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

Reasoning

Factual Accuracy & Hallucination

Metacognition and critical thinking

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
76.6%
2.GPT 4.1 Mini
74.2%
3.Gemini 2.5 Flash
70.2%
4.GPT 4o Mini
69.8%
5.Gemma 3 12b It
69.6%

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 70.2%	5th 69.6%	2nd 74.2%	6th 49.1%	4th 69.8%
71.0%	79%	47%	89%	71%	77%	63%
70.8%	83%	30%	81%	84%	88%	59%
79.0%	84%	88%	72%	82%	67%	81%
78.5%	85%	83%	75%	87%	62%	79%
69.8%	90%	70%	67%	78%	37%	77%
82.3%	86%	62%	91%	89%	85%	81%
65.0%	63%	47%	80%	75%	36%	89%
63.0%	44%	100%	53%	59%	55%	67%
45.0%	38%	77%	34%	43%	37%	41%
68.2%	75%	72%	69%	72%	56%	65%
40.0%	56%	57%	55%	27%	19%	26%
65.5%	71%	79%	80%	73%	21%	69%
71.8%	67%	80%	53%	65%	85%	81%
76.3%	91%	92%	91%	86%	8%	90%
78.2%	72%	72%	80%	85%	82%	78%
83.3%	84%	65%	84%	89%	90%	88%
68.7%	92%	81%	53%	94%	20%	72%
72.0%	94%	78%	84%	92%	2%	82%
51.5%	26%	85%	21%	53%	74%	50%
65.7%	77%	68%	92%	71%	43%	43%
65.5%	76%	79%	59%	74%	39%	66%
77.0%	79%	58%	83%	84%	82%	76%
67.3%	83%	81%	10%	85%	76%	69%
45.8%	0%	41%	58%	75%	35%	66%
56.0%	79%	24%	66%	68%	49%	50%
77.3%	83%	69%	67%	92%	78%	75%
64.8%	73%	54%	82%	71%	41%	68%
59.2%	75%	83%	10%	69%	45%	73%
61.8%	87%	47%	76%	75%	19%	67%
87.8%	89%	92%	93%	81%	86%	86%
81.0%	89%	62%	82%	96%	77%	80%
72.5%	91%	73%	89%	86%	9%	87%
79.3%	88%	89%	70%	86%	59%	84%
90.5%	89%	91%	87%	90%	93%	93%
56.0%	69%	38%	80%	66%	17%	66%
75.7%	79%	74%	71%	87%	57%	86%
62.5%	78%	61%	62%	70%	42%	62%
61.7%	81%	79%	68%	56%	38%	48%
51.5%	70%	41%	60%	61%	13%	64%
61.0%	75%	75%	69%	67%	16%	64%
76.3%	90%	91%	92%	78%	23%	84%
72.3%	87%	77%	63%	78%	48%	81%
78.3%	71%	91%	81%	63%	73%	91%
54.8%	67%	52%	43%	63%	48%	56%
63.3%	84%	26%	83%	74%	43%	70%
65.0%	80%	20%	70%	75%	69%	76%
64.5%	80%	79%	60%	77%	11%	80%
63.5%	74%	73%	72%	65%	38%	59%
43.8%	65%	49%	64%	45%	0%	40%
88.0%	88%	76%	90%	87%	95%	92%
58.2%	50%	79%	46%	59%	39%	76%
71.8%	84%	75%	76%	79%	46%	71%
83.7%	84%	91%	83%	81%	81%	82%
66.0%	66%	66%	66%	66%	66%	66%
81.5%	85%	83%	78%	70%	90%	83%
70.8%	86%	87%	85%	84%	3%	80%
75.5%	87%	86%	70%	72%	70%	68%
72.3%	87%	90%	91%	86%	12%	68%
69.0%	88%	34%	81%	83%	70%	58%
61.8%	78%	68%	54%	70%	37%	64%
72.0%	83%	89%	78%	86%	10%	86%
43.0%	66%	70%	18%	61%	13%	30%
69.5%	76%	76%	76%	79%	32%	78%
67.7%	91%	91%	75%	72%	25%	52%
81.3%	73%	90%	93%	80%	59%	93%
71.5%	73%	94%	39%	50%	94%	79%
62.5%	76%	28%	76%	75%	50%	70%
69.5%	84%	64%	84%	80%	25%	80%
68.5%	71%	82%	55%	68%	60%	75%
57.8%	81%	74%	53%	53%	43%	43%
72.5%	84%	75%	60%	94%	61%	61%
76.0%	89%	38%	82%	87%	78%	82%
63.3%	94%	55%	57%	74%	23%	77%
69.0%	74%	62%	84%	71%	63%	60%
74.2%	75%	94%	90%	69%	44%	73%
76.7%	88%	87%	72%	75%	72%	66%
77.7%	85%	78%	81%	81%	65%	76%
82.3%	83%	88%	93%	89%	73%	68%
55.3%	80%	64%	41%	71%	15%	61%
74.7%	70%	78%	75%	73%	71%	81%
66.7%	75%	76%	63%	64%	65%	57%
38.2%	50%	46%	39%	40%	18%	36%
68.3%	85%	80%	82%	80%	73%	10%
70.2%	80%	72%	83%	78%	45%	63%
52.2%	75%	58%	58%	58%	25%	39%
60.8%	81%	57%	60%	71%	19%	77%
72.7%	78%	69%	68%	82%	55%	84%
84.7%	77%	93%	71%	93%	83%	91%
61.7%	88%	58%	73%	76%	9%	66%
79.3%	82%	90%	74%	89%	54%	87%
78.8%	77%	74%	95%	79%	65%	83%
58.7%	35%	71%	57%	57%	50%	82%