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%3Afemale C5 - Run dfcfea5...

Global Dialogues GD4 - Female (5 context Qs)

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

AI Safety & Robustness

Social interaction

Best Models (Coverage)

1.Claude Haiku 4.5
83.2%
2.GPT 4.1 Mini
82.7%
3.Claude Sonnet 4.5
82.4%
4.Gemini 2.5 Flash
82.2%
5.Claude Sonnet 4
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		1st 83.2%	5th 82.0%	3rd 82.4%	4th 82.2%	12th 77.0%	9th 80.4%	8th 80.7%	6th 81.8%	2nd 82.7%	13th 75.7%	7th 80.7%	11th 78.4%	10th 78.9%
65.6%		71%	66%	73%	67%	54%	62%	64%	60%	63%	73%	62%	73%	65%
64.3%		66%	66%	71%	91%	36%	58%	69%	87%	69%	53%	58%	57%	55%
83.2%		88%	84%	92%	82%	83%	87%	80%	80%	86%	80%	79%	77%	83%
83.4%		89%	82%	89%	80%	87%	84%	80%	90%	79%	84%	83%	76%	81%
65.0%		78%	73%	76%	70%	52%	64%	72%	74%	61%	34%	63%	62%	66%
82.1%		86%	78%	85%	92%	74%	79%	83%	85%	80%	90%	94%	83%	58%
69.8%		88%	80%	82%	75%	63%	81%	64%	61%	65%	59%	61%	64%	64%
78.5%		87%	59%	59%	73%	76%	87%	85%	61%	86%	90%	89%	85%	84%
79.2%		82%	77%	62%	75%	83%	77%	80%	72%	95%	90%	84%	73%	80%
83.5%		81%	90%	49%	90%	87%	93%	65%	92%	81%	95%	95%	90%	77%
81.1%		83%	80%	85%	81%	75%	79%	79%	81%	81%	82%	86%	81%	81%
87.4%		87%	87%	93%	91%	84%	83%	92%	88%	94%	74%	92%	85%	86%
85.5%		90%	86%	87%	84%	88%	77%	88%	82%	85%	87%	90%	82%	86%
63.5%		70%	72%	70%	67%	61%	67%	63%	58%	62%	43%	54%	69%	70%
68.8%		61%	70%	66%	60%	68%	69%	67%	75%	73%	74%	70%	67%	74%
79.5%		89%	89%	92%	89%	71%	83%	83%	91%	81%	55%	72%	68%	70%
87.7%		88%	87%	87%	89%	92%	89%	88%	85%	87%	82%	85%	85%	96%
85.2%		89%	92%	81%	94%	82%	86%	79%	77%	95%	68%	89%	86%	90%
85.2%		85%	82%	82%	82%	87%	84%	83%	89%	90%	75%	91%	88%	89%
77.5%		80%	73%	75%	78%	68%	77%	77%	82%	75%	86%	83%	80%	74%
85.0%		92%	95%	80%	91%	80%	86%	76%	79%	93%	71%	88%	85%	89%
90.7%		92%	93%	94%	86%	93%	80%	91%	95%	92%	84%	89%	92%	98%
70.5%		68%	74%	71%	88%	73%	76%	82%	80%	65%	62%	78%	50%	49%
66.8%		86%	80%	80%	88%	47%	69%	71%	78%	68%	50%	45%	50%	56%
84.9%		84%	85%	90%	85%	92%	83%	79%	92%	82%	86%	77%	86%	83%
84.7%		93%	83%	84%	85%	89%	87%	81%	82%	82%	91%	84%	84%	76%
87.0%		78%	82%	82%	92%	85%	86%	93%	81%	93%	88%	90%	94%	87%
80.3%		89%	80%	82%	79%	58%	82%	92%	74%	86%	86%	85%	75%	76%
85.2%		89%	95%	93%	86%	78%	91%	88%	83%	85%	83%	82%	75%	79%
79.8%		81%	86%	90%	88%	67%	75%	69%	73%	81%	81%	77%	84%	85%
83.2%		88%	88%	85%	90%	83%	88%	88%	85%	85%	68%	88%	78%	67%
82.0%		88%	64%	67%	85%	82%	87%	87%	78%	87%	84%	86%	90%	81%
