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%3Amore Excited Than Concerned - Run 1e37fb8...

Global Dialogues GD4 - More excited than concerned

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

TAGS:

Instruction Following & Prompt Adherence

Mental Health & Crisis Support

AI Safety & Robustness

Factual Accuracy & Hallucination

Best Models (Coverage)

1.Claude Haiku 4.5
80.0%
2.GPT 4.1 Mini
79.4%
3.Gemma 3 12b It
78.8%
4.Gemini 2.5 Flash
77.4%
5.GPT 4o Mini
75.1%

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 80.0%	4th 77.4%	3rd 78.8%	2nd 79.4%	6th 75.0%	5th 75.1%
75.0%	83%	94%	51%	82%	60%	80%
61.0%	55%	54%	46%	69%	76%	66%
77.0%	72%	72%	82%	81%	76%	79%
77.2%	79%	71%	82%	81%	76%	74%
60.0%	67%	66%	56%	59%	56%	56%
89.7%	92%	94%	86%	93%	85%	88%
58.8%	76%	62%	60%	65%	33%	57%
83.0%	86%	75%	88%	91%	75%	83%
84.2%	81%	78%	87%	85%	90%	84%
68.0%	62%	59%	74%	66%	74%	73%
88.3%	92%	85%	92%	94%	84%	83%
77.2%	92%	75%	90%	88%	59%	59%
86.7%	82%	90%	86%	90%	85%	87%
77.5%	85%	83%	91%	69%	69%	68%
69.7%	62%	59%	65%	82%	75%	75%
85.0%	89%	92%	82%	90%	78%	79%
94.3%	91%	96%	96%	95%	93%	95%
84.2%	90%	66%	86%	86%	96%	81%
77.2%	82%	80%	88%	75%	63%	75%
63.3%	61%	79%	73%	55%	59%	53%
78.5%	86%	54%	82%	79%	93%	77%
84.8%	86%	96%	87%	86%	67%	87%
89.2%	92%	92%	84%	92%	88%	87%
48.3%	47%	57%	53%	45%	51%	37%
73.7%	83%	79%	59%	74%	74%	73%
66.3%	74%	78%	60%	75%	48%	63%
90.0%	96%	81%	91%	90%	95%	87%
82.7%	85%	78%	80%	89%	83%	81%
78.3%	89%	80%	75%	77%	71%	78%
73.7%	82%	71%	62%	81%	78%	68%
84.7%	86%	89%	93%	86%	78%	76%
88.8%	93%	91%	91%	89%	83%	86%
84.0%	82%	94%	78%	81%	78%	91%
57.3%	55%	62%	63%	51%	75%	38%
80.3%	75%	89%	90%	82%	72%	74%
88.0%	93%	90%	88%	90%	86%	81%
76.2%	74%	68%	92%	75%	78%	70%
76.7%	81%	81%	84%	82%	67%	65%
88.8%	91%	91%	91%	87%	92%	81%
69.0%	59%	69%	78%	79%	64%	65%
80.7%	92%	81%	80%	92%	79%	60%
84.3%	89%	90%	93%	88%	56%	90%
84.7%	90%	93%	70%	90%	85%	80%
60.7%	61%	51%	69%	62%	59%	62%
78.7%	80%	81%	86%	80%	77%	68%
75.7%	78%	82%	77%	79%	67%	71%
75.5%	77%	77%	70%	75%	77%	77%
86.3%	84%	96%	74%	99%	81%	84%
87.2%	93%	92%	88%	95%	71%	84%
76.7%	79%	85%	88%	74%	66%	68%
79.0%	85%	82%	90%	75%	63%	79%
66.7%	67%	52%	67%	73%	74%	67%
73.8%	73%	89%	66%	83%	53%	79%
60.3%	50%	72%	74%	38%	91%	37%
85.0%	83%	90%	89%	82%	89%	77%
85.0%	85%	86%	79%	87%	81%	92%
61.3%	64%	53%	62%	64%	68%	57%
88.0%	91%	87%	92%	90%	81%	87%
62.2%	67%	94%	49%	58%	63%	42%
67.5%	70%	55%	83%	61%	71%	65%
85.8%	89%	72%	91%	86%	92%	85%
74.0%	82%	77%	53%	85%	71%	76%
82.7%	97%	81%	93%	71%	76%	78%
84.5%	94%	70%	92%	88%	82%	81%
94.2%	91%	97%	89%	98%	92%	98%
89.7%	92%	94%	84%	86%	92%	90%
85.7%	96%	87%	72%	91%	77%	91%
78.5%	85%	84%	76%	83%	70%	73%
81.7%	85%	82%	78%	81%	87%	77%
90.7%	88%	88%	88%	95%	90%	95%
74.3%	74%	66%	82%	71%	77%	76%
80.8%	85%	71%	86%	80%	80%	83%
82.5%	81%	65%	92%	84%	88%	85%
64.7%	64%	74%	68%	66%	58%	58%
71.5%	79%	58%	84%	74%	66%	68%
73.8%	76%	63%	82%	76%	76%	70%
77.7%	75%	70%	90%	73%	79%	79%
81.8%	87%	70%	77%	89%	89%	79%
86.3%	82%	76%	92%	94%	89%	85%
81.2%	80%	86%	87%	78%	84%	72%
85.2%	91%	75%	88%	91%	88%	78%
78.3%	88%	95%	90%	69%	58%	70%
74.0%	80%	67%	83%	69%	71%	74%
83.0%	82%	95%	88%	84%	70%	79%
82.3%	94%	81%	86%	76%	77%	80%
81.3%	86%	64%	92%	86%	77%	83%
59.5%	56%	45%	65%	59%	72%	60%
69.2%	74%	55%	72%	71%	75%	68%
58.3%	52%	94%	60%	51%	53%	40%
80.0%	81%	81%	73%	92%	76%	77%
83.3%	87%	91%	74%	86%	77%	85%
54.2%	46%	72%	56%	49%	44%	58%
74.8%	81%	80%	59%	64%	76%	89%
81.8%	90%	77%	86%	82%	76%	80%
59.3%	63%	49%	70%	53%	61%	60%
86.5%	86%	85%	93%	90%	80%	85%
70.3%	76%	61%	71%	82%	60%	72%
82.7%	81%	66%	93%	91%	77%	88%
83.3%	87%	84%	62%	94%	94%	79%
65.8%	74%	56%	71%	67%	64%	63%
75.8%	77%	65%	80%	80%	76%	77%
84.7%	91%	79%	80%	89%	78%	91%
63.8%	70%	86%	60%	69%	41%	57%
87.0%	85%	87%	83%	97%	85%	85%
83.3%	88%	86%	88%	83%	75%	80%
82.2%	79%	86%	76%	91%	63%	98%
83.0%	88%	80%	70%	87%	81%	92%
61.8%	53%	65%	55%	66%	76%	56%
83.5%	85%	87%	83%	87%	81%	78%
88.5%	88%	94%	89%	92%	86%	82%
82.0%	75%	88%	88%	73%	88%	80%
86.5%	88%	77%	85%	93%	89%	87%
76.7%	79%	72%	71%	81%	79%	78%
82.0%	85%	66%	92%	87%	83%	79%
82.2%	87%	93%	82%	89%	71%	71%
70.2%	76%	58%	85%	62%	73%	67%