DTeval

A Collective Intelligence Project

Loading blueprint versions...

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

Analysis: Gd4 C10 Dtef Global Dialogues Gd4 Gender%3Afemale C10 - Run dfcfea5...

Global Dialogues GD4 - Female (10 context Qs)

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

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Efficiency & Succinctness

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
84.7%
2.Claude Sonnet 4
84.2%
3.GPT 4.1
84.0%
4.Claude Haiku 4.5
83.6%
5.GPT 4.1 Mini
82.3%

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		4th 83.6%	2nd 84.2%	1st 84.8%	8th 80.8%	12th 78.6%	6th 82.0%	7th 81.3%	3rd 84.0%	5th 82.3%	13th 77.2%	9th 79.8%	11th 79.2%	10th 79.8%
67.7%		71%	72%	76%	68%	56%	62%	71%	66%	63%	71%	60%	76%	68%
64.5%		63%	66%	72%	81%	42%	57%	68%	89%	70%	56%	64%	55%	56%
80.6%		81%	75%	92%	56%	83%	87%	86%	88%	89%	79%	79%	76%	77%
85.1%		89%	89%	89%	84%	85%	84%	82%	89%	85%	80%	83%	82%	85%
65.8%		71%	73%	77%	74%	59%	63%	63%	68%	59%	64%	62%	57%	66%
81.3%		81%	78%	85%	91%	79%	77%	83%	89%	77%	81%	94%	83%	59%
70.6%		87%	81%	82%	74%	69%	72%	67%	61%	60%	76%	61%	64%	64%
81.2%		79%	74%	65%	68%	88%	88%	83%	85%	76%	90%	89%	91%	80%
83.4%		87%	80%	78%	78%	84%	89%	76%	90%	97%	89%	83%	81%	72%
72.8%		62%	72%	64%	27%	88%	76%	65%	67%	72%	93%	95%	87%	78%
82.1%		86%	80%	85%	84%	79%	82%	81%	85%	77%	78%	86%	80%	84%
89.1%		95%	95%	91%	93%	85%	85%	88%	96%	97%	74%	88%	86%	85%
86.2%		90%	86%	89%	86%	87%	82%	89%	83%	87%	87%	90%	84%	81%
63.0%		70%	69%	62%	71%	66%	67%	64%	57%	62%	52%	54%	55%	70%
72.5%		65%	79%	76%	64%	71%	69%	66%	81%	79%	77%	72%	68%	76%
79.7%		88%	87%	88%	92%	70%	83%	87%	91%	81%	52%	85%	68%	64%
86.7%		88%	83%	88%	91%	92%	89%	88%	82%	86%	88%	80%	83%	89%
89.9%		93%	97%	96%	94%	84%	94%	94%	94%	94%	70%	79%	88%	92%
86.4%		81%	89%	93%	87%	82%	85%	81%	88%	89%	84%	90%	84%	90%
75.5%		80%	75%	75%	74%	68%	77%	73%	74%	73%	80%	80%	79%	73%
87.7%		94%	90%	93%	91%	78%	97%	91%	91%	87%	74%	76%	87%	91%
89.3%		93%	92%	83%	91%	91%	83%	92%	84%	92%	94%	84%	84%	98%
73.8%		71%	74%	79%	88%	79%	76%	83%	86%	62%	79%	79%	54%	49%
66.2%		80%	80%	80%	90%	48%	70%	74%	72%	52%	55%	45%	50%	64%
85.6%		83%	85%	90%	85%	90%	89%	80%	92%	82%	84%	78%	82%	93%
89.9%		91%	94%	96%	91%	93%	83%	91%	84%	82%	91%	91%	91%	91%
87.7%		89%	96%	95%	89%	83%	95%	82%	92%	85%	86%	80%	83%	85%
79.9%		89%	80%	81%	86%	60%	82%	89%	82%	82%	79%	77%	75%	77%
86.1%		91%	93%	93%	90%	80%	91%	90%	91%	87%	83%	76%	74%	80%
82.4%		83%	87%	89%	88%	72%	81%	81%	84%	77%	81%	83%	81%	84%
