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

General Knowledge

Metacognition and critical thinking

Best Models (Coverage)

1.Claude Haiku 4.5
77.6%
2.GPT 4.1 Mini
75.0%
3.Gemini 2.5 Flash
74.1%
4.Gemma 3 12b It
71.7%
5.GPT 4o Mini
68.8%

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 77.6%	3rd 74.1%	4th 71.7%	2nd 75.0%	6th 47.4%	5th 68.8%
77.8%	77%	79%	84%	85%	61%	81%
71.0%	77%	77%	74%	77%	44%	77%
63.3%	74%	79%	83%	73%	2%	69%
78.8%	86%	94%	60%	83%	75%	75%
72.8%	88%	86%	87%	86%	8%	82%
70.2%	81%	82%	76%	68%	54%	60%
70.2%	70%	83%	73%	75%	53%	67%
69.5%	61%	100%	72%	63%	60%	61%
62.2%	59%	89%	57%	56%	49%	63%
70.7%	71%	70%	62%	75%	68%	78%
59.0%	64%	75%	53%	25%	72%	65%
75.5%	79%	86%	92%	83%	51%	62%
76.8%	81%	78%	68%	95%	68%	71%
87.2%	95%	94%	86%	89%	79%	80%
82.2%	84%	90%	87%	86%	65%	81%
85.2%	93%	91%	84%	82%	81%	80%
64.8%	83%	83%	73%	72%	6%	72%
61.2%	90%	44%	81%	80%	25%	47%
47.3%	40%	88%	40%	44%	28%	44%
63.3%	70%	65%	77%	78%	35%	55%
68.3%	76%	82%	59%	82%	44%	67%
79.3%	87%	84%	82%	84%	61%	78%
75.5%	79%	98%	10%	85%	92%	89%
57.7%	0%	68%	77%	87%	43%	71%
58.0%	69%	64%	67%	81%	5%	62%
72.7%	77%	54%	72%	71%	89%	73%
76.7%	84%	71%	89%	74%	68%	74%
57.2%	61%	68%	10%	67%	88%	49%
73.7%	88%	61%	58%	88%	59%	88%
64.0%	72%	91%	76%	86%	6%	53%
59.8%	79%	72%	78%	64%	34%	32%
64.3%	89%	43%	84%	88%	25%	57%
63.7%	83%	58%	75%	77%	3%	86%
84.8%	87%	87%	81%	87%	87%	80%
76.2%	80%	78%	83%	79%	52%	85%
62.8%	84%	72%	68%	76%	22%	55%
63.0%	76%	56%	71%	76%	44%	55%
61.3%	81%	58%	67%	80%	14%	68%
73.3%	79%	78%	65%	84%	50%	84%
63.7%	83%	56%	72%	86%	16%	69%
85.7%	84%	87%	86%	86%	85%	86%
73.7%	89%	88%	78%	85%	17%	85%
77.0%	74%	91%	67%	66%	73%	91%
55.2%	73%	48%	61%	76%	8%	65%
66.7%	84%	77%	78%	83%	1%	77%
71.5%	87%	74%	73%	76%	45%	74%
55.0%	63%	79%	68%	49%	23%	48%
83.5%	90%	83%	92%	76%	85%	75%
68.2%	81%	72%	83%	72%	54%	47%
79.0%	78%	80%	82%	78%	67%	89%
45.7%	40%	70%	37%	39%	56%	32%
68.2%	76%	78%	76%	57%	60%	62%
66.5%	78%	69%	86%	85%	2%	79%
69.5%	69%	69%	72%	69%	69%	69%
83.2%	85%	84%	86%	73%	85%	86%
67.3%	92%	75%	90%	77%	2%	68%
62.0%	73%	67%	59%	61%	54%	58%
65.0%	87%	59%	81%	81%	20%	62%
62.2%	86%	44%	86%	62%	35%	60%
56.8%	70%	42%	82%	73%	29%	45%
64.0%	80%	67%	85%	64%	4%	84%
70.0%	69%	90%	58%	66%	75%	62%
73.0%	75%	77%	77%	78%	54%	77%
71.2%	79%	62%	79%	87%	41%	79%
86.0%	94%	79%	90%	85%	84%	84%
68.8%	79%	87%	44%	58%	87%	58%
60.0%	72%	63%	58%	82%	1%	84%
63.7%	75%	81%	75%	74%	3%	74%
72.0%	68%	71%	54%	81%	73%	85%
70.7%	85%	72%	64%	84%	41%	78%
79.7%	80%	88%	73%	83%	81%	73%
78.2%	82%	75%	87%	86%	59%	80%
59.5%	72%	73%	53%	80%	22%	57%
73.0%	83%	75%	73%	77%	46%	84%
76.7%	85%	93%	91%	87%	33%	71%
84.0%	88%	75%	86%	86%	86%	83%
71.2%	92%	73%	75%	86%	48%	53%
69.7%	71%	90%	69%	77%	48%	63%
63.8%	78%	78%	40%	66%	62%	59%
77.8%	82%	92%	77%	63%	69%	84%
73.2%	88%	87%	69%	64%	61%	70%
65.2%	75%	71%	47%	72%	57%	69%
79.3%	80%	84%	76%	83%	73%	80%
63.7%	80%	74%	74%	72%	24%	58%
76.7%	80%	61%	82%	72%	87%	78%
60.7%	80%	71%	60%	80%	18%	55%
63.2%	88%	70%	72%	76%	20%	53%
71.3%	81%	76%	65%	66%	75%	65%
69.8%	92%	65%	83%	93%	31%	55%
50.5%	78%	22%	79%	57%	21%	46%
70.8%	86%	52%	91%	69%	50%	77%
52.0%	47%	52%	50%	48%	70%	45%