DTeval

Loading analysis results...

Please wait while we prepare the detailed comparison.

Loading blueprint versions...

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

Analysis: Gd6uk Dtef Global Dialogues Gd6uk AiConcern%3Aequally Concerned And Excited - Run 76e9f49...

Global Dialogues GD6UK - Equally concerned and excited

DTEF: Predict response distributions for Equally concerned and excited. Source: Global Dialogues GD6UK (https://github.com/collect-intel/global-dialogues)

TAGS:

PERIODIC

Dtef

Demographic

Global Dialogues Gd6uk

Instruction Following & Prompt Adherence

Data Privacy & Bodily Autonomy

AI Safety & Robustness

Social interaction

Best Models (Coverage)

1.Gemini 2.5 Flash
76.7%
2.Claude Haiku 4.5
75.7%
3.GPT 4.1 Mini
72.9%
4.Gemma 3 12b It
72.7%
5.GPT 4o Mini
72.3%

View Blueprint

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

	Claude Haiku 4.5	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	2nd 75.7%	1st 76.7%	4th 72.7%	3rd 72.9%	6th 69.4%	5th 72.3%
80.7%	74%	80%	83%	83%	79%	85%
81.2%	85%	75%	86%	78%	84%	79%
71.7%	71%	73%	83%	71%	59%	73%
78.0%	90%	78%	70%	82%	73%	75%
83.7%	85%	87%	86%	83%	75%	86%
80.7%	77%	78%	90%	80%	78%	81%
70.2%	60%	79%	56%	75%	73%	78%
46.5%	61%	59%	44%	32%	39%	44%
63.3%	53%	77%	52%	65%	74%	59%
85.2%	85%	87%	83%	89%	84%	83%
51.2%	52%	59%	55%	43%	59%	39%
68.3%	75%	70%	78%	61%	58%	68%
57.7%	62%	67%	46%	60%	51%	60%
73.5%	80%	87%	93%	69%	56%	56%
81.0%	81%	82%	68%	88%	78%	89%
69.0%	66%	71%	64%	72%	67%	74%
84.0%	86%	87%	72%	84%	88%	87%
80.5%	82%	70%	93%	78%	82%	78%
47.3%	48%	51%	39%	46%	61%	39%
58.0%	60%	62%	58%	63%	50%	55%
74.7%	70%	81%	75%	78%	74%	70%
79.5%	73%	81%	84%	79%	73%	87%
88.8%	96%	90%	92%	87%	81%	87%
78.8%	85%	68%	79%	90%	71%	80%
70.7%	70%	76%	70%	73%	61%	74%
69.3%	77%	68%	58%	75%	70%	68%
86.2%	85%	87%	84%	86%	88%	87%
74.7%	76%	72%	82%	69%	76%	73%
78.7%	87%	79%	73%	75%	74%	84%
71.3%	73%	68%	90%	67%	63%	67%
76.3%	71%	77%	74%	80%	82%	74%
83.8%	84%	76%	90%	88%	75%	90%
78.5%	90%	84%	78%	73%	63%	83%
91.0%	87%	98%	91%	92%	89%	89%
80.7%	72%	82%	71%	85%	86%	88%
78.5%	82%	83%	75%	77%	72%	82%
71.0%	68%	67%	79%	69%	76%	67%
73.0%	78%	79%	76%	73%	64%	68%
70.3%	65%	79%	61%	72%	72%	73%
74.0%	76%	78%	66%	77%	69%	78%
76.3%	88%	75%	78%	71%	72%	74%
82.7%	87%	89%	84%	84%	66%	86%
61.0%	69%	91%	52%	55%	59%	40%
70.7%	72%	74%	61%	69%	74%	74%
79.0%	76%	83%	82%	78%	75%	80%
77.5%	73%	77%	82%	83%	76%	74%
65.5%	71%	65%	59%	68%	68%	62%
80.8%	80%	78%	80%	80%	79%	88%
66.3%	66%	61%	74%	69%	63%	65%
85.3%	90%	90%	92%	82%	77%	81%
41.8%	35%	51%	31%	43%	49%	42%
78.0%	73%	81%	95%	68%	78%	73%
70.7%	72%	74%	91%	66%	52%	69%
76.8%	94%	92%	75%	60%	65%	75%
74.5%	87%	79%	75%	67%	58%	81%
66.2%	69%	70%	79%	66%	49%	64%
70.0%	87%	80%	78%	66%	47%	62%
86.2%	89%	79%	92%	86%	81%	90%
80.3%	73%	77%	85%	82%	83%	82%
71.0%	69%	64%	81%	71%	75%	66%
77.3%	82%	76%	82%	74%	66%	84%
51.3%	61%	59%	53%	53%	41%	41%
76.5%	79%	81%	80%	77%	68%	74%
81.2%	89%	89%	71%	82%	83%	73%
75.8%	81%	76%	78%	79%	68%	73%
52.0%	65%	86%	25%	56%	46%	34%
78.7%	78%	77%	81%	79%	78%	79%
77.8%	80%	81%	74%	79%	75%	78%
62.0%	69%	93%	40%	64%	47%	59%
75.5%	81%	87%	69%	72%	72%	72%
73.0%	69%	79%	68%	78%	66%	78%
85.5%	83%	82%	89%	86%	88%	85%
77.0%	84%	81%	70%	77%	74%	76%
78.2%	78%	91%	81%	74%	67%	78%
72.2%	80%	79%	86%	65%	61%	62%
81.2%	89%	89%	73%	82%	76%	78%
62.5%	70%	59%	72%	66%	55%	53%
74.3%	66%	81%	61%	77%	80%	81%
81.8%	96%	86%	48%	87%	87%	87%
74.0%	78%	75%	71%	76%	70%	74%
73.5%	81%	79%	69%	72%	69%	71%
61.8%	68%	62%	54%	62%	63%	62%
79.3%	84%	79%	77%	69%	80%	87%
82.3%	76%	85%	87%	76%	89%	81%
64.8%	78%	56%	75%	63%	62%	55%
76.5%	83%	76%	75%	77%	73%	75%
77.2%	77%	83%	78%	73%	70%	82%
76.0%	84%	83%	72%	70%	73%	74%
83.2%	90%	88%	78%	84%	75%	84%
62.7%	59%	59%	79%	62%	56%	61%
67.5%	66%	63%	58%	77%	74%	67%
47.8%	42%	54%	39%	57%	42%	53%