83.7%		85%	89%	87%	88%	88%	87%	80%	89%	85%	68%	89%	85%	68%
84.9%		88%	81%	79%	80%	84%	84%	86%	86%	86%	87%	87%	90%	86%
76.9%		82%	80%	93%	88%	66%	78%	81%	84%	81%	73%	67%	63%	64%
74.2%		73%	79%	88%	95%	68%	80%	79%	83%	75%	59%	62%	57%	66%
79.5%		74%	85%	88%	83%	78%	82%	80%	66%	69%	80%	78%	82%	88%
78.1%		82%	84%	86%	82%	81%	78%	74%	86%	77%	65%	81%	84%	55%
81.4%		89%	75%	76%	75%	80%	78%	83%	84%	74%	87%	84%	88%	85%
80.2%		91%	88%	83%	90%	81%	83%	10%	88%	90%	84%	82%	85%	88%
82.8%		87%	89%	85%	89%	88%	86%	88%	92%	87%	66%	87%	70%	63%
77.4%		76%	72%	78%	83%	80%	62%	67%	73%	83%	87%	80%	81%	84%
87.2%		91%	93%	94%	86%	73%	89%	94%	95%	94%	69%	87%	75%	94%
87.4%		90%	92%	93%	83%	92%	90%	86%	83%	90%	92%	76%	83%	86%
73.5%		74%	76%	73%	71%	64%	73%	76%	75%	75%	75%	75%	73%	76%
78.4%		75%	82%	82%	82%	75%	84%	82%	86%	72%	79%	76%	76%	68%
85.5%		90%	92%	92%	81%	86%	89%	83%	84%	81%	90%	72%	86%	86%
83.2%		81%	90%	82%	83%	73%	89%	86%	85%	89%	71%	79%	83%	90%
78.7%		93%	85%	74%	84%	82%	78%	80%	80%	79%	56%	74%	79%	79%
88.7%		94%	94%	94%	80%	77%	87%	89%	93%	93%	80%	98%	90%	84%
86.7%		89%	90%	81%	77%	87%	90%	93%	86%	90%	81%	86%	86%	91%
89.9%		92%	88%	88%	91%	96%	90%	87%	92%	90%	88%	93%	84%	90%
88.5%		94%	93%	91%	95%	81%	93%	89%	90%	91%	84%	83%	81%	85%
71.1%		72%	84%	83%	29%	72%	88%	86%	75%	66%	68%	62%	62%	77%
76.2%		83%	81%	84%	81%	78%	65%	80%	71%	77%	63%	73%	79%	76%
69.1%		73%	70%	66%	89%	59%	69%	78%	72%	68%	67%	65%	63%	59%
87.1%		81%	92%	90%	80%	81%	88%	87%	88%	88%	89%	92%	92%	84%
84.5%		85%	92%	91%	85%	76%	82%	89%	89%	85%	80%	79%	81%	84%
62.9%		51%	74%	66%	77%	48%	60%	80%	82%	70%	41%	58%	50%	61%
90.0%		94%	91%	92%	92%	94%	88%	81%	88%	96%	81%	93%	87%	93%
69.2%		78%	74%	81%	92%	54%	70%	71%	78%	67%	52%	71%	54%	57%
84.6%		81%	85%	90%	86%	91%	85%	75%	84%	84%	86%	83%	83%	87%
82.2%		86%	91%	91%	53%	82%	89%	91%	94%	90%	69%	81%	87%	64%
75.0%		78%	79%	81%	79%	70%	71%	76%	77%	68%	74%	73%	78%	71%
85.6%		86%	92%	88%	83%	92%	83%	89%	93%	88%	66%	75%	93%	85%
86.4%		89%	81%	80%	89%	88%	87%	86%	88%	89%	77%	92%	88%	89%
76.8%		78%	83%	80%	81%	81%	78%	74%	82%	78%	81%	88%	62%	52%
87.8%		93%	91%	97%	84%	82%	91%	85%	89%	94%	80%	87%	74%	95%
79.4%		93%	80%	86%	87%	62%	83%	85%	81%	86%	74%	67%	71%	77%
79.2%		84%	76%	82%	73%	86%	76%	82%	74%	82%	65%	74%	84%	92%
81.8%		81%	82%	79%	86%	83%	85%	81%	84%	81%	81%	77%	79%	84%
83.3%		86%	83%	78%	76%	91%	86%	71%	72%	89%	86%	90%	86%	89%
91.2%		92%	98%	94%	87%	96%	93%	86%	94%	90%	87%	92%	85%	92%
81.5%		86%	88%	88%	66%	80%	83%	80%	89%	84%	81%	83%	85%	67%
88.2%		92%	92%	90%	67%	86%	84%	92%	95%	97%	93%	88%	89%	82%
