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 Concerned Than Excited C10 - Run 5c843db...

Global Dialogues GD6UK - More concerned than excited (10 context Qs)

DTEF: Predict response distributions for More concerned than excited. Source: Global Dialogues GD6UK (https://github.com/collect-intel/global-dialogues)

TAGS:

PERIODIC

Dtef

Demographic

Global Dialogues Gd6uk

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

Reasoning

AI Safety & Robustness

Best Models (Coverage)

1.Claude Haiku 4.5
77.4%
2.Gemini 2.5 Flash
75.0%
3.GPT 4.1 Mini
73.9%
4.GPT 4o Mini
69.5%
5.GPT 4.1 Nano
52.3%

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 77.4%	2nd 75.0%	- -	3rd 73.9%	5th 52.3%	4th 69.5%
63.0%	67%	48%		71%	66%	63%
73.2%	83%	66%		75%	74%	68%
75.6%	70%	82%		83%	59%	84%
82.2%	85%	81%		91%	72%	82%
67.8%	89%	81%		78%	19%	72%
76.4%	86%	65%		89%	78%	64%
68.0%	53%	87%		75%	36%	89%
60.4%	45%	75%		55%	56%	71%
79.0%	57%	91%		80%	90%	77%
71.6%	75%	75%		80%	66%	62%
38.0%	56%	43%		31%	25%	35%
65.2%	71%	77%		82%	34%	62%
67.6%	60%	82%		65%	60%	71%
89.6%	96%	93%		88%	85%	86%
80.0%	71%	78%		84%	85%	82%
90.8%	90%	90%		90%	94%	90%
69.8%	89%	89%		68%	20%	83%
79.8%	92%	71%		86%	58%	92%
80.2%	77%	93%		68%	71%	92%
64.8%	84%	70%		75%	61%	34%
66.6%	74%	85%		76%	34%	64%
78.8%	84%	77%		80%	91%	62%
83.2%	91%	88%		85%	77%	75%
40.4%	0%	41%		63%	35%	63%
57.8%	79%	46%		52%	62%	50%
80.4%	87%	78%		88%	74%	75%
56.4%	79%	48%		71%	18%	66%
76.8%	78%	84%		66%	83%	73%
58.2%	83%	51%		71%	19%	67%
85.2%	80%	93%		83%	86%	84%
74.4%	86%	62%		67%	83%	74%
80.8%	94%	71%		91%	61%	87%
68.6%	83%	82%		86%	6%	86%
89.0%	92%	91%		94%	93%	75%
66.4%	78%	57%		66%	74%	57%
79.2%	88%	84%		84%	53%	87%
66.8%	79%	69%		79%	45%	62%
64.4%	79%	74%		62%	53%	54%
52.2%	73%	58%		61%	13%	56%
64.6%	80%	72%		74%	33%	64%
86.0%	91%	92%		78%	85%	84%
69.8%	87%	77%		84%	25%	76%
75.6%	71%	91%		52%	73%	91%
59.2%	70%	64%		64%	42%	56%
55.0%	83%	26%		80%	17%	69%
58.0%	80%	47%		66%	31%	66%
65.6%	74%	83%		79%	12%	80%
65.8%	72%	78%		65%	55%	59%
41.4%	68%	50%		55%	5%	29%
87.0%	90%	84%		89%	86%	86%
57.2%	38%	93%		54%	35%	66%
71.2%	81%	74%		84%	46%	71%
77.2%	70%	82%		81%	71%	82%
66.0%	66%	66%		66%	66%	66%
80.2%	82%	84%		70%	74%	91%
68.8%	84%	91%		79%	4%	86%
70.2%	89%	79%		70%	54%	59%
77.4%	86%	89%		76%	67%	69%
81.0%	89%	90%		83%	89%	54%
64.6%	70%	82%		75%	34%	62%
71.8%	86%	81%		87%	26%	79%
48.6%	66%	73%		61%	13%	30%
63.2%	76%	80%		73%	22%	65%
63.8%	82%	93%		67%	25%	52%
83.8%	91%	93%		89%	76%	70%
77.8%	77%	94%		54%	94%	70%
59.6%	79%	52%		89%	19%	59%
59.6%	84%	36%		85%	25%	68%
69.2%	63%	78%		63%	59%	83%
53.2%	83%	76%		56%	4%	47%
74.2%	79%	72%		88%	65%	67%
73.8%	78%	59%		86%	71%	75%
66.4%	88%	83%		72%	21%	68%
62.2%	86%	79%		53%	45%	48%
80.0%	84%	90%		75%	78%	73%
78.2%	85%	94%		75%	66%	71%
76.4%	85%	77%		79%	65%	76%
75.2%	83%	77%		68%	68%	80%
60.4%	85%	73%		65%	15%	64%
74.2%	78%	75%		80%	71%	67%
66.6%	69%	69%		70%	63%	62%
38.2%	62%	51%		40%	2%	36%
79.0%	84%	86%		81%	63%	81%
68.6%	80%	72%		83%	45%	63%
45.2%	75%	53%		58%	1%	39%
65.6%	84%	80%		72%	26%	66%
75.6%	86%	80%		79%	51%	82%
87.8%	75%	98%		90%	85%	91%
77.8%	87%	63%		81%	70%	88%
82.0%	79%	88%		86%	70%	87%
82.2%	84%	78%		80%	86%	83%
55.2%	36%	77%		51%	52%	60%