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 Excited Than Concerned C5 - Run 76e44f9...

Global Dialogues GD6UK - More excited than concerned (5 context Qs)

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

Metacognition and critical thinking

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
78.0%
2.GPT 4.1 Mini
75.7%
3.Gemini 2.5 Flash
73.6%
4.Gemma 3 12b It
71.4%
5.GPT 4o Mini
70.0%

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 78.0%	3rd 73.6%	4th 71.4%	2nd 75.7%	6th 48.2%	5th 70.0%
76.7%	77%	79%	84%	87%	56%	77%
70.8%	77%	78%	74%	77%	42%	77%
63.5%	68%	81%	83%	73%	2%	74%
75.2%	76%	89%	60%	86%	65%	75%
72.5%	88%	87%	86%	84%	8%	82%
69.8%	81%	79%	76%	73%	50%	60%
73.8%	71%	83%	74%	75%	67%	73%
70.2%	61%	100%	72%	72%	55%	61%
62.7%	59%	90%	57%	58%	49%	63%
70.2%	70%	68%	62%	75%	68%	78%
60.7%	64%	84%	53%	34%	65%	64%
74.8%	79%	75%	92%	94%	47%	62%
72.7%	81%	59%	68%	83%	74%	71%
87.7%	96%	90%	86%	89%	85%	80%
85.2%	84%	90%	87%	88%	81%	81%
84.3%	89%	85%	85%	82%	81%	84%
70.8%	83%	76%	59%	73%	62%	72%
62.7%	90%	54%	83%	81%	25%	43%
48.2%	41%	92%	39%	46%	28%	43%
68.3%	84%	71%	78%	71%	41%	65%
67.5%	76%	78%	59%	86%	39%	67%
81.0%	88%	91%	82%	84%	71%	70%
75.0%	79%	92%	10%	85%	92%	92%
54.3%	0%	52%	77%	79%	43%	75%
59.8%	69%	68%	65%	81%	5%	71%
72.8%	77%	56%	71%	76%	83%	74%
75.8%	87%	66%	89%	79%	61%	73%
55.7%	61%	57%	10%	67%	84%	55%
73.8%	87%	64%	58%	88%	59%	87%
65.0%	83%	79%	75%	89%	6%	58%
59.3%	79%	78%	74%	53%	28%	44%
62.2%	89%	43%	84%	88%	25%	44%
64.8%	83%	59%	74%	81%	3%	89%
83.8%	87%	85%	81%	86%	77%	87%
74.7%	81%	72%	83%	76%	51%	85%
68.7%	84%	83%	68%	76%	29%	72%
60.5%	76%	60%	71%	77%	26%	53%
63.7%	82%	49%	74%	82%	26%	69%
70.5%	79%	81%	65%	76%	50%	72%
63.7%	83%	56%	76%	82%	16%	69%
77.5%	84%	89%	86%	87%	35%	84%
72.3%	90%	89%	78%	85%	8%	84%
73.7%	69%	91%	69%	54%	68%	91%
58.7%	73%	51%	47%	82%	34%	65%
67.0%	80%	77%	77%	82%	1%	85%
70.7%	87%	74%	73%	75%	41%	74%
56.8%	70%	84%	69%	47%	23%	48%
86.3%	90%	83%	86%	76%	94%	89%
67.3%	81%	72%	74%	75%	58%	44%
76.3%	79%	67%	82%	79%	66%	85%
49.5%	47%	68%	42%	38%	64%	38%
68.5%	76%	80%	76%	66%	59%	54%
67.7%	87%	71%	86%	81%	2%	79%
69.8%	69%	69%	74%	69%	69%	69%
85.0%	84%	89%	77%	81%	85%	94%
72.0%	92%	74%	90%	91%	8%	77%
63.5%	73%	70%	59%	67%	54%	58%
65.5%	87%	64%	81%	81%	20%	60%
69.5%	86%	39%	86%	62%	77%	67%
55.7%	70%	43%	74%	70%	25%	52%
66.0%	82%	63%	84%	79%	4%	84%
71.5%	72%	93%	58%	69%	75%	62%
72.5%	76%	79%	74%	75%	54%	77%
72.0%	79%	67%	78%	87%	41%	80%
88.5%	94%	93%	90%	86%	84%	84%
72.2%	79%	87%	44%	57%	87%	79%
68.8%	72%	66%	61%	82%	54%	78%
69.5%	75%	78%	75%	74%	41%	74%
71.7%	77%	71%	54%	87%	58%	83%
70.7%	86%	73%	65%	81%	41%	78%
80.3%	81%	92%	73%	83%	82%	71%
78.0%	82%	59%	88%	86%	73%	80%
63.3%	72%	76%	53%	75%	43%	61%
71.8%	83%	62%	73%	83%	46%	84%
78.2%	86%	90%	92%	87%	33%	81%
83.2%	88%	67%	86%	86%	83%	89%
70.3%	92%	69%	75%	86%	48%	52%
68.5%	71%	90%	69%	70%	48%	63%
62.0%	76%	79%	40%	66%	53%	58%
77.2%	82%	78%	77%	71%	71%	84%
74.2%	88%	88%	69%	65%	65%	70%
61.3%	75%	71%	47%	66%	40%	69%
78.8%	81%	82%	82%	71%	73%	84%
62.3%	80%	78%	74%	60%	24%	58%
71.5%	80%	61%	81%	72%	68%	67%
64.8%	80%	73%	60%	80%	38%	58%
68.8%	88%	81%	72%	76%	26%	70%
65.5%	81%	92%	72%	78%	14%	56%
67.8%	85%	58%	82%	96%	31%	55%
52.0%	77%	32%	80%	57%	21%	45%
72.2%	86%	51%	91%	78%	50%	77%
49.8%	49%	50%	57%	53%	45%	45%