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 Gender%3Amale C5 - Run f696539...

Global Dialogues GD4 - Male (5 context Qs)

DTEF: Predict response distributions for Male. 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

Sociology & Anthropology

Best Models (Coverage)

1.GPT 4.1
83.4%
2.GPT 4.1 Mini
82.9%
3.Claude Sonnet 4.5
82.7%
4.Claude Sonnet 4
82.2%
5.Claude Haiku 4.5
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		5th 82.0%	4th 82.2%	3rd 82.7%	6th 81.7%	11th 78.0%	8th 80.8%	7th 81.4%	1st 83.4%	2nd 82.9%	13th 76.6%	9th 80.7%	10th 79.0%	12th 77.1%
63.2%		65%	68%	79%	75%	47%	59%	60%	61%	67%	61%	57%	67%	56%
67.2%		65%	67%	72%	90%	41%	59%	62%	89%	73%	65%	69%	61%	60%
83.1%		81%	92%	92%	73%	85%	89%	83%	79%	88%	82%	81%	79%	76%
86.6%		91%	91%	91%	83%	90%	86%	90%	90%	82%	85%	82%	79%	86%
72.2%		81%	79%	80%	78%	59%	75%	76%	70%	67%	71%	69%	64%	70%
80.2%		81%	78%	83%	90%	76%	78%	77%	91%	88%	75%	93%	80%	53%
68.5%		87%	76%	84%	86%	62%	70%	61%	60%	64%	56%	61%	58%	66%
78.8%		90%	65%	61%	77%	86%	87%	86%	63%	84%	86%	85%	80%	74%
86.9%		80%	84%	84%	85%	91%	94%	80%	94%	87%	96%	85%	85%	85%
84.7%		80%	83%	86%	93%	90%	77%	67%	84%	84%	88%	94%	91%	84%
83.6%		84%	82%	85%	89%	84%	82%	84%	89%	73%	90%	90%	85%	70%
86.5%		94%	89%	90%	89%	96%	80%	88%	89%	94%	61%	84%	86%	85%
78.8%		84%	77%	76%	74%	80%	73%	91%	79%	82%	69%	80%	81%	79%
69.4%		89%	89%	74%	68%	66%	69%	63%	66%	68%	55%	55%	70%	70%
71.5%		63%	77%	78%	57%	68%	74%	68%	76%	77%	76%	71%	73%	71%
82.2%		83%	84%	90%	88%	80%	86%	89%	92%	87%	61%	77%	74%	77%
87.1%		90%	82%	90%	92%	90%	88%	91%	80%	88%	85%	84%	79%	93%
87.0%		89%	87%	81%	88%	79%	84%	85%	83%	95%	85%	91%	94%	90%
85.1%		84%	87%	89%	90%	89%	82%	83%	86%	89%	67%	87%	84%	89%
78.5%		85%	78%	78%	74%	67%	79%	78%	84%	79%	77%	88%	82%	71%
88.1%		90%	89%	86%	91%	85%	90%	84%	80%	93%	77%	92%	93%	95%
89.9%		95%	86%	92%	85%	89%	83%	88%	95%	98%	76%	92%	95%	95%
71.3%		67%	70%	74%	92%	69%	80%	80%	85%	77%	69%	77%	51%	36%
68.0%		72%	78%	81%	88%	56%	61%	63%	71%	64%	60%	52%	56%	82%
85.5%		86%	86%	87%	81%	91%	85%	84%	95%	83%	84%	76%	85%	88%
86.0%		94%	82%	85%	85%	95%	86%	83%	87%	83%	90%	84%	81%	83%
86.1%		73%	82%	80%	90%	96%	93%	92%	81%	90%	76%	91%	90%	85%
80.9%		81%	76%	85%	81%	53%	88%	93%	88%	90%	84%	83%	71%	79%
84.6%		92%	90%	90%	91%	76%	88%	89%	94%	81%	80%	78%	72%	79%
83.8%		92%	93%	94%	90%	63%	84%	80%	88%	89%	85%	72%	77%	83%
81.2%		78%	83%	86%	92%	83%	84%	81%	86%	74%	87%	90%	77%	54%
79.4%		77%	62%	75%	84%	88%	89%	80%	77%	88%	81%	90%	91%	50%
