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%3Amale - Run 8219581...

Global Dialogues GD4 - Male

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

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Social interaction

AI Safety & Robustness

Instruction Following & Prompt Adherence

Economics & Finance

Best Models (Coverage)

1.Claude Sonnet 4.5
83.1%
2.Claude Haiku 4.5
82.8%
3.GPT 4.1
82.8%
4.Claude Sonnet 4
82.3%
5.GPT 4.1 Mini
82.0%

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		2nd 82.8%	4th 82.3%	1st 83.1%	7th 81.6%	13th 76.8%	6th 81.7%	8th 80.7%	3rd 82.8%	5th 82.0%	11th 78.2%	10th 79.7%	12th 77.7%	9th 80.2%
63.2%		66%	69%	73%	70%	39%	61%	66%	67%	69%	67%	56%	63%	56%
70.1%		69%	69%	72%	83%	55%	61%	62%	85%	78%	76%	69%	60%	72%
82.2%		84%	85%	89%	90%	68%	87%	84%	86%	82%	76%	79%	78%	81%
86.3%		88%	89%	94%	77%	90%	85%	88%	88%	86%	84%	86%	83%	84%
73.0%		79%	73%	80%	75%	64%	78%	75%	74%	70%	69%	69%	69%	74%
82.2%		76%	78%	89%	79%	79%	81%	88%	88%	84%	89%	93%	76%	68%
56.4%		63%	63%	63%	54%	62%	66%	45%	48%	62%	28%	51%	64%	64%
81.3%		76%	87%	77%	69%	86%	81%	79%	88%	85%	85%	85%	74%	85%
86.9%		89%	88%	87%	78%	88%	95%	79%	93%	89%	94%	85%	76%	89%
78.5%		83%	57%	56%	92%	90%	70%	63%	80%	91%	85%	91%	76%	87%
86.8%		87%	82%	91%	85%	85%	86%	91%	89%	91%	90%	87%	80%	85%
90.0%		96%	93%	94%	86%	92%	93%	92%	98%	92%	71%	93%	85%	85%
78.0%		81%	74%	78%	69%	83%	75%	82%	81%	76%	86%	73%	76%	80%
67.8%		70%	70%	74%	76%	66%	69%	62%	66%	66%	68%	54%	69%	71%
78.2%		73%	77%	80%	78%	73%	87%	82%	86%	82%	78%	80%	64%	77%
82.8%		92%	81%	97%	88%	69%	90%	84%	91%	86%	64%	77%	74%	84%
82.8%		88%	84%	85%	95%	69%	89%	90%	82%	75%	90%	73%	77%	80%
90.4%		90%	90%	89%	86%	94%	94%	96%	93%	90%	91%	81%	86%	95%
85.0%		86%	93%	93%	88%	77%	85%	85%	93%	85%	68%	89%	82%	81%
74.1%		82%	67%	70%	73%	68%	76%	77%	67%	76%	80%	82%	72%	73%
91.2%		95%	93%	89%	95%	94%	88%	94%	93%	93%	82%	92%	86%	91%
91.2%		93%	96%	92%	94%	86%	86%	94%	90%	93%	85%	92%	90%	95%
79.5%		77%	75%	88%	78%	81%	83%	88%	80%	71%	93%	78%	79%	62%
66.6%		75%	73%	75%	63%	54%	69%	71%	70%	69%	74%	51%	57%	65%
85.8%		83%	84%	88%	76%	93%	84%	81%	88%	87%	81%	82%	92%	96%
60.5%		64%	55%	55%	66%	64%	65%	47%	55%	63%	47%	59%	67%	80%
86.8%		80%	83%	88%	95%	91%	86%	92%	88%	92%	91%	80%	82%	81%
74.8%		67%	76%	76%	80%	57%	76%	78%	81%	83%	82%	78%	69%	70%
77.7%		78%	84%	90%	87%	61%	85%	83%	88%	77%	79%	67%	65%	66%
77.0%		81%	80%	91%	86%	64%	84%	76%	74%	77%	76%	72%	66%	74%
85.2%		84%	86%	90%	81%	85%	87%	89%	87%	85%	89%	90%	83%	72%
