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%3Aequally Concerned And Excited C5 - Run 76e9f49...

Global Dialogues GD6UK - Equally concerned and excited (5 context Qs)

DTEF: Predict response distributions for Equally concerned and 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

Credibility

Best Models (Coverage)

1.Gemini 2.5 Flash
78.6%
2.Claude Haiku 4.5
77.4%
3.GPT 4.1 Mini
77.0%
4.Gemma 3 12b It
73.7%
5.GPT 4o Mini
68.3%

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	2nd 77.4%	1st 78.6%	4th 73.7%	3rd 77.0%	6th 58.8%	5th 68.3%
80.5%	79%	68%	81%	83%	81%	91%
82.5%	85%	72%	84%	84%	82%	88%
65.2%	76%	74%	73%	82%	13%	73%
83.0%	90%	87%	84%	83%	77%	77%
73.2%	93%	88%	85%	85%	6%	82%
84.2%	80%	85%	94%	79%	94%	73%
67.5%	55%	77%	71%	70%	69%	63%
53.8%	43%	100%	51%	44%	44%	41%
57.7%	50%	84%	48%	66%	44%	54%
83.8%	82%	87%	77%	87%	91%	79%
61.0%	62%	55%	55%		67%	66%
74.5%	79%	66%	88%	81%	65%	68%
67.3%	68%	80%	64%	75%	52%	65%
76.2%	92%	92%	88%	84%	38%	63%
79.7%	68%	88%	86%	84%	69%	83%
84.5%	89%	82%	81%	86%	87%	82%
81.8%	89%	87%	66%	85%	79%	85%
62.7%	83%	88%	70%	87%	15%	33%
47.2%	36%	76%	27%	69%	23%	52%
70.7%	72%	67%	84%	75%	70%	56%
67.5%	70%	88%	59%	75%	55%	58%
80.3%	71%	90%	82%	82%	84%	73%
77.0%	96%	89%	10%	87%	89%	91%
54.2%	0%	64%	66%	79%	45%	71%
62.5%	61%	40%	74%	73%	66%	61%
76.2%	76%	73%	79%	79%	82%	68%
81.7%	84%	77%	82%	81%	86%	80%
76.3%	62%	73%	93%	76%	99%	55%
78.0%	88%	68%	72%	89%	67%	84%
71.0%	84%	83%	90%	88%	3%	78%
68.2%	81%	80%	86%	81%	34%	47%
61.5%	90%	81%	63%	88%	20%	27%
84.3%	91%	84%	89%	87%	68%	87%
90.2%	87%	96%	84%	96%	93%	85%
70.5%	75%	86%	77%	76%	32%	77%
73.2%	85%	86%	86%	81%	17%	84%
67.7%	73%	78%	82%	80%	34%	59%
69.0%	79%	72%	66%	77%	48%	72%
68.7%	77%	75%	59%	73%	62%	66%
66.8%	81%	73%	64%	77%	33%	73%
83.5%	88%	86%	88%	84%	76%	79%
74.3%	92%	88%	87%	88%	17%	74%
75.5%	69%	91%	77%	54%	71%	91%
64.2%	73%	71%	74%	61%	36%	70%
81.2%	84%	77%	77%	91%	83%	75%
81.0%	87%	82%	78%	75%	78%	86%
64.0%	73%	78%	54%	58%	66%	55%
88.0%	88%	83%	89%	84%	92%	92%
66.8%	71%	68%	88%	75%	46%	53%
85.8%	85%	89%	88%	85%	87%	81%
41.8%	43%	56%	36%	44%	38%	34%
82.5%	83%	83%	93%	75%	85%	76%
64.3%	86%	72%	68%	78%	7%	75%
66.0%	66%	66%	66%	66%	66%	66%
81.8%	86%	88%	83%	80%	71%	83%
62.0%	85%	71%	65%	77%	13%	61%
68.3%	84%	80%	65%	62%	62%	57%
73.3%	82%	85%	70%	91%	82%	30%
75.8%	83%	67%	77%	71%	85%	72%
63.8%	69%	69%	84%	80%	35%	46%
80.7%	89%	79%	84%	83%	65%	84%
59.8%	61%	72%	55%	53%	59%	59%
74.0%	74%	77%	72%	82%	62%	77%
67.5%	90%	86%	69%	83%	45%	32%
83.5%	86%	97%	83%	91%	61%	83%
68.2%	69%	89%	51%	49%	89%	62%
71.0%	82%	68%	77%	89%	32%	78%
80.3%	84%	79%	77%	88%	81%	73%
69.0%	77%	70%	60%	78%	53%	76%
73.5%	81%	88%	77%	78%	38%	79%
71.7%	76%	84%	54%	78%	69%	69%
83.0%	83%	79%	86%	87%	83%	80%
69.8%	82%	80%	76%	75%	43%	63%
83.8%	87%	89%	82%	85%	75%	85%
74.5%	80%	79%	86%	75%	65%	62%
83.0%	93%	93%	80%	80%	76%	76%
67.2%	93%	72%	72%	71%	41%	54%
76.8%	83%	80%	80%	82%	68%	68%
77.7%	82%	88%	49%	81%	89%	77%
72.2%	79%	71%	78%	64%	71%	70%
74.3%	86%	77%	79%	72%	61%	71%
62.0%	67%	81%	61%	56%	44%	63%
79.2%	85%	84%	79%	76%	72%	79%
80.0%	82%	82%	90%	78%	76%	72%
69.2%	82%	46%	82%	61%	82%	62%
70.0%	86%	82%	80%	78%	38%	56%
70.8%	82%	82%	84%	81%	14%	82%
76.7%	80%	87%	73%	75%	79%	66%
64.0%	89%	83%	71%	81%	28%	32%
59.0%	73%	65%	63%	69%	36%	48%
77.2%	83%	67%	89%	82%	73%	69%
52.2%	36%	65%	51%	49%	62%	50%