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 AgeGroup%3A18 25 C10 - Run 140f727...

Global Dialogues GD4 - 18-25 (10 context Qs)

DTEF: Predict response distributions for 18-25. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Global Dialogues Gd4

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
83.2%
2.Claude Sonnet 4
83.1%
3.Claude Haiku 4.5
82.8%
4.GPT 4.1
82.2%
5.Gemini 2.5 Flash
81.8%

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		3rd 82.8%	2nd 83.1%	1st 83.2%	5th 81.8%	12th 78.0%	8th 80.8%	7th 81.1%	4th 82.2%	6th 81.6%	13th 77.0%	10th 79.3%	9th 79.8%	11th 78.2%
70.2%		73%	86%	90%	67%	53%	65%	76%	75%	59%	68%	58%	75%	67%
63.8%		65%	59%	65%	81%	42%	54%	71%	83%	69%	62%	64%	59%	56%
83.3%		79%	85%	90%	81%	86%	90%	82%	83%	89%	79%	82%	78%	79%
83.1%		87%	86%	86%	82%	86%	82%	79%	87%	86%	78%	81%	77%	83%
71.3%		77%	79%	74%	78%	68%	70%	70%	72%	66%	68%	69%	67%	69%
83.5%		87%	81%	94%	90%	78%	80%	81%	96%	83%	86%	93%	81%	55%
66.9%		86%	83%	85%	79%	61%	70%	60%	62%	50%	50%	55%	56%	73%
81.3%		73%	78%	62%	78%	86%	86%	84%	83%	87%	84%	86%	84%	86%
83.1%		75%	81%	81%	79%	88%	91%	81%	91%	94%	74%	83%	82%	80%
72.9%		58%	60%	63%	55%	82%	75%	60%	61%	85%	89%	86%	87%	87%
85.1%		86%	89%	88%	88%	77%	79%	87%	87%	82%	86%	88%	80%	89%
87.8%		92%	90%	90%	93%	92%	87%	85%	90%	93%	74%	93%	81%	82%
85.1%		89%	82%	90%	85%	84%	79%	85%	87%	88%	83%	87%	86%	81%
61.8%		69%	68%	61%	56%	57%	67%	54%	57%	57%	67%	53%	68%	69%
74.0%		62%	75%	75%	59%	74%	75%	68%	81%	83%	76%	82%	72%	80%
77.1%		81%	76%	86%	92%	70%	74%	83%	85%	85%	59%	75%	72%	64%
85.5%		85%	82%	93%	88%	88%	87%	80%	78%	88%	88%	83%	82%	89%
89.6%		90%	90%	96%	94%	86%	94%	91%	92%	93%	76%	73%	95%	95%
84.5%		83%	86%	86%	87%	84%	82%	84%	88%	84%	87%	87%	84%	76%
76.9%		79%	76%	76%	79%	70%	79%	75%	85%	70%	80%	78%	80%	73%
88.2%		94%	95%	98%	84%	81%	93%	94%	95%	84%	73%	72%	90%	93%
89.6%		90%	92%	84%	85%	96%	89%	93%	81%	84%	85%	96%	93%	97%
74.2%		71%	77%	85%	88%	76%	77%	84%	93%	69%	57%	70%	80%	37%
54.0%		63%	58%	59%	56%	43%	57%	60%	61%	50%	54%	43%	39%	59%
86.2%		90%	90%	88%	83%	87%	89%	81%	90%	84%	83%	78%	82%	96%
86.2%		95%	82%	87%	87%	91%	83%	82%	79%	87%	87%	87%	87%	87%
86.6%		96%	88%	90%	92%	77%	96%	79%	96%	79%	79%	80%	88%	86%
75.2%		81%	75%	79%	74%	55%	74%	84%	81%	77%	79%	77%	69%	72%
75.8%		83%	86%	82%	75%	69%	82%	81%	83%	79%	74%	64%	65%	63%
84.8%		84%	94%	90%	88%	82%	83%	83%	88%	82%	78%	75%	90%	85%
84.2%		89%	85%	88%	90%	83%	84%	85%	90%	85%	77%	89%	92%	57%
84.3%		89%	81%	86%	86%	78%	82%	87%	88%	86%	86%	89%	91%	67%
