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 Excited Than Concerned - Run 76e44f9...

Global Dialogues GD6UK - More excited than concerned

DTEF: Predict response distributions for More excited than concerned. 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

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
76.3%
2.Gemini 2.5 Flash
76.1%
3.GPT 4.1 Mini
74.8%
4.Gemma 3 12b It
72.6%
5.GPT 4o Mini
71.6%

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 76.3%	2nd 76.1%	4th 72.6%	3rd 74.8%	6th 69.0%	5th 71.6%
82.5%	77%	81%	85%	85%	82%	85%
78.0%	77%	77%	84%	74%	79%	77%
66.3%	71%	72%	77%	64%	50%	64%
70.8%	85%	77%	58%	78%	55%	72%
77.0%	84%	85%	87%	73%	61%	72%
77.5%	75%	80%	79%	75%	76%	80%
68.8%	60%	77%	55%	73%	74%	74%
62.3%	66%	72%	85%	55%	41%	55%
63.0%	61%	70%	58%	64%	63%	62%
76.3%	85%	77%	65%	72%	81%	78%
58.3%	60%	61%	62%	49%	64%	54%
70.5%	80%	87%	83%	62%	47%	64%
68.3%	71%	85%	52%	67%	65%	70%
85.5%	92%	96%	95%	76%	78%	76%
81.0%	72%	84%	72%	87%	83%	88%
72.5%	74%	74%	69%	75%	74%	69%
80.0%	79%	78%	75%	87%	73%	88%
78.3%	85%	54%	83%	84%	82%	82%
56.0%	55%	55%	48%	55%	72%	51%
63.8%	68%	69%	71%	71%	35%	69%
80.8%	76%	82%	79%	90%	75%	83%
85.8%	87%	83%	88%	85%	83%	89%
80.2%	79%	86%	85%	79%	73%	79%
70.0%	77%	31%	79%	85%	72%	76%
71.3%	74%	83%	68%	82%	41%	80%
69.0%	74%	65%	69%	69%	69%	68%
84.3%	84%	85%	84%	92%	74%	87%
68.3%	61%	64%	69%	64%	88%	64%
84.3%	85%	73%	88%	85%	88%	87%
76.2%	65%	80%	92%	79%	66%	75%
75.7%	80%	79%	91%	68%	73%	63%
82.2%	87%	70%	83%	84%	86%	83%
70.2%	77%	73%	81%	77%	50%	63%
88.2%	87%	81%	91%	87%	92%	91%
82.8%	80%	77%	83%	89%	82%	86%
74.2%	82%	76%	72%	76%	66%	73%
66.2%	69%	60%	61%	71%	75%	61%
73.8%	80%	74%	77%	72%	69%	71%
78.8%	81%	84%	65%	83%	77%	83%
71.0%	70%	64%	70%	76%	75%	71%
79.2%	83%	76%	87%	76%	77%	76%
78.7%	84%	84%	86%	78%	65%	75%
60.8%	70%	91%	45%	55%	60%	44%
71.2%	73%	63%	61%	80%	84%	66%
80.5%	81%	84%	80%	82%	77%	79%
80.5%	82%	88%	74%	83%	78%	78%
63.0%	66%	74%	57%	71%	51%	59%
89.2%	90%	92%	91%	76%	93%	93%
72.8%	75%	70%	80%	77%	67%	68%
80.8%	78%	79%	83%	83%	81%	81%
39.8%	40%	59%	25%	38%	39%	38%
76.0%	76%	67%	90%	75%	72%	76%
65.3%	74%	73%	76%	67%	45%	57%
82.8%	94%	93%	81%	82%	65%	82%
80.7%	85%	87%	86%	76%	57%	93%
67.2%	83%	65%	79%	77%	49%	50%
76.0%	87%	82%	70%	79%	70%	68%
82.7%	89%	75%	81%	85%	90%	76%
75.2%	74%	70%	86%	74%	78%	69%
67.7%	70%	53%	75%	65%	83%	60%
73.2%	83%	79%	84%	69%	59%	65%
61.2%	68%	84%	60%	64%	44%	47%
80.2%	79%	82%	82%	79%	77%	82%
79.8%	79%	85%	72%	81%	75%	87%
72.2%	79%	90%	65%	84%	49%	66%
58.5%	79%	87%	33%	65%	56%	31%
80.0%	80%	80%	80%	82%	76%	82%
74.2%	71%	82%	74%	71%	71%	76%
59.8%	66%	87%	37%	58%	48%	63%
79.3%	86%	93%	62%	80%	76%	79%
71.3%	71%	86%	58%	84%	58%	71%
81.0%	82%	81%	76%	84%	83%	80%
69.2%	72%	73%	67%	74%	62%	67%
81.2%	83%	87%	75%	82%	74%	86%
80.5%	86%	87%	90%	78%	71%	71%
86.8%	87%	90%	83%	89%	85%	87%
61.3%	66%	57%	59%	75%	53%	58%
71.5%	62%	91%	66%	71%	68%	71%
68.0%	78%	71%	45%	83%	66%	65%
77.8%	88%	77%	74%	77%	72%	79%
69.8%	74%	80%	53%	73%	72%	67%
67.2%	75%	69%	47%	70%	70%	72%
77.2%	74%	72%	81%	71%	79%	86%
76.7%	77%	74%	84%	74%	74%	77%
73.7%	77%	75%	83%	67%	75%	65%
72.7%	80%	71%	74%	79%	66%	66%
74.2%	82%	72%	77%	75%	68%	71%
69.3%	69%	79%	71%	69%	63%	65%
82.0%	89%	81%	79%	87%	72%	84%
63.7%	67%	41%	80%	62%	75%	57%
72.3%	82%	77%	59%	79%	73%	64%
48.0%	45%	51%	36%	52%	52%	52%