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 Concerned Than Excited - Run d045707...

Global Dialogues GD4 - More concerned than excited

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

AI Safety & Robustness

Social interaction

Economic Disruption & Reskilling Advice

Mental Health & Crisis Support

General Knowledge

Best Models (Coverage)

1.Gemini 2.5 Flash
77.8%
2.Claude Haiku 4.5
77.5%
3.GPT 4.1 Mini
76.9%
4.GPT 4o Mini
72.9%
5.Gemma 3 12b It
71.9%

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 77.5%	1st 77.8%	5th 71.9%	3rd 76.9%	6th 68.1%	4th 72.9%
62.8%	80%	59%	45%	65%	75%	53%
59.5%	58%	81%	41%	71%	29%	77%
81.7%	87%	82%	80%	80%	78%	83%
75.0%	76%	79%	82%	84%	56%	73%
73.7%	78%	77%	63%	74%	73%	77%
74.0%	77%	76%	77%	79%	71%	64%
67.3%	86%	77%	58%	72%	38%	73%
74.8%	77%	83%	83%	60%	64%	82%
76.7%	81%	60%	82%	89%	91%	57%
71.5%	85%	82%	77%	76%	46%	63%
67.5%	66%	67%	69%	76%	63%	64%
83.5%	91%	90%	84%	92%	54%	90%
83.8%	87%	86%	91%	83%	66%	90%
54.0%	58%	51%	55%	52%	54%	54%
59.3%	65%	55%	58%	63%	64%	51%
80.2%	85%	87%	65%	87%	72%	85%
79.8%	81%	86%	68%	75%	87%	82%
82.7%	93%	82%	88%	91%	53%	89%
84.7%	87%	87%	73%	91%	86%	84%
60.8%	58%	62%	53%	58%	63%	71%
78.5%	84%	82%	85%	83%	53%	84%
83.7%	79%	83%	95%	85%	76%	84%
77.2%	80%	77%	79%	82%	68%	77%
50.0%	53%	68%	35%	52%	46%	46%
74.0%	77%	69%	85%	67%	81%	65%
68.3%	74%	64%	61%	75%	66%	70%
86.5%	94%	90%	89%	93%	61%	92%
83.2%	89%	81%	73%	84%	78%	94%
70.5%	75%	84%	58%	74%	62%	70%
81.3%	84%	87%	73%	84%	89%	71%
74.8%	76%	73%	83%	76%	70%	71%
74.2%	86%	73%	70%	72%	62%	82%
68.0%	71%	64%	71%	66%	82%	54%
63.2%	57%	81%	51%	63%	58%	69%
76.7%	87%	82%	72%	68%	65%	86%
74.2%	79%	69%	76%	82%	65%	74%
72.7%	69%	70%	81%	62%	66%	88%
73.5%	74%	89%	76%	83%	60%	59%
66.8%	81%	64%	71%	78%	53%	54%
66.7%	62%	63%	74%	77%	60%	64%
80.2%	91%	83%	63%	93%	65%	86%
78.7%	87%	78%	86%	89%	66%	66%
76.7%	85%	75%	81%	83%	68%	68%
65.7%	69%	69%	54%	61%	77%	64%
81.3%	90%	80%	83%	96%	66%	73%
82.3%	75%	80%	88%	87%	86%	78%
83.3%	86%	93%	75%	90%	71%	85%
88.7%	93%	94%	90%	98%	61%	96%
79.2%	81%	78%	92%	82%	79%	63%
78.7%	88%	77%	70%	84%	79%	74%
77.2%	83%	76%	69%	76%	75%	84%
47.2%	50%	52%	42%	50%	49%	40%
70.3%	80%	69%	53%	76%	87%	57%
63.3%	57%	78%	52%	70%	65%	58%
88.7%	92%	80%	86%	93%	88%	93%
74.0%	74%	83%	58%	78%	81%	70%
58.3%	59%	74%	38%	59%	66%	54%
83.8%	91%	84%	83%	87%	70%	88%
68.3%	72%	86%	53%	74%	53%	72%
77.8%	71%	77%	86%	80%	64%	89%
71.8%	84%	68%	72%	80%	82%	45%
76.5%	85%	78%	64%	73%	89%	70%
80.8%	78%	98%	80%	91%	61%	77%
65.3%	60%	62%	67%	70%	63%	70%
77.8%	81%	61%	80%	84%	77%	84%
70.8%	69%	88%	69%	62%	70%	67%
63.2%	74%	72%	48%	55%	74%	56%
64.0%	70%	70%	63%	85%	36%	60%
71.7%	74%	71%	75%	73%	70%	67%
85.7%	95%	78%	91%	83%	75%	92%
87.2%	87%	95%	93%	91%	66%	91%
69.2%	62%	73%	74%	71%	80%	55%
82.5%	89%	88%	70%	76%	94%	78%
48.8%	53%	57%	45%	57%	36%	45%
64.5%	68%	66%	68%	78%	49%	58%
84.0%	89%	93%	85%	87%	70%	80%
77.5%	83%	85%	84%	82%	60%	71%
79.2%	94%	74%	68%	86%	85%	68%
70.7%	68%	69%	72%	74%	60%	81%
81.7%	82%	84%	89%	91%	58%	86%
87.2%	82%	91%	97%	85%	80%	88%
89.0%	88%	91%	83%	90%	92%	90%
78.2%	85%	81%	77%	71%	82%	73%
81.7%	86%	81%	87%	86%	75%	75%
78.0%	77%	79%	78%	83%	71%	80%
67.8%	62%	76%	71%	72%	55%	71%
74.0%	72%	81%	74%	68%	64%	85%
85.5%	80%	90%	89%	82%	86%	86%
77.7%	70%	94%	92%	70%	72%	68%
78.3%	94%	88%	76%	85%	62%	65%
84.0%	94%	72%	79%	81%	89%	89%
48.2%	40%	62%	51%	47%	33%	56%
70.5%	76%	68%	62%	72%	72%	73%
84.7%	82%	88%	81%	94%	78%	85%
60.5%	57%	75%	65%	61%	52%	53%
85.5%	91%	87%	84%	89%	74%	88%
87.0%	92%	89%	90%	82%	86%	83%
84.8%	89%	92%	78%	85%	81%	84%
73.5%	78%	87%	49%	84%	63%	80%
68.5%	70%	82%	62%	80%	49%	68%
59.5%	59%	63%	60%	61%	63%	51%
80.5%	89%	75%	77%	81%	73%	88%
70.5%	83%	69%	56%	76%	68%	71%
71.5%	72%	80%	78%	69%	55%	75%
82.0%	80%	76%	75%	86%	95%	80%
76.3%	92%	76%	79%	70%	77%	64%
63.2%	79%	84%	48%	56%	75%	37%
59.7%	53%	76%	41%	69%	54%	65%
76.5%	81%	80%	74%	88%	59%	77%
83.2%	91%	73%	90%	87%	78%	80%
71.3%	68%	83%	72%	49%	68%	88%
83.2%	91%	94%	63%	75%	91%	85%
69.8%	67%	76%	59%	72%	75%	70%
65.5%	62%	65%	72%	67%	64%	63%
77.8%	69%	94%	86%	83%	64%	71%
78.5%	79%	86%	81%	89%	55%	81%