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

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

General Knowledge

Best Models (Coverage)

1.Claude Haiku 4.5
76.5%
2.Gemini 2.5 Flash
74.2%
3.GPT 4.1 Mini
73.0%
4.GPT 4o Mini
71.8%
5.Gemma 3 12b It
68.0%

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 76.5%	2nd 74.2%	5th 68.0%	3rd 73.0%	6th 66.6%	4th 71.8%
81.5%	91%	60%	91%	76%	75%	96%
80.8%	88%	62%	84%	84%	81%	86%
77.7%	81%	82%	74%	73%	74%	82%
79.2%	80%	82%	80%	83%	72%	78%
75.5%	84%	71%	67%	80%	79%	72%
82.7%	77%	86%	90%	86%	66%	91%
70.0%	69%	85%	54%	75%	72%	65%
60.8%	58%	62%	54%	63%	61%	67%
54.7%	49%	62%	43%	66%	63%	45%
75.0%	77%	74%	73%	76%	74%	76%
35.5%	40%	32%	44%	31%	31%	35%
69.5%	66%	83%	68%	80%	48%	72%
57.5%	65%	77%	40%	65%	43%	55%
86.5%	96%	92%	97%	82%	76%	76%
73.8%	68%	79%	58%	79%	82%	77%
65.5%	66%	68%	51%	70%	69%	69%
85.0%	91%	92%	84%	80%	85%	78%
88.2%	90%	83%	89%	88%	86%	93%
57.2%	55%	84%	32%	66%	55%	51%
55.8%	54%	51%	78%	67%	43%	42%
69.8%	69%	76%	76%	75%	52%	71%
74.2%	68%	91%	83%	76%	53%	74%
85.0%	92%	66%	88%	91%	89%	84%
73.5%	98%	63%	71%	79%	63%	67%
67.3%	74%	51%	82%	68%	67%	62%
80.8%	88%	85%	73%	82%	76%	81%
76.0%	76%	63%	81%	76%	80%	80%
72.8%	75%	78%	66%	63%	82%	73%
73.7%	86%	62%	77%	68%	77%	72%
80.7%	81%	95%	89%	74%	75%	70%
82.8%	88%	90%	66%	86%	81%	86%
83.8%	94%	72%	94%	93%	55%	95%
81.3%	88%	84%	70%	83%	75%	88%
88.2%	92%	93%	76%	90%	88%	90%
77.3%	70%	77%	81%	80%	78%	78%
78.8%	88%	85%	73%	84%	57%	86%
69.2%	79%	65%	62%	79%	68%	62%
66.0%	75%	71%	63%	63%	69%	55%
60.8%	73%	46%	70%	65%	49%	62%
70.0%	76%	68%	77%	64%	71%	64%
78.7%	91%	90%	72%	77%	71%	71%
78.8%	89%	74%	76%	82%	70%	82%
57.0%	71%	91%	50%	37%	45%	48%
59.2%	74%	53%	48%	61%	60%	59%
75.7%	86%	58%	85%	85%	54%	86%
68.2%	75%	43%	73%	70%	69%	79%
65.8%	69%	70%	68%	67%	56%	65%
62.3%	58%	68%	72%	62%	55%	59%
60.8%	68%	65%	46%	68%	66%	52%
80.3%	90%	85%	76%	83%	72%	76%
50.8%	41%	80%	32%	42%	51%	59%
80.5%	78%	76%	79%	82%	83%	85%
80.7%	80%	88%	85%	75%	74%	82%
89.3%	89%	90%	82%	90%	87%	98%
74.8%	81%	88%	78%	66%	53%	83%
74.8%	81%	88%	90%	78%	40%	72%
74.0%	82%	82%	69%	78%	55%	78%
87.0%	88%	85%	85%	89%	87%	88%
77.0%	83%	67%	88%	68%	77%	79%
67.5%	72%	65%	61%	74%	68%	65%
82.5%	91%	89%	78%	79%	72%	86%
46.7%	61%	66%	10%	61%	41%	41%
71.7%	69%	71%	69%	80%	72%	69%
70.2%	71%	72%	58%	76%	83%	61%
75.0%	78%	77%	64%	77%	72%	82%
55.3%	62%	96%	29%	54%	52%	39%
74.0%	83%	57%	84%	83%	53%	84%
80.7%	80%	77%	84%	82%	80%	81%
62.2%	71%	89%	37%	64%	46%	66%
60.0%	73%	62%	43%	57%	69%	56%
77.7%	84%	78%	79%	83%	60%	82%
82.5%	89%	77%	83%	83%	84%	79%
76.7%	89%	68%	72%	74%	77%	80%
69.8%	72%	67%	72%	65%	71%	72%
74.2%	84%	90%	80%	69%	61%	61%
74.8%	86%	92%	65%	74%	66%	66%
68.5%	79%	81%	65%	73%	48%	65%
70.0%	71%	95%	68%	67%	52%	67%
66.3%	80%	65%	46%	71%	65%	71%
72.7%	75%	73%	72%	80%	60%	76%
63.2%	68%	70%	61%	59%	58%	63%
45.5%	61%	42%	37%	49%	41%	43%
65.8%	81%	70%	10%	68%	79%	87%
79.0%	80%	71%	78%	79%	80%	86%
61.3%	74%	45%	68%	52%	71%	58%
72.0%	82%	68%	72%	71%	67%	72%
74.7%	84%	80%	68%	79%	55%	82%
80.7%	81%	86%	75%	75%	83%	84%
77.5%	87%	63%	74%	77%	76%	88%
80.3%	76%	85%	83%	85%	71%	82%
61.3%	58%	71%	53%	71%	61%	54%
52.8%	37%	75%	36%	57%	65%	47%