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 C10 Dtef Global Dialogues Gd6uk AiConcern%3Amore Excited Than Concerned C10 - Run 76e44f9...

Global Dialogues GD6UK - More excited than concerned (10 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

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
75.9%
2.GPT 4.1 Mini
74.9%
3.Gemini 2.5 Flash
73.4%
4.Gemma 3 12b It
72.8%
5.GPT 4o Mini
70.9%

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 75.9%	3rd 73.4%	4th 72.8%	2nd 74.9%	6th 57.1%	5th 70.9%
77.7%	77%	67%	79%	85%	73%	85%
71.2%	66%	59%	64%	78%	81%	79%
59.0%	68%	54%	82%	73%	2%	75%
72.5%	86%	74%	64%	83%	54%	74%
71.2%	88%	89%	87%	73%	8%	82%
72.5%	81%	78%	73%	70%	69%	64%
71.5%	67%	85%	82%	67%	61%	67%
68.3%	58%	100%	66%	72%	55%	59%
74.7%	66%	91%	65%	82%	81%	63%
69.5%	66%	68%	62%	72%	83%	66%
61.5%	64%	80%	53%	42%	65%	65%
71.3%	78%	85%	89%	67%	47%	62%
80.8%	83%	92%	65%	84%	77%	84%
86.7%	95%	85%	93%	89%	79%	79%
85.0%	83%	89%	89%	88%	80%	81%
81.7%	74%	91%	82%	81%	81%	81%
63.5%	83%	73%	70%	78%	6%	71%
75.0%	77%	79%	77%	79%	76%	62%
57.2%	50%	84%	40%	64%	47%	58%
69.2%	73%	71%	83%	62%	75%	51%
70.5%	76%	79%	58%	81%	61%	68%
81.8%	81%	88%	83%	85%	67%	87%
81.8%	79%	86%	76%	85%	73%	92%
52.8%	0%	43%	77%	79%	43%	75%
65.7%	67%	64%	67%	81%	53%	62%
72.2%	77%	65%	71%	76%	70%	74%
72.8%	84%	78%	81%	74%	44%	76%
72.2%	61%	70%	99%	61%	93%	49%
63.7%	84%	62%	58%	88%	3%	87%
61.5%	83%	10%	90%	89%	6%	91%
70.5%	80%	87%	78%	53%	74%	51%
74.8%	75%	65%	71%	89%	75%	74%
62.2%	68%	57%	84%	77%	3%	84%
85.7%	87%	83%	87%	87%	83%	87%
80.0%	80%	84%	81%	79%	83%	73%
64.7%	79%	61%	66%	76%	47%	59%
58.5%	65%	39%	78%	65%	51%	53%
67.7%	81%	56%	74%	72%	53%	70%
74.2%	79%	89%	66%	83%	49%	79%
64.3%	78%	55%	69%	82%	31%	71%
83.0%	84%	87%	80%	83%	75%	89%
72.5%	85%	88%	84%	85%	8%	85%
76.3%	77%	91%	72%	75%	52%	91%
64.2%	66%	48%	71%	84%	51%	65%
78.0%	84%	70%	81%	85%	68%	80%
76.7%	87%	86%	78%	76%	58%	75%
56.2%	63%	85%	68%	49%	23%	49%
83.3%	89%	94%	91%	76%	57%	93%
62.0%	71%	60%	81%	72%	41%	47%
79.3%	78%	70%	83%	79%	81%	85%
37.3%	33%	54%	36%	35%	34%	32%
68.3%	76%	82%	67%	57%	69%	59%
64.7%	59%	68%	79%	77%	20%	85%
69.0%	69%	69%	69%	69%	69%	69%
81.5%	86%	86%	69%	73%	85%	90%
64.5%	95%	80%	72%	77%	12%	51%
77.5%	93%	84%	59%	75%	84%	70%
71.3%	88%	70%	66%	69%	68%	67%
72.5%	86%	49%	78%	66%	88%	68%
58.0%	70%	41%	81%	64%	48%	44%
64.2%	72%	62%	82%	64%	31%	74%
68.2%	69%	87%	58%	75%	58%	62%
77.0%	76%	88%	83%	69%	69%	77%
71.2%	79%	69%	72%	90%	41%	76%
77.5%	87%	80%	76%	69%	74%	79%
71.0%	69%	87%	54%	50%	87%	79%
74.3%	72%	83%	60%	82%	66%	83%
70.5%	75%	68%	77%	72%	57%	74%
71.0%	75%	71%	50%	82%	64%	84%
71.5%	87%	84%	66%	83%	27%	82%
79.3%	87%	81%	75%	84%	73%	76%
78.8%	83%	60%	79%	86%	80%	85%
64.0%	77%	71%	56%	77%	46%	57%
81.0%	84%	79%	77%	88%	74%	84%
84.3%	85%	94%	90%	87%	70%	80%
84.7%	87%	77%	84%	92%	85%	83%
72.7%	90%	86%	67%	89%	52%	52%
65.3%	62%	80%	69%	62%	55%	64%
56.7%	78%	78%	46%	66%	14%	58%
75.8%	82%	72%	75%	81%	70%	75%
75.3%	87%	82%	71%	70%	72%	70%
66.3%	74%	68%	48%	79%	60%	69%
76.8%	78%	77%	79%	79%	67%	81%
62.2%	77%	89%	62%	63%	24%	58%
77.2%	80%	61%	82%	75%	87%	78%
63.8%	81%	66%	63%	77%	41%	55%
63.5%	79%	56%	70%	76%	44%	56%
76.3%	77%	95%	82%	73%	66%	65%
84.3%	81%	87%	85%	87%	84%	82%
52.7%	75%	31%	81%	56%	35%	38%
78.0%	93%	53%	85%	79%	82%	76%
47.3%	40%	53%	47%	48%	45%	51%