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 C10 Dtef Global Dialogues Gd6uk AiConcern%3Amore Concerned Than Excited C10 - Run 5c843db...

Global Dialogues GD6UK - More concerned than excited (10 context Qs)

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

TAGS:

PERIODIC

Dtef

Demographic

Global Dialogues Gd6uk

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Metacognition and critical thinking

AI Safety & Robustness

Data Privacy & Bodily Autonomy

General Knowledge

Best Models (Coverage)

1.Claude Haiku 4.5
78.4%
2.GPT 4.1 Mini
74.2%
3.Gemini 2.5 Flash
73.8%
4.GPT 4o Mini
70.5%
5.Gemma 3 12b It
70.0%

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	1st 78.4%	3rd 73.8%	5th 70.0%	2nd 74.2%	6th 54.7%	4th 70.5%
63.3%	67%	48%	81%	66%	55%	63%
72.5%	83%	61%	87%	71%	71%	62%
77.0%	70%	88%	83%	83%	54%	84%
80.5%	85%	81%	76%	91%	71%	79%
67.8%	90%	78%	77%	78%	12%	72%
80.5%	86%	65%	84%	86%	86%	76%
71.0%	54%	77%	64%	74%	66%	91%
56.8%	46%	59%	49%	59%	57%	71%
78.5%	61%	87%	70%	81%	90%	82%
71.5%	70%	73%	73%	75%	76%	62%
44.0%	53%	33%	44%	27%	81%	26%
73.3%	71%	93%	79%	94%	34%	69%
60.8%	63%	76%	48%	65%	46%	67%
91.7%	96%	97%	91%	95%	85%	86%
77.8%	75%	73%	72%	85%	74%	88%
89.0%	90%	90%	93%	90%	81%	90%
72.3%	94%	89%	72%	75%	20%	84%
81.0%	92%	78%	77%	88%	58%	93%
62.3%	83%	86%	31%	60%	22%	92%
67.7%	84%	67%	88%	75%	61%	31%
66.8%	73%	87%	66%	76%	34%	65%
81.0%	88%	74%	89%	77%	91%	67%
80.7%	91%	87%	66%	80%	89%	71%
61.3%	73%	68%	69%	74%	35%	49%
61.7%	79%	12%	78%	64%	87%	50%
79.7%	88%	77%	66%	88%	81%	78%
60.2%	80%	50%	80%	67%	18%	66%
81.0%	75%	83%	88%	69%	88%	83%
67.0%	81%	39%	74%	69%	72%	67%
85.0%	71%	94%	90%	83%	86%	86%
80.0%	86%	62%	82%	95%	79%	76%
81.8%	94%	76%	78%	95%	61%	87%
68.3%	86%	77%	73%	84%	1%	89%
86.8%	92%	93%	72%	92%	93%	79%
68.7%	78%	56%	83%	58%	80%	57%
79.7%	88%	88%	72%	87%	57%	86%
66.2%	79%	69%	66%	79%	45%	59%
63.8%	80%	78%	69%	58%	55%	43%
54.0%	74%	46%	74%	61%	13%	56%
61.8%	80%	74%	73%	67%	13%	64%
76.3%	91%	94%	71%	84%	34%	84%
71.3%	87%	83%	78%	78%	25%	77%
74.2%	71%	91%	76%	48%	68%	91%
58.5%	68%	67%	55%	63%	42%	56%
66.2%	87%	26%	91%	76%	60%	57%
65.8%	74%	47%	63%	70%	63%	78%
65.7%	79%	78%	67%	78%	12%	80%
66.2%	72%	81%	72%	58%	55%	59%
47.7%	68%	59%	65%	48%	5%	41%
85.2%	90%	84%	75%	90%	80%	92%
53.5%	39%	93%	36%	49%	38%	66%
72.7%	84%	78%	78%	79%	46%	71%
79.0%	70%	82%	84%	81%	70%	87%
66.0%	66%	66%	66%	66%	66%	66%
75.8%	82%	83%	71%	70%	67%	82%
82.7%	84%	82%	86%	84%	76%	84%
72.8%	89%	88%	68%	70%	54%	68%
75.8%	87%	87%	68%	77%	67%	69%
76.5%	89%	63%	80%	83%	80%	64%
63.3%	75%	80%	61%	69%	34%	61%
73.0%	76%	83%	85%	87%	26%	81%
43.2%	61%	66%	18%	63%	0%	51%
70.7%	79%	86%	79%	75%	40%	65%
64.5%	82%	91%	70%	67%	25%	52%
84.0%	91%	88%	84%	89%	76%	76%
71.5%	74%	94%	36%	52%	94%	79%
58.3%	76%	28%	87%	81%	19%	59%
63.3%	84%	36%	86%	80%	25%	69%
64.0%	71%	82%	48%	66%	40%	77%
57.2%	83%	81%	65%	48%	24%	42%
73.5%	79%	73%	66%	88%	65%	70%
77.3%	87%	58%	76%	86%	83%	74%
65.0%	88%	75%	57%	77%	21%	72%
68.2%	85%	80%	73%	71%	53%	47%
77.3%	84%	91%	77%	78%	61%	73%
74.8%	85%	86%	73%	75%	64%	66%
72.3%	85%	90%	39%	81%	56%	83%
80.7%	83%	77%	93%	68%	72%	91%
63.2%	85%	75%	48%	71%	35%	65%
75.3%	78%	86%	69%	80%	69%	70%
66.2%	69%	68%	69%	69%	63%	59%
45.2%	61%	53%	40%	40%	42%	35%
67.7%	82%	74%	10%	84%	73%	83%
69.8%	80%	76%	77%	78%	45%	63%
46.2%	75%	51%	57%	54%	1%	39%
65.5%	85%	73%	60%	77%	26%	72%
76.7%	86%	84%	68%	82%	55%	85%
82.0%	76%	88%	72%	91%	78%	87%
78.0%	87%	61%	80%	85%	70%	85%
82.2%	76%	86%	82%	87%	75%	87%
82.2%	84%	72%	88%	80%	86%	83%
54.2%	36%	73%	46%	51%	51%	68%