77.3%		82%	76%	89%	87%	66%	75%	77%	89%	82%	66%	75%	69%	72%
66.2%		70%	65%	68%	91%	64%	64%	78%	64%	66%	60%	61%	56%	54%
81.4%		86%	79%	82%	80%	80%	82%	86%	77%	72%	81%	84%	82%	87%
80.7%		82%	85%	86%	84%	83%	78%	83%	87%	82%	66%	88%	86%	59%
83.5%		90%	80%	77%	81%	80%	83%	85%	79%	82%	87%	87%	89%	85%
76.9%		82%	72%	67%	70%	88%	84%	82%	68%	75%	78%	88%	81%	65%
82.2%		85%	83%	82%	86%	82%	81%	86%	82%	82%	82%	84%	91%	62%
81.5%		91%	92%	90%	91%	86%	89%	10%	88%	91%	63%	91%	90%	88%
85.5%		92%	87%	89%	85%	82%	85%	94%	91%	86%	70%	87%	73%	91%
88.2%		83%	91%	95%	94%	96%	94%	93%	74%	96%	80%	77%	83%	91%
76.1%		76%	70%	81%	76%	70%	80%	81%	77%	73%	82%	74%	71%	78%
74.1%		79%	75%	73%	71%	70%	87%	86%	77%	69%	75%	71%	65%	65%
86.5%		89%	92%	94%	90%	86%	88%	77%	91%	79%	87%	78%	84%	90%
86.2%		89%	89%	85%	86%	74%	94%	86%	85%	90%	73%	85%	90%	94%
76.1%		82%	73%	69%	81%	82%	77%	77%	74%	75%	75%	76%	74%	74%
89.3%		90%	98%	94%	90%	80%	83%	90%	99%	89%	72%	98%	98%	80%
88.5%		87%	93%	85%	85%	95%	87%	95%	76%	94%	93%	87%	86%	88%
88.8%		93%	90%	90%	92%	90%	94%	94%	88%	92%	86%	83%	80%	82%
85.9%		93%	92%	88%	86%	82%	95%	94%	85%	89%	84%	80%	73%	76%
78.7%		70%	87%	89%	81%	69%	80%	92%	92%	77%	73%	67%	70%	76%
77.6%		85%	80%	85%	88%	74%	61%	84%	75%	81%	61%	77%	82%	76%
60.5%		67%	59%	64%	65%	59%	61%	67%	52%	59%	67%	58%	63%	46%
88.4%		90%	94%	93%	79%	87%	84%	88%	92%	89%	90%	89%	93%	81%
81.9%		82%	91%	91%	83%	75%	79%	87%	91%	82%	77%	77%	76%	74%
60.8%		56%	67%	61%	62%	51%	67%	76%	79%	60%	43%	54%	51%	63%
89.2%		91%	89%	92%	90%	93%	90%	83%	86%	89%	83%	91%	94%	89%
67.4%		70%	63%	78%	96%	53%	64%	74%	67%	75%	56%	57%	59%	64%
78.2%		81%	82%	84%	82%	93%	77%	70%	68%	75%	84%	67%	75%	79%
83.8%		82%	91%	92%	67%	83%	87%	83%	81%	97%	87%	83%	88%	69%
74.3%		80%	83%	82%	79%	61%	71%	75%	80%	62%	77%	66%	79%	71%
85.7%		86%	94%	86%	84%	96%	88%	90%	94%	86%	74%	73%	86%	77%
85.4%		88%	85%	86%	62%	88%	86%	83%	89%	82%	91%	91%	90%	89%
80.5%		76%	81%	87%	88%	80%	80%	84%	91%	77%	74%	91%	93%	44%
80.5%		84%	83%	79%	97%	72%	81%	93%	80%	84%	66%	80%	67%	80%
74.4%		86%	74%	79%	89%	57%	77%	86%	79%	76%	70%	60%	63%	71%
78.5%		92%	76%	72%	82%	86%	80%	73%	79%	87%	68%	78%	64%	84%
77.8%		78%	83%	84%	82%	80%	62%	76%	78%	83%	72%	88%	73%	72%
79.5%		79%	77%	79%	74%	83%	80%	65%	83%	87%	79%	84%	79%	85%
82.8%		72%	89%	76%	92%	78%	88%	80%	84%	81%	87%	78%	86%	85%
81.2%		88%	88%	79%	68%	84%	85%	76%	84%	89%	71%	82%	86%	76%
87.1%		86%	97%	87%	58%	92%	90%	85%	78%	93%	95%	95%	93%	83%
77.4%		84%	81%	83%	84%	70%	79%	88%	82%	74%	57%	79%	66%	79%