74.5%		79%	72%	82%	89%	62%	69%	87%	80%	78%	61%	75%	73%	61%
72.7%		72%	77%	80%	95%	71%	67%	82%	81%	76%	64%	64%	61%	55%
86.8%		82%	84%	92%	74%	92%	86%	87%	88%	91%	91%	90%	92%	79%
82.7%		84%	87%	87%	88%	91%	76%	85%	87%	80%	86%	88%	79%	57%
88.1%		93%	84%	72%	82%	91%	89%	90%	89%	89%	86%	94%	94%	92%
84.8%		84%	89%	86%	84%	84%	83%	78%	85%	85%	88%	82%	90%	85%
80.0%		85%	80%	80%	88%	81%	78%	83%	89%	80%	73%	88%	84%	51%
74.8%		68%	73%	71%	68%	82%	68%	60%	70%	83%	89%	81%	80%	80%
86.0%		95%	94%	94%	71%	83%	91%	85%	90%	93%	72%	81%	76%	93%
85.8%		92%	94%	93%	84%	93%	91%	86%	78%	89%	79%	69%	78%	89%
67.4%		68%	66%	66%	61%	64%	63%	69%	76%	74%	78%	65%	68%	58%
74.2%		75%	76%	74%	72%	76%	85%	83%	68%	64%	85%	68%	67%	72%
87.0%		90%	92%	92%	86%	90%	91%	87%	91%	85%	83%	70%	86%	88%
84.0%		71%	92%	82%	75%	75%	93%	91%	92%	90%	75%	78%	92%	86%
81.0%		87%	83%	76%	89%	71%	85%	85%	80%	84%	81%	70%	81%	81%
85.2%		91%	95%	92%	75%	75%	85%	75%	99%	82%	75%	97%	92%	75%
87.2%		96%	90%	89%	73%	86%	83%	90%	96%	87%	77%	83%	90%	94%
88.5%		90%	97%	91%	82%	90%	90%	89%	90%	89%	79%	89%	82%	93%
88.2%		89%	93%	90%	93%	86%	86%	86%	87%	92%	82%	90%	84%	88%
69.8%		72%	72%	76%	87%	65%	62%	71%	78%	64%	65%	70%	64%	61%
77.4%		85%	78%	88%	88%	69%	63%	78%	73%	75%	80%	72%	87%	70%
67.7%		69%	64%	64%	94%	59%	65%	66%	69%	68%	72%	63%	63%	64%
82.8%		74%	85%	96%	69%	79%	79%	91%	90%	89%	81%	88%	79%	77%
85.1%		85%	80%	89%	86%	77%	85%	96%	87%	89%	83%	80%	81%	88%
62.6%		52%	78%	64%	92%	47%	69%	62%	58%	63%	55%	74%	46%	54%
84.2%		88%	81%	82%	89%	91%	77%	87%	85%	89%	67%	82%	90%	86%
69.8%		67%	76%	85%	95%	55%	75%	75%	76%	73%	52%	63%	51%	65%
84.6%		86%	87%	89%	85%	86%	85%	78%	81%	82%	87%	80%	85%	89%
87.6%		83%	93%	96%	83%	77%	93%	94%	89%	95%	91%	87%	88%	70%
68.5%		73%	76%	81%	71%	49%	66%	73%	78%	60%	67%	61%	68%	67%
86.8%		92%	88%	87%	84%	93%	84%	82%	87%	96%	79%	79%	85%	93%
84.9%		87%	82%	88%	86%	91%	82%	85%	90%	80%	89%	90%	85%	69%
73.0%		65%	80%	77%	92%	79%	78%	82%	79%	68%	45%	96%	66%	42%
87.8%		91%	88%	91%	97%	79%	88%	90%	84%	91%	77%	80%	92%	93%
74.4%		81%	76%	74%	89%	57%	76%	81%	77%	78%	84%	62%	62%	70%
78.7%		74%	79%	75%	72%	82%	84%	81%	73%	80%	60%	87%	86%	90%
81.7%		82%	79%	75%	82%	82%	84%	81%	81%	84%	86%	81%	80%	85%
83.3%		93%	77%	63%	79%	81%	72%	76%	84%	93%	96%	89%	92%	88%
83.0%		85%	90%	78%	66%	91%	82%	72%	93%	82%	88%	83%	79%	90%
86.3%		93%	88%	84%	73%	88%	87%	80%	89%	94%	88%	88%	85%	85%
85.5%		93%	92%	80%	74%	87%	85%	82%	78%	91%	91%	93%	87%	79%
72.5%		67%	88%	90%	84%	62%	68%	83%	82%	62%	59%	69%	59%	70%
