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

Epistemic Humility & Self Awareness

Reasoning

Efficiency & Succinctness

Best Models (Coverage)

1.Gemini 2.5 Flash
78.3%
2.Claude Haiku 4.5
77.2%
3.GPT 4.1 Mini
76.4%
4.Gemma 3 12b It
73.7%
5.GPT 4o Mini
68.4%

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 77.2%	1st 78.3%	4th 73.7%	3rd 76.4%	6th 60.2%	5th 68.4%
80.5%	79%	68%	83%	80%	81%	92%
81.5%	85%	71%	84%	85%	82%	82%
65.5%	76%	74%	73%	80%	17%	73%
83.8%	90%	85%	86%	83%	77%	82%
73.7%	88%	93%	86%	85%	6%	84%
83.3%	80%	92%	94%	76%	94%	64%
68.3%	55%	80%	73%	70%	69%	63%
53.5%	46%	100%	51%	37%	44%	43%
55.2%	50%	89%	46%	54%	44%	48%
83.8%	81%	87%	77%	83%	90%	85%
52.2%	57%	55%	55%	36%	67%	43%
78.7%	79%	79%	88%	79%	76%	71%
65.7%	70%	81%	51%	75%	52%	65%
74.8%	92%	84%	87%	76%	38%	72%
82.0%	67%	90%	86%	89%	83%	77%
83.2%	82%	87%	78%	83%	87%	82%
81.0%	89%	88%	66%	84%	74%	85%
61.7%	80%	82%	70%	87%	18%	33%
44.7%	36%	78%	27%	52%	23%	52%
67.5%	78%	62%	83%	71%	56%	55%
67.7%	70%	81%	57%	77%	55%	66%
80.2%	71%	92%	86%	82%	82%	68%
77.8%	96%	94%	10%	87%	89%	91%
57.3%	0%	73%	74%	81%	45%	71%
65.7%	61%	51%	74%	78%	72%	58%
78.5%	77%	73%	84%	78%	89%	70%
81.3%	84%	79%	80%	83%	82%	80%
74.7%	62%	76%	93%	68%	94%	55%
77.8%	88%	63%	72%	89%	67%	88%
68.0%	84%	76%	90%	88%	3%	67%
71.7%	80%	80%	85%	82%	56%	47%
62.8%	90%	82%	63%	95%	20%	27%
74.7%	91%	88%	89%	89%	12%	79%
88.0%	87%	91%	84%	94%	87%	85%
80.7%	75%	91%	72%	81%	88%	77%
69.5%	84%	83%	82%	84%	19%	65%
68.0%	73%	71%	82%	89%	44%	49%
69.7%	78%	75%	66%	76%	55%	68%
71.5%	77%	80%	59%	76%	62%	75%
64.5%	81%	66%	80%	80%	12%	68%
83.2%	88%	87%	88%	84%	76%	76%
83.5%	92%	87%	87%	89%	58%	88%
75.5%	73%	91%	77%	50%	71%	91%
65.7%	74%	71%	73%	64%	39%	73%
81.0%	84%	81%	74%	87%	79%	81%
83.2%	86%	83%	78%	86%	80%	86%
59.0%	74%	78%	54%	61%	27%	60%
88.5%	88%	88%	90%	78%	96%	91%
68.0%	71%	68%	78%	75%	63%	53%
87.0%	85%	88%	90%	92%	81%	86%
45.2%	45%	71%	36%	47%	38%	34%
82.2%	83%	83%	93%	75%	95%	64%
73.8%	86%	86%	68%	88%	44%	71%
66.0%	66%	66%	66%	66%	66%	66%
76.3%	86%	80%	76%	73%	72%	71%
63.2%	85%	60%	65%	77%	37%	55%
68.3%	84%	76%	63%	62%	62%	63%
75.5%	82%	85%	70%	92%	78%	46%
75.0%	83%	75%	86%	71%	55%	80%
65.5%	69%	70%	84%	82%	38%	50%
78.2%	90%	79%	84%	83%	56%	77%
61.5%	66%	69%	55%	61%	59%	59%
73.3%	74%	82%	72%	75%	62%	75%
73.5%	89%	83%	68%	93%	38%	70%
84.3%	87%	91%	81%	86%	78%	83%
71.7%	69%	89%	51%	56%	89%	76%
71.2%	83%	70%	77%	87%	32%	78%
79.3%	84%	72%	78%	88%	81%	73%
68.3%	77%	77%	62%	73%	51%	70%
81.0%	87%	82%	77%	78%	82%	80%
75.5%	76%	89%	54%	86%	79%	69%
82.5%	83%	74%	86%	86%	83%	83%
71.2%	82%	75%	87%	70%	50%	63%
76.8%	84%	40%	86%	82%	84%	85%
75.8%	80%	78%	86%	81%	65%	65%
83.0%	93%	93%	80%	77%	79%	76%
66.3%	93%	69%	63%	73%	46%	54%
80.5%	83%	94%	80%	81%	77%	68%
77.2%	82%	85%	49%	74%	88%	85%
73.2%	79%	71%	78%	64%	71%	76%
74.5%	87%	76%	79%	73%	61%	71%
61.7%	67%	73%	60%	58%	45%	67%
80.3%	87%	83%	78%	78%	79%	77%
84.0%	82%	91%	89%	83%	87%	72%
67.5%	66%	44%	82%	62%	87%	64%
71.3%	86%	77%	90%	75%	44%	56%
67.5%	81%	81%	81%	86%	15%	61%
73.3%	80%	83%	72%	74%	72%	59%
61.3%	89%	86%	71%	78%	12%	32%
55.5%	65%	65%	63%	71%	24%	45%
74.3%	83%	63%	87%	76%	47%	90%
47.2%	37%	59%	51%	43%	50%	43%