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 Dtef Global Dialogues Gd4 AiConcern%3Aequally Concerned And Excited - Run 4a96f68...

Global Dialogues GD4 - Equally concerned and excited

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

TAGS:

Factual Accuracy & Hallucination

Instruction Following & Prompt Adherence

AI Safety & Robustness

Demographic & Cultural Knowledge

Best Models (Coverage)

1.Gemini 2.5 Flash
80.7%
2.Claude Haiku 4.5
80.5%
3.GPT 4.1 Mini
78.9%
4.Gemma 3 12b It
78.8%
5.GPT 4o Mini
77.0%

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	2nd 80.5%	1st 80.7%	4th 78.8%	3rd 78.9%	6th 74.1%	5th 77.0%
69.2%	75%	71%	56%	74%	67%	72%
64.8%	67%	74%	53%	71%	70%	54%
81.0%	78%	89%	82%	85%	75%	77%
78.3%	76%	81%	80%	81%	76%	76%
60.7%	67%	68%	56%	58%	60%	55%
91.2%	96%	90%	89%	91%	88%	93%
62.2%	85%	59%	66%	68%	40%	55%
83.5%	85%	79%	83%	82%	86%	86%
86.5%	88%	85%	91%	85%	88%	82%
88.8%	75%	97%	90%	82%	96%	93%
84.8%	89%	84%	90%	85%	76%	85%
82.0%	87%	84%	91%	87%	64%	79%
86.7%	86%	86%	87%	87%	88%	86%
65.5%	72%	61%	73%	59%	69%	59%
72.8%	72%	63%	64%	86%	78%	74%
77.3%	78%	85%	78%	83%	70%	70%
80.7%	86%	83%	89%	78%	74%	74%
84.5%	86%	84%	92%	85%	77%	83%
80.5%	84%	84%	86%	82%	65%	82%
45.7%	61%	51%	44%	37%	37%	44%
79.2%	79%	78%	89%	75%	76%	78%
86.3%	93%	86%	91%	87%	74%	87%
92.3%	92%	91%	92%	93%	93%	93%
46.3%	48%	52%	44%	50%	39%	45%
83.5%	84%	85%	83%	83%	90%	76%
74.7%	86%	77%	79%	77%	56%	73%
90.2%	91%	92%	94%	86%	85%	93%
82.2%	90%	83%	75%	82%	79%	84%
80.3%	88%	86%	69%	82%	77%	80%
77.3%	85%	77%	71%	78%	77%	76%
89.5%	91%	89%	89%	91%	88%	89%
78.8%	80%	83%	78%	73%	75%	84%
76.0%	82%	84%	82%	84%	62%	62%
60.5%	63%	69%	61%	63%	62%	45%
80.0%	80%	84%	81%	74%	77%	84%
87.7%	91%	86%	90%	89%	85%	85%
82.7%	81%	90%	86%	69%	78%	92%
75.5%	83%	79%	87%	84%	64%	56%
89.8%	85%	91%	94%	91%	89%	89%
66.2%	60%	65%	81%	79%	50%	62%
79.7%	79%	95%	75%	85%	71%	73%
84.2%	87%	85%	88%	86%	79%	80%
78.7%	82%	72%	72%	89%	85%	72%
64.3%	62%	63%	62%	62%	69%	68%
85.0%	82%	87%	92%	86%	81%	82%
81.7%	86%	89%	86%	74%	80%	75%
82.7%	90%	87%	72%	79%	88%	80%
92.0%	93%	96%	95%	93%	90%	85%
86.5%	91%	86%	88%	80%	87%	87%
83.8%	86%	85%	88%	83%	72%	89%
84.0%	83%	87%	87%	84%	75%	88%
67.2%	62%	75%	69%	65%	64%	68%
75.5%	81%	77%	72%	81%	65%	77%
58.0%	51%	57%	59%	63%	67%	51%
82.7%	85%	82%	90%	82%	79%	78%
88.5%	90%	94%	82%	89%	89%	87%
63.3%	63%	73%	56%	60%	72%	56%
88.2%	92%	91%	88%	87%	83%	88%
62.7%	64%	72%	55%	66%	58%	61%
76.3%	73%	76%	83%	70%	78%	78%
85.7%	94%	89%	84%	93%	82%	72%
72.5%	79%	78%	57%	73%	74%	74%
82.0%	88%	84%	93%	74%	72%	81%
87.2%	90%	73%	92%	82%	93%	93%
91.7%	92%	93%	86%	96%	89%	94%
83.8%	88%	98%	85%	79%	70%	83%
75.7%	83%	77%	72%	76%	71%	75%
73.8%	78%	75%	78%	75%	69%	68%
76.5%	75%	79%	83%	73%	76%	73%
88.0%	85%	80%	93%	93%	89%	88%
77.7%	75%	81%	72%	75%	80%	83%
85.3%	87%	78%	91%	87%	84%	85%
92.2%	93%	90%	93%	96%	91%	90%
64.5%	61%	76%	64%	66%	52%	68%
71.3%	72%	69%	74%	69%	69%	75%
78.5%	80%	84%	81%	78%	74%	74%
80.5%	83%	84%	85%	77%	69%	85%
81.5%	86%	78%	75%	87%	83%	80%
82.7%	83%	75%	89%	84%	79%	86%
80.5%	82%	84%	91%	74%	77%	75%
93.8%	95%	92%	94%	93%	94%	95%
82.3%	84%	87%	97%	87%	61%	78%
78.0%	83%	72%	85%	76%	75%	77%
86.0%	94%	86%	87%	87%	74%	88%
84.8%	94%	83%	86%	82%	79%	85%
84.3%	86%	85%	87%	82%	80%	86%
66.5%	62%	67%	77%	68%	62%	63%
73.3%	71%	79%	74%	81%	68%	67%
55.3%	49%	68%	69%	52%	42%	52%
80.2%	79%	82%	74%	96%	77%	73%
80.0%	82%	76%	77%	91%	80%	74%
51.7%	44%	61%	50%	47%	49%	59%
77.0%	77%	89%	66%	70%	71%	89%
82.5%	83%	88%	85%	81%	76%	82%
58.2%	61%	66%	63%	55%	52%	52%
82.5%	86%	83%	84%	78%	76%	88%
82.7%	87%	81%	72%	89%	79%	88%
89.2%	90%	82%	93%	92%	89%	89%
72.8%	78%	92%	52%	76%	69%	70%
65.0%	66%	71%	61%	69%	54%	69%
71.5%	69%	76%	74%	71%	72%	67%
88.0%	91%	90%	80%	91%	87%	89%
70.0%	85%	71%	71%	67%	55%	71%
87.3%	82%	93%	86%	87%	88%	88%
85.5%	96%	90%	73%	88%	74%	92%
81.8%	94%	88%	78%	85%	66%	80%
82.5%	89%	93%	74%	82%	79%	78%
62.8%	62%	70%	48%	68%	64%	65%
74.3%	82%	68%	74%	81%	66%	75%
86.0%	87%	90%	92%	94%	79%	74%
84.5%	90%	90%	85%	68%	85%	89%
93.2%	91%	94%	92%	97%	93%	92%
76.0%	84%	79%	75%	79%	65%	74%
81.0%	87%	71%	90%	82%	70%	86%
89.5%	87%	93%	95%	95%	76%	91%
63.2%	55%	72%	67%	58%	70%	57%