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: Gd4 C10 Dtef Global Dialogues Gd4 AiConcern%3Amore Concerned Than Excited C10 - Run 1b4d3c5...

Global Dialogues GD4 - More concerned than excited (10 context Qs)

DTEF: Predict response distributions for More concerned than excited. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Demographic Data Analysis

Survey Response Prediction

AI Safety & Robustness

Social interaction

Emotional Support

Trust

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Best Models (Coverage)

1.Claude Haiku 4.5
81.1%
2.GPT 4.1 Mini
78.0%
3.Gemini 2.5 Flash
77.2%
4.Gemma 3 12b It
73.9%
5.GPT 4o Mini
70.7%

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 81.1%	3rd 77.2%	4th 73.9%	2nd 78.0%	6th 61.7%	5th 70.7%
56.5%	69%	69%	54%	53%	44%	50%
72.3%	58%	86%	44%	84%	73%	89%
76.0%	85%	85%	86%	70%	75%	55%
80.3%	82%	81%	71%	78%	86%	84%
76.0%	78%	69%	73%	84%	72%	80%
74.8%	79%	77%	78%	77%	79%	59%
70.2%	87%	73%	64%	66%	65%	66%
75.7%	88%	82%	66%	75%	78%	65%
73.8%	81%	66%	89%	84%	88%	35%
67.8%	70%	38%	86%	85%	85%	43%
72.8%	79%	78%	71%	76%	55%	78%
80.8%	92%	97%	91%	91%	19%	95%
74.2%	91%	90%	88%	77%	27%	72%
47.0%	71%	45%	45%	50%	36%	35%
55.5%	61%	40%	53%	63%	64%	52%
75.8%	78%	66%	69%	88%	59%	95%
86.7%	90%	89%	89%	76%	89%	87%
84.0%	91%	76%	93%	93%	63%	88%
81.0%	87%	87%	84%	82%	69%	77%
59.0%	46%	74%	53%	62%	53%	66%
79.7%	84%	81%	84%	85%	60%	84%
83.3%	91%	86%	95%	83%	79%	66%
74.8%	85%	78%	82%	76%	75%	53%
60.3%	63%	76%	44%	66%	54%	59%
71.5%	80%	60%	92%	66%	86%	45%
86.0%	86%	86%	86%	84%	88%	86%
79.7%	89%	87%	75%	79%	69%	79%
65.3%	87%	79%	61%	76%	21%	68%
69.0%	85%	89%	74%	70%	36%	60%
77.0%	87%	88%	75%	75%	78%	59%
77.5%	83%	83%	79%	81%	72%	67%
73.8%	90%	81%	64%	73%	54%	81%
60.8%	76%	78%	83%	58%	33%	37%
68.3%	65%	78%	60%	76%	52%	79%
72.7%	80%	81%	63%	72%	63%	77%
81.5%	87%	88%	76%	85%	77%	76%
77.5%	92%	78%	72%	79%	68%	76%
79.3%	86%	88%	69%	84%	71%	78%
75.2%	82%	78%	70%	70%	75%	76%
74.3%	63%	79%	69%	90%	60%	85%
77.8%	94%	64%	73%	77%	71%	88%
79.2%	93%	78%	75%	79%	92%	58%
73.2%	86%	73%	81%	72%	82%	45%
76.7%	73%	91%	57%	80%	70%	89%
76.7%	89%	87%	83%	93%	19%	89%
79.7%	80%	89%	80%	83%	76%	70%
79.5%	86%	83%	84%	84%	71%	69%
90.5%	93%	94%	84%	90%	94%	88%
80.0%	91%	59%	82%	81%	96%	71%
72.8%	86%	89%	78%	74%	39%	71%
70.7%	84%	80%	69%	73%	47%	71%
53.2%	62%	56%	44%	55%	52%	50%
58.7%	83%	71%	87%	48%	23%	40%
68.0%	65%	81%	54%	78%	56%	74%
79.7%	93%	81%	74%	89%	67%	74%
71.7%	70%	89%	64%	72%	69%	66%
54.2%	55%	78%	38%	52%	30%	72%
72.5%	80%	86%	78%	79%	35%	77%
72.8%	79%	74%	56%	82%	65%	81%
74.7%	82%	89%	80%	92%	20%	85%
70.0%	88%	52%	89%	92%	72%	27%
69.7%	88%	81%	73%	68%	38%	70%
79.3%	82%	86%	91%	97%	47%	73%
72.7%	76%	65%	68%	78%	73%	76%
73.0%	86%	80%	84%	73%	59%	56%
67.5%	87%	62%	83%	67%	63%	43%
57.5%	83%	71%	66%	46%	40%	39%
65.7%	79%	71%	62%	84%	42%	56%
73.7%	72%	69%	75%	75%	75%	76%
83.2%	95%	68%	89%	90%	72%	85%
74.3%	82%	92%	71%	87%	42%	72%
60.3%	61%	63%	94%	86%	20%	38%
78.0%	94%	67%	86%	73%	79%	69%
53.8%	51%	64%	39%	66%	47%	56%
78.3%	81%	77%	68%	87%	72%	85%
85.3%	84%	72%	96%	88%	79%	93%
81.2%	89%	85%	83%	80%	70%	80%
73.3%	94%	86%	69%	71%	55%	65%
68.0%	76%	40%	76%	77%	62%	77%
74.2%	90%	82%	80%	88%	17%	88%
86.5%	92%	90%	96%	87%	80%	74%
89.3%	86%	90%	85%	93%	90%	92%
69.8%	88%	62%	86%	75%	51%	57%
81.8%	86%	82%	79%	90%	83%	71%
74.2%	86%	81%	76%	81%	56%	65%
77.8%	82%	86%	71%	85%	64%	79%
79.5%	80%	72%	80%	82%	82%	81%
86.8%	79%	87%	90%	87%	89%	89%
82.5%	85%	92%	92%	72%	71%	83%
79.5%	85%	97%	81%	85%	65%	64%
73.3%	74%	84%	79%	54%	83%	66%
62.0%	91%	79%	41%	78%	5%	78%
73.5%	89%	60%	70%	64%	73%	85%
83.5%	83%	88%	79%	88%	76%	87%
65.7%	74%	80%	65%	83%	18%	74%
82.5%	91%	83%	80%	89%	74%	78%
63.0%	81%	34%	85%	82%	28%	68%
78.5%	83%	55%	87%	90%	80%	76%
76.8%	76%	83%	59%	89%	64%	90%
67.2%	82%	81%	58%	82%	20%	80%
57.8%	65%	51%	64%	62%	53%	52%
81.0%	82%	75%	83%	85%	73%	88%
85.5%	92%	89%	78%	85%	89%	80%
69.5%	76%	77%	66%	75%	56%	67%
76.2%	74%	74%	80%	81%	65%	83%
80.7%	90%	94%	68%	86%	93%	53%
64.3%	82%	88%	57%	67%	54%	38%
66.0%	53%	85%	40%	77%	64%	77%
70.5%	73%	78%	66%	73%	60%	73%
68.7%	88%	82%	86%	68%	41%	47%
81.0%	91%	83%	80%	80%	76%	76%
86.8%	93%	94%	81%	88%	92%	73%
77.3%	64%	87%	73%	73%	86%	81%
75.2%	83%	54%	72%	84%	76%	82%
82.8%	83%	87%	90%	85%	63%	89%
70.8%	81%	76%	68%	94%	14%	92%