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%3Amore Concerned Than Excited - Run 5c843db...

Global Dialogues GD6UK - More concerned than excited

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

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
76.3%
2.Gemini 2.5 Flash
74.3%
3.GPT 4.1 Mini
72.7%
4.GPT 4o Mini
71.6%
5.Gemma 3 12b It
68.1%

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 76.3%	2nd 74.3%	5th 68.1%	3rd 72.7%	6th 65.1%	4th 71.6%
83.3%	90%	58%	91%	75%	90%	96%
81.8%	86%	62%	84%	91%	84%	84%
75.8%	81%	82%	74%	82%	54%	82%
76.3%	70%	82%	80%	73%	75%	78%
74.8%	84%	71%	67%	77%	73%	77%
83.0%	78%	86%	93%	87%	63%	91%
72.8%	69%	91%	54%	80%	78%	65%
61.5%	58%	70%	52%	59%	63%	67%
53.7%	54%	62%	40%	52%	62%	52%
74.0%	75%	75%	73%	80%	69%	72%
34.0%	37%	32%	43%	31%	31%	30%
70.8%	66%	83%	69%	85%	50%	72%
57.3%	65%	69%	40%	69%	46%	55%
85.8%	91%	92%	97%	83%	76%	76%
73.8%	68%	79%	58%	79%	82%	77%
61.6%	58%		52%	69%	67%	62%
86.0%	91%	90%	84%	79%	93%	79%
83.8%	90%	87%	90%	88%	54%	94%
50.0%	56%	71%	32%	57%	46%	38%
55.5%	61%	51%	78%	57%	43%	43%
70.7%	69%	76%	73%	75%	55%	76%
76.0%	69%	91%	83%	80%	59%	74%
88.0%	92%	76%	94%	88%	89%	89%
73.2%	98%	69%	71%	81%	63%	57%
70.0%	74%	61%	82%	64%	77%	62%
79.8%	82%	85%	73%	82%	81%	76%
72.7%	76%	54%	81%	77%	80%	68%
67.5%	75%	82%	66%	45%	64%	73%
71.3%	81%	58%	76%	68%	77%	68%
81.3%	81%	93%	95%	74%	75%	70%
83.7%	88%	90%	66%	86%	86%	86%
83.5%	94%	72%	94%	93%	54%	94%
81.2%	88%	86%	70%	83%	75%	85%
88.5%	92%	93%	76%	90%	89%	91%
77.8%	69%	77%	83%	76%	77%	85%
78.8%	87%	85%	73%	84%	51%	93%
69.2%	79%	65%	62%	73%	69%	67%
66.0%	75%	72%	63%	58%	69%	59%
62.5%	73%	56%	70%	65%	49%	62%
72.0%	76%	68%	77%	64%	71%	76%
78.2%	91%	90%	71%	77%	69%	71%
79.5%	90%	74%	76%	82%	73%	82%
56.8%	71%	91%	50%	45%	43%	41%
59.8%	74%	54%	48%	61%	61%	61%
73.7%	86%	57%	85%	79%	49%	86%
69.5%	76%	42%	75%	70%	75%	79%
63.2%	74%	69%	68%	68%	35%	65%
63.7%	58%	68%	72%	65%	55%	64%
61.7%	68%	65%	46%	68%	66%	57%
80.8%	90%	86%	76%	85%	72%	76%
50.8%	46%	79%	32%	42%	54%	52%
79.8%	78%	79%	79%	83%	75%	85%
80.3%	81%	86%	85%	75%	74%	81%
90.2%	89%	93%	82%	89%	90%	98%
75.7%	81%	88%	78%	66%	53%	88%
76.7%	81%	88%	90%	78%	43%	80%
71.8%	79%	82%	69%	80%	43%	78%
82.2%	87%	85%	85%	89%	59%	88%
75.2%	76%	69%	88%	67%	74%	77%
68.5%	72%	70%	61%	77%	65%	66%
82.2%	91%	89%	78%	79%	70%	86%
46.7%	61%	72%	10%	55%	41%	41%
70.0%	69%	67%	68%	77%	72%	67%
69.5%	71%	73%	56%	76%	80%	61%
74.5%	75%	74%	64%	80%	72%	82%
54.7%	67%	86%	29%	54%	53%	39%
73.3%	83%	57%	84%	79%	53%	84%
78.2%	76%	67%	84%	82%	80%	80%
61.3%	71%	84%	37%	65%	44%	67%
59.3%	73%	62%	43%	56%	66%	56%
78.0%	84%	78%	79%	88%	61%	78%
83.8%	89%	76%	78%	88%	89%	83%
77.5%	87%	72%	72%	83%	70%	81%
69.8%	73%	71%	72%	65%	66%	72%
75.2%	84%	95%	80%	69%	62%	61%
73.2%	86%	88%	65%	71%	63%	66%
67.7%	79%	81%	65%	73%	47%	61%
69.0%	71%	91%	67%	67%	51%	67%
67.2%	89%	65%	46%	71%	67%	65%
71.0%	75%	73%	72%	75%	60%	71%
62.5%	69%	70%	61%	59%	59%	57%
47.0%	61%	41%	37%	49%	54%	40%
67.7%	81%	78%	10%	72%	80%	85%
78.2%	80%	71%	77%	79%	76%	86%
57.5%	74%	42%	68%	52%	51%	58%
73.0%	80%	72%	72%	77%	61%	76%
74.7%	84%	80%	68%	79%	49%	88%
79.3%	80%	81%	75%	78%	77%	85%
76.2%	89%	63%	74%	77%	70%	84%
80.5%	76%	85%	83%	85%	74%	80%
62.7%	58%	72%	61%	71%	60%	54%
53.0%	38%	70%	36%	57%	70%	47%