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 Religion%3Ai Do Not Identify With Any Religious Group Or Faith C10 - Run c1c5bf9...

Global Dialogues GD4 - I do not identify with any religious group or faith (10 context Qs)

DTEF: Predict response distributions for I do not identify with any religious group or faith. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

AI Safety & Robustness

Social interaction

Knowledge, learning and memory

Best Models (Coverage)

1.Claude Haiku 4.5
82.4%
2.Gemini 2.5 Flash
81.5%
3.GPT 4.1 Mini
80.8%
4.GPT 4o Mini
76.8%
5.Gemma 3 12b It
76.6%

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 82.4%	2nd 81.5%	5th 76.6%	3rd 80.8%	6th 74.8%	4th 76.8%
73.3%	80%	78%	57%	69%	87%	69%
62.7%	64%	82%	39%	66%	61%	64%
79.0%	73%	82%	82%	86%	74%	77%
83.5%	86%	81%	88%	81%	80%	85%
65.3%	71%	79%	57%	63%	63%	59%
84.0%	83%	90%	82%	83%	77%	89%
67.5%	91%	69%	59%	59%	72%	55%
81.5%	88%	69%	84%	78%	86%	84%
85.3%	93%	78%	78%	93%	91%	79%
79.5%	70%	66%	84%	88%	89%	80%
81.8%	87%	73%	85%	86%	79%	81%
81.0%	84%	85%	88%	82%	60%	87%
80.8%	85%	80%	79%	84%	84%	73%
59.7%	73%	58%	56%	70%	45%	56%
64.7%	59%	54%	65%	74%	74%	62%
74.5%	82%	89%	65%	74%	65%	72%
83.7%	79%	85%	88%	84%	82%	84%
84.8%	93%	88%	89%	93%	70%	76%
87.5%	87%	94%	79%	92%	93%	80%
82.0%	86%	83%	58%	85%	87%	93%
84.3%	96%	86%	85%	84%	77%	78%
90.3%	89%	87%	96%	92%	90%	88%
80.5%	81%	92%	86%	77%	65%	82%
60.0%	66%	69%	53%	52%	66%	54%
74.8%	80%	85%	82%	67%	72%	63%
90.0%	89%	89%	95%	89%	89%	89%
81.2%	92%	88%	78%	77%	77%	75%
83.5%	94%	94%	59%	91%	90%	73%
76.2%	86%	86%	68%	78%	72%	67%
83.2%	85%	88%	75%	86%	82%	83%
85.3%	84%	91%	88%	89%	70%	90%
78.3%	84%	79%	82%	83%	80%	62%
80.0%	89%	92%	64%	93%	71%	71%
68.2%	69%	92%	63%	64%	60%	61%
76.8%	92%	73%	74%	65%	71%	86%
83.0%	85%	82%	86%	86%	73%	86%
76.7%	76%	83%	82%	68%	65%	86%
81.2%	83%	89%	79%	82%	70%	84%
85.5%	88%	87%	89%	85%	79%	85%
76.0%	63%	81%	70%	87%	69%	86%
82.8%	94%	83%	78%	84%	75%	83%
82.7%	84%	78%	87%	84%	89%	74%
80.0%	85%	79%	73%	89%	90%	64%
79.0%	82%	83%	74%	71%	83%	81%
81.8%	87%	77%	86%	83%	72%	86%
81.3%	88%	88%	79%	89%	76%	68%
78.8%	93%	84%	73%	77%	70%	76%
92.3%	92%	94%	91%	91%	91%	95%
87.7%	91%	81%	91%	87%	91%	85%
83.5%	85%	88%	89%	89%	72%	78%
82.2%	89%	85%	78%	89%	75%	77%
59.5%	63%	47%	60%	62%	61%	64%
77.5%	86%	94%	73%	85%	55%	72%
64.2%	69%	75%	55%	55%	72%	59%
82.2%	83%	71%	83%	89%	82%	85%
76.3%	79%	77%	74%	79%	76%	73%
54.2%	49%	76%	39%	63%	37%	61%
87.2%	91%	86%	87%	91%	86%	82%
62.8%	64%	86%	53%	72%	50%	52%
75.3%	75%	80%	86%	74%	54%	83%
72.2%	83%	47%	76%	93%	67%	67%
73.3%	84%	83%	60%	67%	79%	67%
84.7%	88%	89%	98%	76%	74%	83%
88.2%	90%	87%	89%	87%	89%	87%
79.3%	79%	83%	82%	80%	69%	83%
78.3%	89%	80%	79%	90%	75%	57%
73.7%	85%	90%	60%	78%	77%	52%
76.5%	84%	78%	76%	88%	58%	75%
78.0%	75%	85%	69%	75%	86%	78%
84.5%	88%	72%	84%	82%	85%	96%
88.7%	88%	87%	94%	83%	89%	91%
73.5%	88%	27%	81%	87%	84%	74%
83.8%	91%	88%	81%	89%	74%	80%
69.2%	76%	86%	63%	69%	58%	63%
81.5%	82%	84%	81%	82%	84%	76%
75.7%	72%	68%	84%	85%	75%	70%
81.5%	85%	84%	86%	81%	66%	87%
86.0%	90%	87%	78%	88%	84%	89%
80.0%	82%	83%	78%	81%	81%	75%
82.5%	85%	83%	84%	81%	76%	86%
88.7%	96%	95%	88%	86%	84%	83%
84.7%	81%	91%	91%	90%	62%	93%
74.5%	74%	61%	80%	74%	80%	78%
86.5%	85%	86%	89%	79%	92%	88%
83.3%	87%	80%	89%	90%	69%	85%
83.8%	87%	83%	84%	85%	82%	82%
77.3%	77%	72%	75%	83%	80%	77%
85.7%	89%	86%	89%	84%	77%	89%
69.2%	70%	92%	70%	70%	51%	62%
81.2%	92%	90%	78%	91%	56%	80%
73.3%	75%	70%	58%	77%	86%	74%
70.7%	76%	94%	60%	66%	62%	66%
64.8%	85%	49%	61%	63%	63%	68%
83.0%	88%	89%	76%	87%	73%	85%
70.8%	72%	74%	80%	66%	66%	67%
84.5%	84%	83%	85%	88%	83%	84%
76.2%	84%	80%	87%	72%	70%	64%
79.8%	69%	62%	90%	88%	94%	76%
70.3%	71%	92%	48%	82%	60%	69%
84.0%	86%	84%	79%	89%	80%	86%
67.7%	67%	75%	70%	71%	63%	60%
91.8%	88%	87%	92%	96%	94%	94%
85.3%	93%	93%	83%	78%	91%	74%
82.8%	82%	92%	70%	84%	83%	86%
85.2%	96%	87%	81%	90%	71%	86%
83.8%	96%	89%	77%	85%	78%	78%
61.8%	80%	81%	38%	76%	46%	50%
65.5%	64%	86%	41%	68%	62%	72%
76.3%	69%	89%	87%	80%	56%	77%
82.3%	89%	87%	72%	88%	79%	79%
84.8%	86%	81%	91%	77%	86%	88%
83.7%	86%	88%	75%	92%	78%	83%
82.3%	79%	85%	79%	79%	89%	83%
88.0%	91%	88%	89%	89%	87%	84%
84.0%	83%	95%	76%	90%	74%	86%
85.8%	82%	82%	96%	89%	76%	90%