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

Efficiency & Succinctness

Credibility

Best Models (Coverage)

1.Claude Haiku 4.5
78.0%
2.GPT 4.1 Mini
75.1%
3.Gemini 2.5 Flash
74.0%
4.Gemma 3 12b It
71.4%
5.GPT 4o Mini
69.2%

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 74.0%	4th 71.4%	2nd 75.1%	6th 48.4%	5th 69.2%
79.0%	78%	86%	84%	85%	56%	85%
75.8%	76%	69%	74%	77%	82%	77%
64.2%	74%	79%	83%	73%	2%	74%
75.2%	87%	76%	58%	83%	76%	71%
73.0%	88%	86%	87%	82%	8%	87%
69.5%	84%	75%	76%	68%	50%	64%
71.5%	70%	77%	74%	75%	67%	66%
69.3%	61%	100%	72%	59%	63%	61%
62.3%	59%	91%	57%	56%	49%	62%
69.0%	70%	72%	62%	75%	57%	78%
59.5%	55%	84%	53%	30%	82%	53%
72.2%	79%	82%	92%	67%	51%	62%
77.2%	82%	78%	71%	88%	73%	71%
87.0%	95%	94%	86%	88%	79%	80%
82.0%	83%	90%	87%	88%	65%	79%
86.2%	89%	92%		82%	84%	84%
68.0%	83%	72%	73%	76%	32%	72%
61.5%	90%	51%	82%	76%	25%	45%
49.3%	40%	92%	39%	52%	28%	45%
63.3%	70%	68%	79%	71%	36%	56%
67.8%	76%	83%	59%	82%	39%	68%
84.0%	88%	85%	82%	87%	75%	87%
76.0%	79%	98%	10%	85%	92%	92%
53.7%	0%	49%	80%	83%	43%	67%
62.5%	69%	78%	67%	81%	18%	62%
74.2%	77%	70%	72%	76%	80%	70%
61.7%	87%	24%	87%	86%	13%	73%
57.3%	61%	67%	10%	67%	88%	51%
75.5%	88%	73%	58%	88%	59%	87%
68.3%	72%	86%	76%	86%	31%	59%
57.7%	79%	77%	88%	61%	8%	33%
62.3%	90%	43%	84%	88%	25%	44%
65.8%	83%	80%	74%	77%	3%	78%
83.3%	87%	84%	83%	83%	76%	87%
75.7%	81%	75%	83%	79%	51%	85%
62.2%	84%	75%	68%	76%	11%	59%
59.8%	76%	43%	71%	70%	44%	55%
62.8%	81%	50%	67%	78%	26%	75%
71.7%	77%	85%	66%	81%	49%	72%
63.7%	83%	61%	72%	82%	16%	68%
78.3%	84%	88%	86%	85%	38%	89%
73.0%	90%	92%	78%	85%	8%	85%
74.3%	78%	91%	69%	62%	73%	73%
53.5%	74%	45%	47%	82%	8%	65%
76.5%	84%	76%	77%	85%	51%	86%
70.5%	87%	69%	73%	75%	45%	74%
60.3%	78%	87%	68%	58%	23%	48%
85.0%	90%	80%	86%	80%	89%	85%
67.2%	81%	72%	74%	74%	58%	44%
77.7%	78%	76%	82%	78%	67%	85%
47.5%	47%	64%	39%	44%	56%	35%
69.0%	78%	74%	76%	62%	69%	55%
69.2%	76%	80%	86%	85%	2%	86%
69.8%	69%	69%	74%	69%	69%	69%
87.0%	84%	92%	86%	81%	85%	94%
70.0%	95%	75%	90%	77%	20%	63%
62.5%	73%	63%	59%	67%	54%	59%
64.3%	87%	55%	81%	81%	20%	62%
67.7%	86%	54%	86%	68%	53%	59%
55.5%	70%	44%	74%	70%	25%	50%
67.2%	80%	69%	85%	83%	4%	82%
70.2%	69%	91%	58%	66%	75%	62%
74.2%	76%	77%	75%	83%	54%	80%
71.0%	79%	65%	74%	87%	41%	80%
89.3%	94%	93%	90%	91%	84%	84%
70.7%	79%	87%	44%	55%	87%	72%
68.2%	72%	67%	58%	80%	49%	83%
69.8%	75%	81%	74%	74%	41%	74%
71.5%	77%	71%	56%	75%	71%	79%
72.0%	86%	91%	65%	84%	27%	79%
79.2%	81%	86%	73%	83%	79%	73%
75.8%	82%	63%	86%	86%	57%	81%
61.3%	72%	80%	53%	75%	22%	66%
72.7%	84%	67%	73%	82%	46%	84%
77.8%	85%	93%	92%	87%	35%	75%
83.0%	88%	73%	83%	86%	86%	82%
72.3%	92%	81%	75%	86%	48%	52%
68.0%	71%	89%	69%	68%	48%	63%
64.3%	78%	79%	40%	64%	66%	59%
75.7%	82%	72%	79%	68%	69%	84%
74.3%	87%	82%	69%	73%	62%	73%
65.7%	75%	71%	47%	66%	64%	71%
76.8%	81%	74%	76%	73%	77%	80%
62.0%	80%	77%	74%	63%	24%	54%
71.8%	80%	58%	81%	66%	68%	78%
63.5%	80%	80%	60%	80%	18%	63%
62.5%	88%	73%	72%	76%	10%	56%
66.8%	81%	85%	72%	66%	32%	65%
70.3%	92%	65%	83%	93%	31%	58%
50.8%	79%	22%	79%	59%	21%	45%
71.2%	89%	51%	93%	67%	50%	77%
54.0%	46%	47%	51%	53%	81%	46%