80.6%		76%	85%	80%	81%	84%	82%	80%	78%	82%	83%	77%	83%	77%
83.3%		76%	89%	87%	75%	88%	89%	75%	71%	86%	82%	89%	87%	89%
85.1%		85%	90%	88%	88%	86%	84%	83%	80%	78%	74%	87%	91%	92%
88.8%		93%	89%	91%	91%	77%	86%	90%	92%	89%	90%	87%	89%	91%
85.3%		86%	87%	88%	87%	80%	79%	84%	86%	87%	82%	86%	87%	90%
85.0%		90%	94%	85%	77%	87%	83%	84%	82%	85%	82%	83%	88%	85%
92.5%		88%	88%	92%	93%	99%	91%	92%	96%	98%	93%	89%	93%	90%
89.3%		94%	86%	90%	86%	86%	85%	92%	92%	96%	88%	93%	85%	88%
80.4%		84%	92%	87%	63%	86%	88%	85%	87%	83%	77%	72%	69%	72%
87.7%		88%	87%	87%	80%	91%	90%	92%	87%	89%	90%	83%	85%	91%
83.8%		90%	90%	78%	88%	81%	88%	85%	83%	89%	71%	87%	87%	72%
84.6%		86%	80%	87%	89%	86%	80%	83%	84%	79%	84%	88%	87%	87%
71.9%		73%	68%	68%	74%	76%	73%	68%	60%	76%	67%	76%	79%	77%
78.5%		82%	77%	78%	79%	81%	75%	74%	71%	81%	75%	83%	80%	84%
74.8%		72%	85%	85%	87%	61%	74%	76%	71%	72%	48%	66%	85%	90%
86.7%		90%	88%	91%	89%	81%	79%	85%	88%	93%	90%	79%	90%	84%
73.6%		69%	68%	74%	76%	65%	75%	78%	78%	75%	78%	78%	71%	72%
63.4%		92%	92%	93%	44%	41%	52%	61%	53%	67%	57%	47%	62%	63%
74.5%		90%	72%	76%	81%	72%	58%	73%	71%	55%	75%	71%	90%	84%
85.2%		91%	85%	85%	87%	75%	89%	90%	86%	91%	90%	82%	78%	79%
67.4%		65%	69%	67%	70%	80%	68%	67%	58%	59%	66%	68%	65%	74%
86.7%		87%	88%	87%	90%	82%	82%	90%	86%	91%	90%	79%	91%	84%
91.0%		90%	92%	90%	93%	96%	91%	86%	88%	88%	96%	86%	95%	92%
86.1%		80%	94%	82%	50%	90%	94%	90%	80%	84%	93%	92%	94%	96%
78.8%		77%	79%	90%	97%	59%	80%	84%	95%	81%	67%	72%	67%	77%
81.0%		86%	84%	73%	88%	79%	77%	79%	87%	86%	72%	72%	76%	94%
79.2%		72%	82%	84%	85%	82%	82%	80%	90%	82%	75%	75%	66%	75%
89.4%		89%	88%	88%	87%	89%	82%	92%	91%	91%	95%	98%	86%	86%
90.2%		92%	97%	98%	91%	83%	85%	87%	80%	85%	97%	86%	95%	96%
85.7%		89%	89%	85%	88%	66%	83%	82%	96%	90%	91%	95%	85%	75%
83.5%		88%	81%	82%	88%	76%	88%	91%	84%	85%	89%	82%	76%	75%
82.2%		93%	72%	88%	65%	67%	92%	79%	93%	94%	83%	69%	79%	94%
83.8%		95%	93%	97%	91%	65%	77%	95%	92%	87%	60%	79%	87%	71%
62.8%		59%	62%	68%	78%	36%	63%	66%	81%	66%	57%	70%	54%	57%
76.1%		61%	83%	66%	81%	85%	81%	64%	76%	77%	76%	76%	82%	81%
86.6%		93%	92%	90%	93%	86%	88%	88%	88%	95%	78%	85%	74%	76%
87.6%		89%	92%	92%	82%	91%	86%	89%	84%	81%	94%	78%	90%	91%
83.1%		92%	87%	88%	78%	75%	83%	87%	92%	87%	67%	90%	77%	77%
87.2%		82%	90%	87%	91%	83%	93%	92%	89%	89%	88%	85%	84%	80%
88.5%		90%	93%	90%	92%	94%	85%	88%	88%	89%	86%	90%	92%	74%
88.5%		87%	87%	86%	97%	83%	87%	94%	92%	97%	73%	97%	88%	83%
75.2%		74%	78%	61%	76%	86%	70%	68%	64%	81%	75%	81%	81%	83%