80.6%		89%	80%	88%	95%	60%	78%	92%	79%	85%	80%	83%	71%	68%
72.2%		74%	79%	84%	97%	65%	67%	79%	80%	77%	51%	61%	62%	63%
78.4%		82%	73%	79%	82%	78%	82%	79%	76%	68%	69%	80%	83%	88%
77.1%		83%	77%	81%	84%	75%	78%	77%	82%	73%	65%	88%	75%	64%
82.0%		86%	72%	71%	79%	81%	85%	85%	79%	76%	87%	87%	89%	89%
85.7%		91%	89%	85%	88%	80%	75%	80%	90%	89%	92%	87%	85%	83%
84.0%		85%	88%	83%	92%	84%	88%	87%	89%	85%	70%	88%	86%	67%
75.2%		71%	62%	78%	69%	78%	64%	61%	74%	81%	92%	79%	84%	84%
85.8%		94%	92%	93%	82%	73%	88%	97%	98%	92%	65%	90%	68%	84%
85.9%		90%	92%	91%	83%	91%	91%	86%	80%	86%	90%	70%	81%	86%
73.0%		74%	73%	75%	62%	65%	73%	72%	69%	73%	86%	75%	72%	80%
76.0%		82%	84%	82%	79%	66%	83%	79%	78%	67%	77%	71%	73%	67%
86.7%		93%	92%	90%	79%	86%	87%	87%	85%	89%	87%	81%	85%	86%
83.4%		77%	90%	93%	81%	83%	88%	82%	90%	83%	58%	80%	90%	89%
80.2%		86%	82%	71%	89%	79%	78%	81%	77%	78%	85%	78%	79%	79%
86.5%		88%	89%	98%	84%	77%	87%	80%	85%	88%	77%	98%	90%	84%
88.6%		93%	90%	89%	72%	88%	83%	90%	95%	90%	90%	86%	95%	91%
87.5%		81%	88%	88%	90%	85%	90%	88%	92%	87%	82%	91%	87%	88%
87.4%		94%	88%	90%	89%	82%	95%	89%	84%	87%	81%	92%	79%	86%
67.1%		69%	72%	79%	29%	67%	66%	80%	82%	69%	67%	71%	62%	59%
76.6%		86%	79%	90%	90%	66%	65%	72%	62%	76%	81%	77%	82%	70%
64.6%		69%	63%	61%	88%	52%	61%	61%	65%	67%	68%	65%	60%	60%
85.0%		81%	92%	89%	66%	80%	86%	89%	86%	92%	84%	91%	87%	82%
85.5%		93%	84%	85%	77%	76%	91%	93%	83%	93%	87%	82%	79%	88%
56.2%		45%	68%	58%	66%	47%	67%	57%	66%	67%	49%	44%	43%	54%
86.9%		87%	90%	92%	77%	93%	83%	81%	83%	95%	70%	93%	92%	94%
66.5%		73%	77%	78%	88%	50%	70%	71%	77%	67%	54%	56%	46%	58%
82.3%		82%	86%	90%	82%	88%	88%	73%	79%	80%	80%	78%	83%	81%
81.5%		86%	91%	94%	87%	66%	89%	89%	89%	94%	64%	81%	65%	64%
70.8%		75%	68%	78%	77%	53%	67%	75%	74%	63%	74%	67%	76%	73%
87.6%		90%	95%	91%	86%	95%	91%	88%	95%	88%	68%	76%	93%	83%
84.2%		89%	75%	82%	91%	79%	83%	84%	85%	83%	85%	92%	85%	81%
73.2%		70%	76%	79%	87%	77%	78%	73%	79%	72%	64%	83%	58%	55%
89.3%		95%	94%	92%	79%	87%	93%	85%	94%	95%	84%	85%	88%	90%
80.0%		87%	81%	92%	84%	60%	80%	86%	88%	82%	81%	71%	74%	74%
79.7%		85%	86%	82%	76%	87%	75%	84%	70%	86%	72%	73%	69%	91%
81.5%		86%	76%	78%	81%	78%	82%	86%	81%	84%	82%	83%	78%	85%
83.6%		86%	84%	72%	70%	90%	87%	71%	73%	98%	90%	91%	86%	89%
91.5%		92%	98%	95%	90%	94%	92%	83%	92%	90%	88%	92%	91%	92%
81.7%		88%	88%	91%	71%	83%	84%	73%	87%	91%	80%	80%	76%	70%
88.5%		91%	92%	91%	87%	87%	84%	81%	92%	97%	90%	89%	87%	83%
78.2%		86%	83%	87%	85%	74%	81%	85%	83%	78%	62%	71%	68%	73%
