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

Knowledge, learning and memory

Best Models (Coverage)

1.Claude Haiku 4.5
76.4%
2.GPT 4.1 Mini
75.6%
3.Gemini 2.5 Flash
74.0%
4.Gemma 3 12b It
72.0%
5.GPT 4o Mini
71.0%

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 76.4%	3rd 74.0%	4th 72.0%	2nd 75.6%	6th 58.0%	5th 71.0%
76.0%	67%	62%	77%	89%	80%	81%
76.2%	78%	74%	64%	77%	86%	78%
59.0%	68%	55%	82%	73%	2%	74%
73.0%	86%	65%	72%	84%	54%	77%
70.8%	88%	88%	85%	73%	8%	83%
73.8%	81%	80%	73%	68%	77%	64%
67.8%	60%	75%	69%	67%	69%	67%
67.5%	58%	100%	66%	63%	59%	59%
72.7%	66%	88%	63%	75%	81%	63%
69.2%	66%	69%	59%	72%	83%	66%
63.8%	64%	87%	53%	50%	65%	64%
74.0%	78%	81%	83%	83%	57%	62%
81.0%	82%	92%	63%	91%	72%	86%
87.0%	95%	85%	93%	90%	79%	80%
81.8%	83%	87%	70%	86%	84%	81%
79.8%	78%	77%	81%	81%	81%	81%
64.0%	83%	75%	70%	75%	6%	75%
73.7%	77%	67%	77%	77%	76%	68%
58.3%	51%	85%	39%	70%	47%	58%
67.2%	77%	67%	82%	66%	65%	46%
71.0%	78%	83%	58%	81%	59%	67%
82.7%	81%	89%	83%	84%	72%	87%
83.0%	79%	96%	76%	85%	73%	89%
54.5%	0%	51%	80%	91%	43%	62%
66.3%	69%	64%	65%	75%	54%	71%
70.8%	78%	61%	71%	71%	70%	74%
73.7%	84%	70%	82%	86%	40%	80%
74.2%	69%	63%	99%	67%	98%	49%
63.8%	87%	59%	58%	88%	3%	88%
73.2%	83%	79%	91%	89%	6%	91%
69.3%	80%	89%	72%	53%	74%	48%
74.7%	74%	76%	71%	79%	74%	74%
69.8%	68%	61%	84%	81%	43%	82%
83.3%	87%	82%	87%	81%	83%	80%
77.5%	80%	85%	82%	76%	69%	73%
64.3%	82%	85%	66%	76%	22%	55%
58.7%	65%	39%	75%	70%	60%	43%
75.3%	81%	76%	74%	82%	69%	70%
73.7%	81%	80%	64%	84%	49%	84%
68.2%	78%	54%	75%	87%	47%	68%
81.8%	84%	85%	76%	86%	76%	84%
77.3%	85%	92%	84%	85%	36%	82%
79.2%	70%	91%	72%	91%	60%	91%
61.7%	66%	50%	68%	80%	41%	65%
78.0%	84%	76%	76%	85%	63%	84%
77.0%	87%	87%	78%	78%	58%	74%
54.8%	63%	77%	66%	52%	23%	48%
85.8%	90%	95%	91%	76%	74%	89%
59.2%	72%	52%	74%	69%	41%	47%
79.5%	79%	68%	86%	79%	80%	85%
40.0%	33%	67%	35%	35%	38%	32%
59.5%	76%	78%	80%	57%	11%	55%
65.3%	67%	67%	75%	84%	20%	79%
69.0%	69%	69%	69%	69%	69%	69%
78.8%	85%	88%	69%	73%	68%	90%
62.2%	93%	49%	75%	77%	12%	67%
76.5%	92%	85%	58%	70%	84%	70%
68.3%	84%	57%	66%	69%	68%	66%
76.0%	86%	66%	80%	70%	87%	67%
60.0%	70%	43%	76%	70%	58%	43%
63.0%	72%	66%	82%	67%	18%	73%
70.8%	69%	92%	58%	69%	75%	62%
74.0%	76%	88%	83%	69%	47%	81%
73.7%	79%	68%	73%	88%	53%	81%
77.2%	86%	74%	76%	74%	74%	79%
73.5%	71%	87%	52%	65%	87%	79%
73.3%	72%	79%	58%	83%	65%	83%
70.2%	75%	54%	77%	72%	69%	74%
69.8%	75%	71%	39%	80%	71%	83%
73.0%	87%	89%	64%	89%	27%	82%
78.7%	83%	82%	75%	84%	73%	75%
78.7%	83%	60%	82%	86%	80%	81%
66.2%	79%	75%	56%	79%	43%	65%
80.5%	84%	77%	77%	81%	80%	84%
83.8%	85%	95%	90%	80%	70%	83%
83.5%	88%	64%	84%	92%	85%	88%
70.3%	90%	84%	59%	86%	52%	51%
69.2%	71%	86%	69%	71%	55%	63%
60.2%	78%	71%	46%	66%	42%	58%
77.2%	82%	73%	75%	77%	72%	84%
73.2%	87%	83%	68%	64%	67%	70%
67.2%	74%	68%	48%	79%	60%	74%
78.3%	81%	79%	75%	79%	73%	83%
62.3%	77%	85%	73%	60%	20%	59%
75.2%	80%	49%	82%	75%	87%	78%
66.8%	85%	71%	63%	80%	38%	64%
64.5%	86%	82%	70%	76%	20%	53%
78.2%	77%	88%	82%	74%	83%	65%
82.3%	81%	79%	85%	87%	84%	78%
53.5%	77%	37%	80%	54%	33%	40%
79.3%	93%	66%	89%	70%	82%	76%
47.2%	45%	47%	48%	46%	45%	52%