86.8%		89%	89%	80%	86%	89%	85%	87%	89%	90%	82%	91%	90%	81%
71.8%		84%	75%	81%	84%	60%	66%	87%	73%	67%	79%	63%	51%	64%
70.4%		74%	72%	77%	83%	60%	78%	67%	77%	74%	57%	66%	62%	68%
86.5%		89%	92%	86%	91%	83%	86%	70%	85%	85%	84%	90%	91%	92%
85.4%		78%	83%	87%	89%	85%	86%	89%	88%	83%	87%	89%	85%	81%
87.2%		90%	88%	67%	92%	96%	83%	83%	84%	84%	87%	94%	93%	93%
82.8%		86%	89%	83%	85%	86%	79%	72%	85%	81%	84%	72%	89%	85%
84.5%		81%	83%	85%	81%	85%	83%	92%	86%	85%	88%	88%	84%	77%
71.8%		62%	71%	77%	67%	79%	67%	62%	75%	80%	77%	69%	79%	69%
90.9%		95%	95%	94%	86%	85%	95%	91%	95%	96%	80%	94%	83%	93%
86.8%		93%	94%	85%	91%	95%	85%	88%	90%	84%	79%	77%	94%	73%
80.8%		88%	92%	90%	88%	61%	81%	90%	78%	91%	93%	64%	60%	75%
76.7%		75%	76%	74%	78%	66%	92%	88%	83%	76%	87%	73%	73%	56%
85.8%		88%	91%	95%	80%	84%	88%	84%	92%	89%	79%	83%	79%	83%
88.3%		92%	89%	88%	91%	86%	95%	89%	91%	86%	81%	86%	85%	89%
85.2%		94%	87%	87%	90%	80%	91%	85%	85%	86%	86%	81%	79%	76%
86.5%		81%	87%	87%	82%	82%	85%	86%	91%	82%	88%	96%	96%	82%
90.9%		94%	88%	86%	90%	98%	91%	88%	89%	92%	93%	92%	89%	92%
87.8%		91%	92%	91%	86%	78%	91%	89%	93%	90%	83%	87%	80%	90%
87.2%		91%	94%	95%	90%	84%	92%	86%	88%	88%	70%	88%	79%	88%
72.6%		70%	88%	83%	75%	66%	71%	81%	79%	70%	69%	68%	60%	64%
65.6%		72%	63%	63%	71%	61%	59%	70%	59%	75%	64%	65%	57%	74%
68.2%		72%	63%	67%	73%	63%	68%	74%	70%	70%	75%	59%	66%	67%
83.5%		78%	89%	95%	73%	75%	90%	87%	86%	88%	83%	82%	80%	79%
80.7%		79%	83%	89%	88%	70%	75%	81%	88%	82%	85%	68%	73%	88%
78.6%		80%	85%	85%	63%	63%	94%	75%	87%	72%	72%	82%	76%	88%
85.5%		90%	81%	82%	84%	91%	79%	91%	83%	93%	90%	86%	75%	87%
70.5%		79%	70%	84%	88%	55%	70%	74%	75%	75%	51%	63%	55%	78%
84.1%		84%	87%	85%	86%	91%	84%	73%	85%	85%	82%	86%	87%	78%
86.8%		91%	83%	96%	83%	73%	93%	84%	98%	89%	90%	76%	80%	93%
66.5%		73%	76%	74%	66%	46%	70%	69%	71%	61%	76%	56%	63%	63%
91.0%		98%	95%	95%	91%	89%	97%	95%	92%	92%	82%	87%	85%	85%
88.8%		89%	89%	92%	91%	84%	91%	88%	90%	89%	89%	90%	81%	91%
79.2%		74%	77%	87%	65%	83%	85%	88%	79%	73%	96%	85%	77%	61%
83.4%		83%	94%	92%	96%	65%	92%	94%	80%	78%	73%	80%	72%	85%
72.8%		76%	77%	77%	85%	58%	77%	87%	75%	72%	75%	59%	65%	63%
75.7%		76%	75%	74%	78%	75%	74%	73%	71%	77%	71%	76%	79%	85%
81.7%		80%	80%	78%	81%	84%	81%	79%	84%	82%	85%	81%	83%	84%
87.8%		92%	82%	88%	89%	89%	85%	88%	82%	92%	85%	88%	89%	92%
86.8%		90%	89%	89%	88%	80%	89%	82%	91%	90%	88%	87%	76%	89%
85.2%		88%	88%	87%	66%	94%	83%	70%	91%	94%	88%	88%	85%	85%
91.9%		97%	97%	92%	92%	83%	95%	84%	93%	89%	93%	93%	91%	96%
74.1%		86%	84%	82%	77%	62%	72%	85%	83%	73%	62%	68%	59%	70%