81.8%		78%	81%	88%	80%	81%	82%	81%	83%	86%	83%	81%	78%	82%
82.5%		76%	89%	83%	77%	92%	82%	83%	66%	84%	86%	85%	82%	87%
86.7%		91%	91%	89%	89%	91%	85%	80%	89%	87%	77%	87%	86%	85%
84.8%		86%	81%	85%	86%	74%	81%	83%	84%	89%	85%	88%	89%	91%
80.5%		87%	74%	77%	88%	72%	74%	81%	86%	86%	81%	85%	78%	77%
85.5%		84%	90%	91%	81%	87%	87%	80%	85%	85%	78%	87%	90%	86%
87.8%		96%	87%	82%	86%	85%	88%	85%	87%	92%	92%	92%	82%	88%
90.5%		98%	90%	92%	96%	91%	90%	91%	95%	94%	71%	91%	88%	89%
79.0%		85%	84%	84%	63%	81%	85%	78%	82%	78%	79%	76%	71%	81%
89.9%		82%	88%	91%	95%	90%	81%	97%	91%	89%	91%	88%	88%	98%
83.8%		81%	91%	89%	77%	83%	91%	88%	87%	83%	80%	84%	83%	73%
80.5%		81%	75%	79%	83%	78%	79%	80%	86%	80%	83%	87%	77%	78%
79.8%		83%	85%	87%	78%	81%	79%	71%	70%	85%	70%	78%	84%	86%
77.4%		77%	75%	77%	82%	80%	74%	72%	86%	79%	71%	77%	76%	80%
75.8%		81%	87%	86%	90%	68%	72%	72%	78%	69%	47%	65%	81%	89%
76.1%		85%	76%	72%	76%	76%	76%	71%	70%	76%	83%	79%	77%	72%
74.4%		74%	71%	72%	71%	72%	81%	82%	68%	75%	82%	77%	73%	69%
73.0%		88%	84%	89%	83%	55%	68%	71%	77%	95%	57%	58%	62%	62%
76.8%		87%	65%	80%	83%	93%	67%	62%	73%	65%	56%	94%	87%	86%
86.6%		87%	87%	86%	91%	78%	92%	88%	85%	91%	72%	93%	85%	91%
68.2%		71%	77%	67%	66%	76%	72%	61%	64%	64%	65%	65%	69%	70%
82.9%		81%	78%	82%	83%	82%	84%	85%	83%	86%	79%	88%	90%	77%
86.6%		73%	91%	91%	75%	93%	85%	64%	90%	92%	92%	95%	92%	93%
86.8%		79%	93%	91%	66%	95%	95%	78%	82%	74%	94%	94%	90%	97%
77.8%		84%	88%	88%	90%	50%	82%	91%	93%	86%	60%	69%	60%	71%
81.8%		87%	92%	85%	88%	77%	77%	76%	89%	84%	68%	67%	83%	91%
77.8%		70%	85%	87%	83%	82%	82%	80%	86%	73%	66%	82%	62%	74%
82.1%		79%	84%	89%	89%	77%	83%	90%	74%	86%	59%	83%	87%	87%
88.6%		92%	91%	95%	84%	91%	84%	83%	83%	82%	92%	93%	93%	89%
78.3%		81%	76%	74%	76%	69%	80%	77%	81%	85%	82%	82%	77%	78%
87.1%		90%	84%	78%	83%	81%	92%	93%	86%	93%	77%	95%	87%	93%
83.5%		68%	73%	90%	78%	77%	92%	89%	97%	91%	87%	74%	76%	94%
70.1%		89%	55%	23%	92%	60%	73%	91%	85%	85%	47%	71%	66%	74%
66.0%		68%	62%	81%	80%	44%	65%	78%	85%	76%	46%	60%	55%	58%
76.1%		67%	80%	76%	87%	82%	80%	81%	67%	80%	59%	80%	75%	75%
83.8%		90%	80%	87%	76%	83%	87%	91%	89%	92%	90%	78%	73%	73%
87.2%		91%	80%	84%	74%	89%	89%	88%	90%	92%	81%	91%	93%	91%
82.5%		89%	85%	84%	96%	71%	81%	85%	80%	89%	82%	94%	72%	64%
88.4%		83%	93%	88%	96%	84%	90%	97%	92%	96%	90%	82%	82%	76%
77.2%		85%	83%	80%	91%	82%	10%	90%	87%	87%	56%	92%	88%	73%
91.9%		94%	94%	97%	97%	90%	93%	93%	97%	94%	88%	92%	84%	82%
81.3%		82%	79%	79%	82%	87%	81%	72%	81%	86%	78%	79%	84%	87%