83.0%		81%	84%	84%	79%	91%	83%	84%	87%	86%	84%	81%	82%	73%
82.7%		79%	88%	86%	75%	89%	88%	79%	67%	85%	83%	87%	83%	86%
88.4%		88%	94%	93%	89%	90%	88%	84%	89%	83%	81%	89%	88%	93%
84.2%		87%	80%	88%	90%	69%	83%	86%	85%	87%	81%	88%	85%	85%
79.5%		84%	77%	80%	87%	84%	74%	74%	83%	84%	81%	85%	76%	64%
84.1%		78%	93%	88%	74%	77%	82%	83%	84%	93%	81%	85%	91%	84%
89.8%		90%	80%	86%	91%	88%	83%	92%	95%	99%	93%	93%	85%	92%
88.2%		93%	83%	89%	90%	86%	93%	93%	89%	91%	75%	95%	85%	85%
82.9%		88%	89%	88%	65%	82%	89%	89%	89%	88%	80%	75%	73%	83%
84.1%		81%	77%	79%	79%	86%	82%	98%	88%	84%	70%	88%	88%	93%
84.0%		62%	83%	91%	87%	80%	93%	84%	87%	89%	86%	86%	88%	76%
81.8%		81%	78%	81%	87%	87%	78%	78%	86%	82%	85%	86%	82%	72%
76.0%		77%	81%	72%	78%	77%	75%	74%	68%	83%	60%	79%	80%	84%
79.3%		80%	80%	80%	87%	74%	73%	74%	84%	83%	70%	82%	82%	82%
82.5%		90%	96%	91%	83%	76%	80%	91%	88%	78%	57%	63%	93%	87%
78.3%		85%	81%	80%	75%	68%	79%	69%	80%	85%	81%	81%	85%	69%
72.8%		66%	67%	70%	82%	60%	78%	88%	75%	75%	81%	67%	68%	70%
74.0%		83%	75%	90%	82%	62%	64%	71%	89%	83%	67%	67%	58%	71%
72.5%		83%	78%	78%	52%	78%	67%	71%	77%	57%	53%	91%	85%	72%
86.3%		93%	86%	92%	94%	72%	91%	89%	89%	90%	81%	85%	78%	82%
73.5%		76%	79%	73%	74%	81%	76%	67%	65%	70%	70%	72%	74%	78%
84.3%		83%	77%	87%	86%	90%	82%	87%	87%	87%	87%	89%	87%	67%
89.5%		87%	93%	93%	77%	90%	90%	79%	93%	94%	91%	90%	93%	94%
86.3%		82%	91%	91%	71%	88%	88%	89%	80%	88%	89%	88%	82%	95%
78.5%		78%	87%	92%	93%	56%	76%	86%	96%	93%	57%	70%	62%	74%
83.5%		86%	88%	88%	80%	82%	85%	85%	91%	93%	66%	76%	87%	79%
71.4%		68%	82%	72%	58%	79%	75%	68%	79%	73%	63%	82%	61%	68%
82.2%		83%	83%	89%	87%	78%	87%	88%	76%	89%	65%	81%	84%	79%
85.1%		92%	86%	91%	90%	87%	74%	74%	85%	75%	93%	84%	91%	84%
71.0%		84%	73%	83%	0%	60%	73%	71%	87%	89%	75%	83%	73%	72%
84.6%		86%	81%	81%	89%	84%	88%	88%	86%	86%	81%	88%	74%	88%
80.6%		67%	67%	75%	77%	75%	92%	90%	95%	85%	84%	78%	70%	93%
77.2%		93%	69%	29%	94%	64%	77%	94%	92%	87%	72%	71%	83%	79%
68.2%		69%	68%	74%	69%	47%	66%	81%	88%	73%	62%	64%	58%	68%
74.5%		65%	80%	71%	85%		88%	69%	66%	87%	56%	95%	67%	65%
75.9%		84%	70%	81%	91%	76%	77%	82%	84%	77%	75%	67%	62%	61%
89.8%		91%	87%	82%	84%	95%	90%	91%	91%	86%	91%	93%	95%	91%
76.5%		79%	78%	84%	88%	67%	82%	78%	86%	87%	70%	87%	66%	43%
87.0%		85%	91%	88%	89%	85%	90%	91%	90%	86%	86%	86%	84%	80%
83.8%		89%	87%	88%	59%	92%	85%	84%	89%	83%	87%	87%	85%	74%
91.7%		78%	96%	98%	95%	94%	95%	97%	99%	90%	73%	89%	98%	90%
83.8%		84%	90%	83%	83%	87%	82%	75%	77%	85%	79%	85%	91%	88%