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 C5 Dtef Global Dialogues Gd6uk AiConcern%3Amore Concerned Than Excited C5 - Run 5c843db...

Global Dialogues GD6UK - More concerned than excited (5 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

Factual Accuracy & Hallucination

Reasoning

Instruction Following & Prompt Adherence

Epistemic Humility & Self Awareness

AI Safety & Robustness

Data Privacy & Bodily Autonomy

Economic Disruption & Reskilling Advice

Public Sector & Governance

Best Models (Coverage)

1.Claude Haiku 4.5
76.6%
2.GPT 4.1 Mini
74.4%
3.Gemini 2.5 Flash
70.5%
4.GPT 4o Mini
70.3%
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 76.6%	3rd 70.5%	5th 70.0%	2nd 74.4%	6th 46.4%	4th 70.3%
69.2%	79%	40%	89%	66%	77%	64%
71.7%	83%	52%	81%	75%	77%	62%
78.7%	84%	88%	72%	82%	59%	87%
78.2%	85%	85%	75%	80%	66%	78%
70.2%	90%	69%	67%	78%	40%	77%
75.3%	86%	68%	83%	89%	62%	64%
64.0%	60%	36%	76%	85%	36%	91%
57.3%	44%	73%	53%	59%	51%	64%
45.2%	38%	76%	37%	42%	37%	41%
69.5%	75%	76%	71%	74%	56%	65%
42.5%	56%	64%	55%	31%	19%	30%
69.8%	79%	79%	80%	81%	21%	79%
70.2%	67%	80%	50%	65%	82%	77%
78.5%	97%	97%	91%	83%	8%	95%
77.0%	70%	68%	80%	85%	81%	78%
84.3%	92%	63%	84%	89%	90%	88%
67.2%	92%	84%	54%	88%	20%	65%
75.3%	94%	71%	83%	92%	35%	77%
55.5%	27%	78%	22%	68%	74%	64%
65.7%	77%	67%	94%	73%	41%	42%
66.2%	73%	82%	65%	72%	39%	66%
75.2%	78%	53%	83%	84%	77%	76%
66.7%	83%	83%	10%	85%	70%	69%
52.7%	0%	74%	57%	80%	35%	70%
51.2%	75%	20%	66%	63%	42%	41%
77.8%	83%	71%	66%	88%	82%	77%
60.5%	73%	54%	80%	71%	18%	67%
74.8%	75%	76%	78%	69%	78%	73%
57.8%	83%	27%	76%	75%	19%	67%
87.0%	81%	93%	93%	83%	86%	86%
82.3%	95%	56%	79%	96%	83%	85%
76.2%	91%	68%	89%	85%	38%	86%
79.8%	88%	93%	72%	86%	54%	86%
91.0%	92%	99%	87%	85%	89%	94%
54.7%	69%	38%	80%	66%	17%	58%
66.7%	79%	83%	72%	87%	6%	73%
63.7%	78%	68%	62%	70%	42%	62%
58.0%	78%	74%	68%	54%	20%	54%
63.0%	70%	64%	60%	64%	60%	60%
61.3%	75%	72%	74%	67%	16%	64%
77.7%	91%	90%	92%	78%	31%	84%
66.7%	87%	73%	63%	77%	20%	80%
77.7%	75%	91%	80%	56%	73%	91%
54.0%	68%	55%	44%	63%	38%	56%
59.3%	85%	26%	85%	74%	17%	69%
64.3%	80%	19%	70%	78%	60%	79%
65.2%	74%	80%	64%	80%	13%	80%
63.0%	70%	65%	72%	72%	44%	55%
45.0%	68%	54%	63%	45%	0%	40%
86.7%	88%	81%	90%	87%	88%	86%
61.2%	50%	79%	43%	66%	58%	71%
71.8%	85%	75%	76%	84%	46%	65%
83.3%	84%	92%	86%	81%	76%	81%
66.0%	66%	66%	66%	66%	66%	66%
82.0%	85%	87%	78%	70%	89%	83%
72.3%	86%	90%	85%	84%	9%	80%
73.7%	89%	80%	70%	65%	70%	68%
73.2%	87%	87%	91%	89%	12%	73%
63.8%	81%	41%	82%	81%	40%	58%
62.8%	78%	68%	54%	70%	43%	64%
73.5%	83%	89%	78%	87%	19%	85%
44.3%	66%	70%	18%	61%	0%	51%
68.8%	75%	83%	76%	74%	32%	73%
63.2%	89%	86%	75%	63%	15%	51%
77.3%	70%	91%	72%	83%	70%	78%
72.5%	74%	94%	41%	62%	94%	70%
67.7%	72%	28%	78%	76%	82%	70%
70.3%	85%	65%	83%	84%	25%	80%
66.7%	71%	83%	57%	68%	42%	79%
53.8%	80%	71%	53%	56%	24%	39%
70.3%	84%	68%	60%	92%	53%	65%
75.0%	89%	38%	82%	87%	72%	82%
62.8%	93%	58%	57%	74%	23%	72%
64.0%	74%	66%	86%	65%	45%	48%
69.7%	75%	90%	80%	72%	29%	72%
77.7%	86%	95%	72%	75%	72%	66%
73.0%	85%	78%	81%	79%	39%	76%
79.7%	83%	93%	93%	85%	33%	91%
55.2%	79%	64%	41%	66%	15%	66%
74.0%	70%	76%	75%	79%	63%	81%
66.2%	75%	75%	63%	70%	52%	62%
38.8%	50%	42%	37%	40%	29%	35%
80.7%	87%	75%	81%	81%	74%	86%
69.3%	80%	67%	83%	78%	45%	63%
51.5%	75%	49%	57%	54%	35%	39%
60.2%	80%	60%	60%	71%	19%	71%
63.3%	78%	78%	68%	82%	4%	70%
85.3%	77%	95%	71%	93%	85%	91%
62.3%	88%	54%	72%	76%	10%	74%
78.5%	82%	87%	72%	89%	59%	82%
79.0%	77%	65%	95%	89%	65%	83%
62.3%	42%	93%	57%	50%	50%	82%