85.8%		88%	88%	88%	85%	89%	79%	88%	87%	85%	73%	87%	86%	92%
83.2%		83%	88%	84%	80%	83%	91%	78%	78%	87%	78%	84%	81%	86%
87.8%		89%	94%	87%	88%	85%	88%	89%	91%	89%	83%	89%	86%	84%
76.4%		81%	77%	83%	78%	54%	81%	76%	82%	80%	84%	75%	71%	71%
83.8%		84%	85%	87%	76%	79%	81%	84%	88%	86%	85%	82%	84%	88%
84.0%		82%	94%	87%	70%	76%	85%	87%	87%	89%	86%	82%	82%	85%
90.9%		90%	87%	87%	90%	96%	90%	91%	95%	95%	93%	93%	88%	87%
89.2%		95%	94%	95%	89%	84%	93%	94%	96%	87%	71%	90%	85%	86%
82.4%		88%	84%	83%	83%	80%	89%	76%	86%	82%	82%	83%	73%	82%
90.1%		91%	92%	92%	84%	95%	83%	96%	88%	86%	88%	91%	92%	93%
86.2%		81%	91%	93%	84%	83%	93%	90%	92%	88%	74%	87%	88%	76%
84.4%		84%	77%	86%	87%	86%	81%	82%	85%	86%	86%	86%	80%	91%
77.3%		79%	81%	82%	76%	78%	71%	76%	70%	77%	68%	82%	82%	83%
82.4%		83%	80%	81%	85%	79%	76%	81%	87%	86%	74%	88%	87%	84%
81.0%		87%	91%	91%	82%	93%	79%	81%	76%	77%	48%	73%	87%	88%
85.0%		85%	81%	76%	85%	79%	79%	75%	83%	86%	95%	88%	98%	95%
69.5%		70%	68%	66%	71%	63%	71%	67%	73%	75%	67%	67%	69%	77%
59.6%		60%	61%	60%	71%	59%	48%	41%	52%	55%	57%	67%	72%	72%
62.8%		77%	60%	60%	53%	63%	53%	56%	57%	61%	56%	81%	84%	56%
82.8%		87%	86%	87%	86%	71%	92%	90%	87%	87%	81%	77%	73%	73%
74.5%		75%	84%	71%	74%	82%	76%	75%	69%	70%	72%	72%	73%	76%
87.5%		89%	89%	90%	88%	93%	88%	73%	88%	87%	87%	91%	86%	88%
86.2%		87%	89%	92%	73%	89%	85%	83%	92%	92%	80%	90%	84%	84%
86.7%		90%	91%	89%	81%	85%	90%	83%	84%	87%	82%	88%	86%	91%
79.4%		83%	76%	87%	95%	60%	83%	86%	85%	85%	69%	74%	61%	88%
87.7%		90%	95%	91%	89%	89%	77%	81%	94%	92%	76%	86%	88%	92%
76.6%		77%	80%	85%	79%	78%	75%	74%	87%	79%	73%	73%	65%	71%
79.7%		70%	83%	87%	83%	70%	77%	84%	87%	84%	87%	71%	70%	83%
54.7%		65%	48%	55%	55%	56%	60%	45%	44%	62%	30%	57%	69%	65%
81.2%		84%	73%	84%	88%	79%	79%	75%	86%	74%	88%	87%	83%	75%
85.4%		84%	90%	87%	88%	74%	92%	89%	93%	92%	78%	90%	75%	78%
86.2%		95%	91%	77%	82%	74%	92%	89%	89%	91%	73%	88%	92%	88%
84.6%		94%	97%	94%	96%	59%	78%	95%	93%	77%	90%	82%	65%	80%
70.2%		71%	68%	75%	80%	53%	70%	79%	80%	79%	65%	64%	60%	69%
78.3%		84%	81%	85%	75%	72%	79%	83%	83%	86%	45%	78%	82%	85%
80.9%		80%	78%	85%	86%	77%	84%	89%	84%	81%	88%	81%	62%	77%
85.3%		91%	91%	68%	81%	98%	83%	69%	77%	83%	84%	94%	95%	95%
78.2%		87%	77%	80%	85%	60%	90%	72%	73%	79%	89%	87%	70%	68%
67.4%		72%	63%	53%	66%	68%	73%	64%	56%	70%	54%	73%	83%	81%
88.4%		90%	88%	90%	89%	90%	87%	88%	90%	91%	86%	87%	83%	90%
91.3%		96%	96%	94%	92%	94%	95%	95%	97%	90%	76%	86%	95%	81%
84.3%		83%	88%	80%	86%	90%	85%	83%	86%	87%	79%	87%	85%	77%