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 C5 Dtef Global Dialogues Gd4 AiConcern%3Aequally Concerned And Excited C5 - Run 24fa9eb...

Global Dialogues GD4 - Equally concerned and excited (5 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Mental Health & Crisis Support

Education Systems & Pedagogy

AI Safety & Robustness

Best Models (Coverage)

1.Claude Haiku 4.5
82.0%
2.GPT 4.1 Mini
80.3%
3.Gemini 2.5 Flash
77.5%
4.Gemma 3 12b It
76.0%
5.GPT 4.1 Nano
67.1%

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 82.0%	3rd 77.5%	4th 76.0%	2nd 80.3%	5th 67.1%	6th 65.4%
72.7%	74%	87%	56%	77%	65%	77%
65.7%	62%	74%	53%	70%	66%	69%
81.8%	79%	93%	84%	85%	76%	74%
73.3%	90%	69%	71%	84%	76%	50%
57.3%	65%	67%	48%	52%	65%	47%
80.2%	91%	84%	92%	85%	73%	56%
71.8%	90%	77%	67%	68%	68%	61%
80.0%	87%	85%	80%	84%	81%	63%
79.8%	89%	80%	75%	90%	76%	69%
86.3%	94%	96%	87%	72%	93%	76%
79.2%	90%	89%	78%	85%	83%	50%
70.8%	95%	85%	83%	86%	15%	61%
86.7%	91%	91%	85%	87%	85%	81%
67.7%	89%	66%	74%	72%	36%	69%
60.2%	61%	46%	52%	69%	50%	83%
79.0%	78%	90%	76%	86%	70%	74%
88.8%	86%	95%	85%	87%	84%	96%
62.2%	91%	80%	62%	75%	25%	40%
76.3%	83%	80%	88%	82%	55%	70%
47.2%	43%	59%	55%	44%	41%	41%
54.0%	77%	77%	54%	71%	16%	29%
84.8%	92%	80%	85%	90%	72%	90%
76.3%	90%	91%	92%	81%	51%	53%
51.5%	63%	49%	58%	44%	62%	33%
78.8%	83%	83%	84%	82%	87%	54%
90.5%	93%	90%	94%	85%	93%	88%
69.5%	87%	88%	71%	92%	28%	51%
77.0%	89%	72%	90%	94%	51%	66%
81.7%	86%	83%	87%	83%	68%	83%
74.5%	85%	78%	71%	80%	78%	55%
78.3%	92%	57%	92%	88%	89%	52%
77.0%	81%	82%	58%	87%	84%	70%
86.2%	85%	95%	89%	89%	77%	82%
65.7%	63%	87%	67%	72%	59%	46%
78.0%	85%	76%	77%	79%	86%	65%
80.7%	90%	88%	85%	85%	84%	52%
77.5%	91%	85%	69%	90%	82%	48%
84.3%	86%	88%	85%	87%	72%	88%
74.7%	91%	58%	88%	82%	81%	48%
75.3%	68%	78%	79%	81%	62%	84%
79.3%	86%	60%	77%	97%	71%	85%
84.0%	92%	86%	88%	86%	64%	88%
76.2%	71%	70%	89%	76%	76%	75%
63.8%	61%	58%	71%	57%	83%	53%
70.3%	85%	90%	77%	78%	29%	63%
75.0%	82%	85%	76%	88%	61%	58%
77.2%	81%	74%	86%	77%	88%	57%
83.0%	95%	98%	81%	94%	75%	55%
87.8%	95%	86%	87%	89%	74%	96%
71.7%	83%	87%	84%	89%	18%	69%
76.0%	88%	90%	91%	88%	18%	81%
56.2%	69%	29%	61%	59%	56%	63%
74.3%	85%	75%	73%	78%	75%	60%
63.0%	66%	70%	58%	63%	67%	54%
75.2%	89%	91%	79%	70%	79%	43%
73.2%	90%	75%	83%	91%	34%	66%
53.3%	47%	67%	45%	57%	54%	50%
76.5%	88%	91%	72%	83%	48%	77%
68.3%	64%	94%	63%	73%	55%	61%
62.7%	81%	69%	71%	73%	38%	44%
77.3%	86%	37%	82%	94%	86%	79%
71.5%	80%	77%	61%	60%	75%	76%
84.5%	87%	88%	93%	89%	82%	68%
76.8%	94%	59%	77%	88%	93%	50%
74.8%	84%	61%	95%	83%	74%	52%
87.5%	95%	93%	88%	92%	66%	91%
79.7%	85%	85%	80%	86%	64%	78%
73.3%	87%	72%	81%	84%	52%	64%
80.7%	80%	78%	89%	74%	80%	83%
91.2%	93%	89%	90%	97%	84%	94%
65.2%	71%	64%	65%	65%	81%	45%
78.0%	88%	65%	79%	88%	85%	63%
84.0%	94%	64%	87%	83%	90%	86%
66.7%	68%	84%	74%	56%	64%	54%
67.7%	77%	60%	68%	82%	79%	40%
78.0%	83%	58%	84%	86%	83%	74%
72.7%	85%	77%	81%	64%	61%	68%
74.8%	87%	83%	76%	86%	60%	57%
74.5%	86%	64%	82%	81%	80%	54%
69.2%	83%	86%	76%	63%	68%	39%
90.0%	95%	92%	79%	93%	88%	93%
82.7%	98%	92%	79%	94%	65%	68%
74.0%	83%	59%	80%	80%	71%	71%
86.0%	94%	87%	89%	90%	73%	83%
75.7%	93%	85%	72%	80%	62%	62%
74.0%	85%	63%	76%	87%	85%	48%
56.5%	65%	66%	71%	77%	27%	33%
65.7%	74%	73%	60%	76%	68%	43%
48.0%	59%	68%	50%	68%	12%	31%
79.5%	83%	84%	77%	95%	64%	74%
86.2%	82%	91%	89%	88%	79%	88%
50.3%	58%	73%	37%	59%	48%	27%
80.8%	83%	85%	87%	69%	77%	84%
75.2%	87%	88%	89%	86%	34%	67%
57.0%	64%	65%	59%	46%	66%	42%
79.3%	84%	86%	68%	80%	86%	72%
76.0%	81%	60%	74%	91%	77%	73%
76.7%	78%	48%	86%	86%	79%	83%
72.8%	72%	79%	54%	87%	64%	81%
63.8%	75%	75%	52%	82%	70%	29%
73.7%	69%	69%	78%	73%	68%	85%
71.7%	94%	78%	76%	95%	38%	49%
91.2%	92%	90%	94%	88%	93%	90%
77.2%	83%	94%	67%	85%	61%	73%
83.5%	96%	86%	88%	88%	58%	85%
72.5%	67%	67%	67%	90%	64%	80%
84.7%	91%	94%	78%	90%	64%	91%
65.0%	64%	87%	47%	73%	53%	66%
76.5%	69%	81%	82%	74%	78%	75%
89.8%	87%	92%	91%	94%	89%	86%
76.7%	90%	83%	64%	79%	85%	59%
86.2%	92%	73%	93%	84%	93%	82%
88.8%	87%	93%	88%	90%	93%	82%
74.3%	92%	59%	74%	84%	89%	48%
89.7%	87%	93%	96%	98%	74%	90%
57.7%	68%	64%	61%	63%	55%	35%