67%	62%	70%
72.5%		73%	71%	86%	89%	68%	76%	81%	80%	77%	50%	66%	60%	65%
73.3%		71%	76%	71%	81%	78%	80%	54%	69%	65%	73%	78%	82%	75%
85.0%		86%	86%	89%	84%	87%	84%	86%	87%	84%	87%	87%	78%	80%
70.8%		74%	63%	54%	68%	82%	72%	65%	65%	63%	85%	74%	88%	68%
80.8%		88%	82%	84%	79%	86%	80%	72%	85%	89%	70%	68%	84%	84%
89.2%		93%	92%	85%	89%	90%	89%	86%	90%	92%	87%	87%	91%	89%
68.8%		57%	62%	77%	58%	81%	65%	62%	66%	76%	64%	70%	77%	80%
87.4%		93%	93%	96%	91%	70%	93%	94%	91%	91%	70%	89%	71%	94%
88.2%		92%	93%	83%	84%	93%	92%	88%	90%	93%	93%	79%	93%	74%
82.8%		82%	83%	81%	82%	77%	91%	85%	88%	88%	78%	86%	72%	84%
72.9%		74%	79%	69%	70%	66%	88%	81%	84%	71%	74%	68%	71%	53%
86.3%		89%	87%	91%	85%	87%	91%	78%	91%	83%	82%	81%	88%	89%
83.1%		79%	83%	78%	90%	89%	86%	85%	91%	81%	64%	79%	90%	85%
80.9%		92%	84%	68%	87%	80%	79%	81%	76%	84%	87%	81%	79%	74%
89.2%		89%	94%	89%	84%	94%	89%	89%	84%	88%	80%	93%	94%	93%
87.9%		81%	78%	78%	80%	89%	99%	89%	86%	95%	97%	88%	88%	95%
84.5%		88%	87%	84%	85%	82%	89%	87%	95%	81%	70%	85%	76%	90%
86.5%		92%	92%	93%	93%	73%	90%	87%	88%	83%	79%	90%	80%	84%
72.8%		70%	81%	91%	75%	65%	73%	74%	85%	72%	67%	70%	61%	62%
72.5%		74%	74%	74%	70%	67%	65%	72%	66%	72%	73%	77%	74%	84%
65.5%		68%	61%	62%	69%	70%	71%	68%	74%	70%	59%	55%	62%	62%
87.8%		85%	95%	90%	85%	79%	90%	88%	90%	88%	84%	92%	88%	87%
85.6%		81%	88%	80%	89%	80%	86%	93%	92%	87%	92%	78%	79%	88%
70.5%		70%	79%	79%	65%	51%	84%	73%	86%	72%	72%	70%	58%	58%
88.8%		93%	92%	92%	90%	92%	90%	77%	88%	92%	87%	87%	84%	90%
69.2%		76%	68%	81%	88%	58%	70%	72%	76%	76%	39%	74%	51%	70%
79.9%		79%	83%	84%	83%	92%	79%	73%	82%	74%	72%	78%	85%	75%
87.9%		93%	91%	91%	88%	76%	89%	91%	93%	93%	92%	84%	74%	88%
72.1%		77%	76%	78%	77%	55%	71%	77%	74%	71%	78%	66%	68%	69%
85.8%		88%	92%	88%	92%	91%	86%	91%	87%	88%	72%	76%	77%	88%
86.2%		88%	90%	89%	67%	85%	85%	82%	86%	92%	90%	92%	84%	91%
84.6%		78%	91%	87%	81%	83%	85%	87%	81%	87%	88%	89%	84%	79%
88.4%		90%	91%	87%	90%	79%	90%	90%	94%	91%	92%	85%	78%	92%
80.7%		87%	81%	93%	93%	65%	91%	84%	84%	81%	72%	68%	74%	76%
77.0%		86%	85%	79%	81%	74%	70%	71%	71%	81%	73%	69%	78%	83%
81.8%		82%	82%	78%	84%	87%	80%	82%	81%	81%	85%	82%	81%	79%
92.0%		93%	84%	90%	94%	87%	92%	99%	92%	96%	90%	90%	91%	98%
86.2%		87%	86%	86%	90%	88%	91%	83%	85%	78%	88%	87%	80%	92%
82.6%		84%	85%	85%	67%	88%	84%	71%	91%	90%	87%	83%	79%	80%
89.5%		93%	91%	79%	82%	87%	93%	92%	92%	90%	90%	89%	88%	98%
73.6%		83%	80%	78%	89%	62%	71%	86%	74%	71%	73%	71%	64%	55%