79.1%		86%	84%	85%	84%	63%	87%	93%	82%	78%	67%	71%	68%	80%
82.1%		83%	88%	87%	79%	84%	82%	80%	83%	81%	81%	75%	82%	82%
80.7%		76%	91%	83%	62%	92%	82%	76%	71%	84%	81%	81%	82%	88%
87.4%		91%	89%	89%	78%	91%	85%	90%	92%	86%	78%	87%	91%	89%
87.1%		89%	85%	87%	91%	77%	85%	90%	88%	89%	85%	83%	89%	94%
81.8%		87%	77%	83%	88%	81%	77%	81%	85%	76%	76%	85%	80%	88%
86.2%		84%	94%	87%	84%	84%	89%	86%	85%	89%	78%	88%	88%	85%
90.5%		92%	87%	92%	84%	91%	92%	85%	93%	98%	94%	98%	82%	88%
90.4%		95%	91%	94%	89%	91%	89%	89%	93%	90%	81%	92%	88%	93%
80.9%		84%	88%	84%	70%	81%	82%	79%	85%	82%	80%	80%	79%	78%
91.2%		94%	91%	95%	90%	90%	87%	95%	96%	89%	96%	88%	82%	93%
85.6%		89%	90%	88%	83%	84%	90%	87%	89%	89%	82%	84%	83%	75%
82.9%		84%	81%	84%	85%	88%	78%	81%	84%	80%	80%	86%	82%	85%
80.2%		83%	84%	84%	76%	73%	80%	70%	74%	85%	73%	86%	88%	86%
77.8%		81%	75%	77%	77%	80%	74%	70%	82%	81%	73%	86%	77%	78%
78.4%		81%	91%	88%	91%	87%	78%	73%	73%	69%	46%	74%	77%	91%
83.2%		90%	94%	92%	71%	66%	85%	80%	87%	90%	72%	72%	95%	88%
73.7%		72%	70%	70%	84%	66%	83%	79%	71%	72%	78%	77%	69%	67%
69.1%		79%	93%	92%	82%	47%	69%	63%	72%	62%	57%	57%	63%	62%
67.1%		84%	63%	80%	44%	63%	61%	61%	61%	61%	55%	66%	93%	80%
87.8%		91%	86%	85%	95%	75%	88%	93%	91%	91%	90%	85%	86%	85%
70.2%		71%	80%	67%	65%	76%	71%	68%	68%	68%	65%	65%	69%	79%
84.2%		83%	78%	82%	81%	86%	83%	85%	87%	90%	84%	88%	89%	78%
87.7%		84%	91%	90%	79%	94%	79%	72%	90%	94%	91%	94%	92%	90%
86.8%		75%	95%	87%	63%	95%	95%	79%	79%	89%	95%	92%	91%	94%
78.2%		84%	89%	94%	86%	55%	83%	84%	95%	87%	58%	67%	62%	72%
82.5%		90%	87%	85%	88%	81%	75%	77%	88%	89%	67%	72%	86%	88%
74.8%		75%	85%	87%	23%	79%	83%	88%	93%	74%	70%	79%	62%	74%
90.5%		93%	92%	88%	89%	92%	84%	92%	91%	94%	92%	94%	91%	85%
85.8%		83%	92%	96%	87%	90%	84%	86%	67%	83%	92%	77%	90%	89%
79.6%		81%	76%	76%	73%	69%	81%	84%	90%	82%	88%	80%	76%	79%
87.2%		90%	84%	84%	85%	81%	89%	86%	90%	90%	95%	95%	82%	83%
82.3%		73%	74%	78%	68%	71%	95%	88%	96%	91%	96%	64%	85%	91%
82.2%		89%	86%	96%	94%	64%	85%	94%	96%	86%	66%	71%	77%	65%
64.7%		61%	64%	78%	72%	47%	64%	66%	83%	72%	58%	62%	55%	59%
79.9%		76%	76%	76%	94%	87%	82%	70%	77%	82%	80%	77%	82%	80%
84.5%		91%	81%	92%	83%	86%	88%	90%	92%	85%	78%	78%	83%	71%
86.5%		90%	86%	86%	81%	91%	92%	92%	89%	81%	81%	76%	93%	87%
86.5%		90%	85%	87%	93%	87%	81%	92%	81%	97%	76%	96%	76%	83%
91.1%		82%	93%	90%	95%	84%	94%	97%	97%	98%	91%	92%	88%	83%
86.8%		89%	84%	83%	91%	89%	83%	88%	88%	92%	88%	92%	89%	73%
89.7%		94%	97%	98%	97%	68%	93%	93%	99%	92%	75%	86%	85%	89%
80.5%		81%	78%	79%	87%	88%	78%	75%	75%	84%	73%	80%	79%	90%