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

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Metacognition and critical thinking

AI Safety & Robustness

General Knowledge

Best Models (Coverage)

1.Claude Haiku 4.5
76.7%
2.GPT 4.1 Mini
74.2%
3.Gemma 3 12b It
70.3%
4.Gemini 2.5 Flash
70.0%
5.GPT 4o Mini
69.9%

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 76.7%	4th 70.0%	3rd 70.3%	2nd 74.2%	6th 50.1%	5th 69.9%
66.5%	79%	48%	89%	71%	36%	76%
68.7%	83%	27%	80%	75%	79%	68%
77.2%	70%	85%	72%	83%	67%	86%
78.5%	85%	65%	74%	91%	76%	80%
72.3%	90%	74%	67%	78%	51%	74%
72.8%	86%	68%	88%	88%	37%	70%
69.3%	60%	50%	81%	72%	70%	83%
56.8%	45%	71%	53%	55%	55%	62%
43.3%	38%	68%	36%	40%	37%	41%
69.5%	75%	77%	70%	74%	56%	65%
38.8%	56%	49%	56%	27%	19%	26%
77.5%	73%	94%	80%	73%	83%	62%
69.0%	67%	78%	51%	65%	82%	71%
75.7%	92%	92%	89%	83%	8%	90%
75.8%	74%	68%	80%	85%	70%	78%
83.3%	93%	62%	84%	87%	86%	88%
68.0%	89%	89%	54%	84%	20%	72%
73.8%	94%	75%	87%	92%	7%	88%
40.0%	26%	81%	21%	40%	22%	50%
66.2%	77%	67%	90%	77%	43%	43%
65.2%	69%	79%	65%	73%	39%	66%
75.8%	79%	54%	83%	80%	83%	76%
66.7%	83%	83%	10%	85%	70%	69%
44.5%	0%	41%	58%	80%	35%	53%
65.0%	78%	44%	67%	64%	84%	53%
79.3%	83%	80%	67%	92%	81%	73%
65.2%	73%	53%	81%	76%	41%	67%
70.7%	75%	88%	78%	69%	41%	73%
62.0%	83%	53%	75%	75%	19%	67%
89.3%	89%	95%	93%	90%	86%	83%
79.5%	89%	52%	86%	96%	77%	77%
80.7%	90%	71%	92%	85%	59%	87%
80.8%	88%	90%	72%	90%	59%	86%
90.2%	92%	91%	86%	85%	93%	94%
54.5%	69%	38%	80%	57%	17%	66%
80.2%	94%	82%	72%	90%	57%	86%
63.7%	78%	68%	62%	70%	42%	62%
63.2%	81%	76%	68%	62%	38%	54%
57.8%	70%	27%	60%	64%	66%	60%
61.0%	75%	72%	75%	64%	16%	64%
77.8%	90%	90%	91%	78%	34%	84%
71.0%	87%	73%	63%	84%	44%	75%
71.2%	75%	91%	77%	63%	73%	48%
53.5%	67%	54%	43%	63%	38%	56%
58.2%	84%	26%	86%	67%	17%	69%
60.3%	80%	19%	70%	78%	48%	67%
64.0%	74%	78%	60%	80%	12%	80%
61.5%	74%	70%	71%	61%	38%	55%
51.0%	68%	66%	60%	51%	21%	40%
88.5%	88%	86%	90%	88%	87%	92%
60.5%	50%	79%	44%	63%	51%	76%
77.8%	84%	75%	76%	84%	77%	71%
82.7%	72%	89%	86%	81%	81%	87%
66.0%	66%	66%	66%	66%	66%	66%
81.0%	85%	83%	79%	78%	78%	83%
70.7%	86%	86%	85%	78%	9%	80%
74.7%	88%	88%	70%	64%	70%	68%
72.0%	87%	91%	84%	86%	6%	78%
71.2%	82%	41%	81%	83%	82%	58%
62.3%	78%	71%	61%	69%	34%	61%
78.3%	83%	88%	78%	93%	46%	82%
46.7%	66%	71%	18%	61%	13%	51%
68.8%	76%	75%	76%	78%	40%	68%
65.3%	89%	91%	76%	63%	25%	48%
83.2%	71%	82%	93%	83%	79%	91%
70.5%	70%	94%	41%	54%	94%	70%
63.5%	76%	33%	83%	75%	44%	70%
64.8%	85%	36%	83%	80%	25%	80%
68.7%	71%	83%	54%	69%	52%	83%
59.2%	81%	79%	53%	56%	43%	43%
71.3%	84%	70%	60%	92%	61%	61%
74.3%	89%	28%	82%	87%	78%	82%
65.2%	91%	62%	57%	81%	23%	77%
64.8%	72%	55%	82%	70%	63%	47%
72.3%	80%	82%	80%	75%	44%	73%
74.7%	86%	89%	72%	75%	60%	66%
81.0%	85%	91%	81%	88%	65%	76%
84.5%	83%	91%	93%	76%	73%	91%
55.0%	80%	65%	41%	65%	15%	64%
74.2%	70%	81%	75%	75%	63%	81%
64.3%	75%	68%	63%	62%	59%	59%
38.3%	50%	49%	37%	40%	18%	36%
81.0%	88%	77%	81%	83%	73%	84%
69.0%	78%	67%	83%	78%	45%	63%
51.3%	75%	50%	57%	53%	34%	39%
62.7%	79%	63%	60%	78%	19%	77%
76.3%	90%	77%	68%	84%	55%	84%
77.2%	76%	91%	71%	93%	36%	96%
62.3%	89%	63%	72%	75%	9%	66%
81.3%	82%	90%	74%	89%	66%	87%
77.7%	86%	65%	95%	83%	65%	72%
61.2%	42%	84%	57%	57%	50%	77%