75.8%		75%	78%	79%	78%	81%	77%	66%	73%	72%	69%	75%	81%	81%
80.3%		81%	77%	83%	79%	85%	89%	76%	71%	81%	73%	82%	81%	86%
84.9%		85%	94%	94%	88%	86%	89%	88%	87%	90%	73%	81%	75%	74%
83.0%		88%	79%	85%	88%	63%	85%	86%	84%	86%	86%	84%	78%	87%
85.1%		87%	87%	88%	65%	86%	85%	86%	87%	89%	88%	88%	87%	83%
85.4%		87%	93%	82%	82%	83%	90%	82%	88%	83%	79%	84%	88%	89%
89.5%		91%	87%	82%	90%	94%	87%	87%	86%	91%	92%	93%	88%	95%
88.2%		95%	93%	94%	88%	90%	88%	92%	97%	84%	64%	85%	88%	89%
77.6%		83%	78%	78%	68%	80%	83%	80%	75%	70%	79%	78%	77%	80%
93.7%		88%	98%	89%	93%	91%	98%	98%	91%	96%	92%	95%	95%	94%
83.9%		85%	89%	84%	86%	79%	85%	87%	83%	81%	81%	87%	82%	82%
85.3%		86%	86%	87%	86%	88%	84%	86%	84%	83%	84%	85%	85%	85%
77.2%		79%	80%	84%	81%	84%	70%	68%	66%	76%	64%	80%	87%	85%
80.4%		81%	79%	77%	83%	85%	75%	76%	87%	83%	67%	86%	82%	84%
76.7%		80%	82%	88%	89%	90%	70%	72%	76%	68%	45%	64%	80%	93%
78.5%		90%	73%	61%	72%	76%	76%	69%	68%	76%	95%	82%	94%	89%
79.5%		78%	75%	73%	78%	76%	82%	88%	82%	84%	80%	82%	74%	82%
47.0%		42%	51%	52%	61%	48%	40%	32%	48%	46%	44%	46%	62%	39%
65.2%		77%	62%	62%	51%	59%	55%	55%	58%	62%	62%	90%	79%	76%
86.5%		92%	89%	89%	95%	74%	93%	90%	92%	84%	78%	84%	80%	85%
65.3%		63%	70%	79%	66%	71%	70%	66%	59%	62%	65%	51%	65%	62%
79.9%		74%	83%	81%	86%	83%	70%	66%	83%	77%	80%	75%	90%	91%
81.8%		83%	86%	89%	70%	85%	82%	64%	89%	82%	79%	88%	88%	79%
86.0%		88%	86%	77%	72%	95%	85%	76%	79%	96%	92%	92%	92%	88%
81.8%		85%	89%	90%	97%	59%	86%	84%	92%	84%	76%	75%	60%	86%
73.4%		76%	81%	85%	89%	65%	65%	60%	83%	75%	66%	67%	78%	64%
76.2%		78%	84%	89%	75%	73%	77%	76%	89%	78%	69%	73%	58%	71%
87.3%		73%	90%	96%	88%	83%	90%	90%	87%	92%	94%	83%	78%	91%
55.5%		63%	48%	45%	62%	57%	53%	53%	36%	58%	40%	60%	78%	68%
80.9%		77%	76%	79%	80%	71%	80%	87%	84%	82%	86%	83%	86%	81%
88.1%		91%	91%	89%	87%	77%	94%	93%	92%	91%	77%	91%	88%	84%
89.0%		96%	91%	78%	89%	75%	96%	97%	95%	96%	81%	74%	95%	94%
84.4%		89%	92%	96%	96%	70%	85%	94%	97%	88%	75%	84%	49%	82%
67.8%		68%	65%	77%	77%	48%	66%	76%	84%	78%	62%	63%	54%	64%
77.2%		81%	85%	86%	83%	70%	78%	75%	84%	77%	52%	76%	79%
86.8%		90%	87%	86%	85%	89%	90%	82%	91%	94%	89%	89%	73%	83%
75.2%		77%	65%	59%	67%	85%	74%	59%	68%	68%	90%	90%	90%	85%
82.4%		87%	74%	74%	96%	73%	83%	80%	68%	84%	89%	94%	83%	86%
71.7%		73%	65%	55%	73%	75%	81%	65%	55%	76%		80%	84%	79%
87.5%		89%	89%	89%	73%	90%	88%	82%	86%	87%	91%	92%	93%	88%
89.8%		95%	95%	92%	94%	81%	93%	96%	98%	88%	75%	86%	94%	80%
77.8%		70%	80%	75%	87%	88%	81%	78%	81%	79%	73%	73%	82%	65%