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: Gd3 Ctx Dtef Global Dialogues Gd3 Religion%3Ai Do Not Identify With Any Religious Group Or Faith Ctx - Run b007675...

Global Dialogues GD3 - I do not identify with any religious group or faith (with context)

DTEF: Predict response distributions for I do not identify with any religious group or faith. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

AI Safety & Robustness

Best Models (Coverage)

1.Claude Sonnet 4.5
85.6%
2.Mistral Medium 3
83.9%
3.Claude Sonnet 4
83.5%
4.GPT 4.1
83.4%
5.Llama 4 Maverick
82.6%

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	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini	Qwen3 30b A3B Instruct 2507	Qwen3 Next 80b A3B Instruct
Score	8th 80.4%	3rd 83.5%	1st 85.6%	6th 82.3%	13th 75.0%	5th 82.6%	2nd 83.9%	4th 83.4%	7th 81.5%	11th 78.3%	12th 76.4%	10th 79.7%	9th 80.2%
87.2%	91%	90%	90%	87%	82%	85%	87%	90%	93%	77%	89%	84%	88%
80.4%	75%	88%	85%	84%	75%	78%	83%	87%	62%	85%	68%	87%	88%
56.9%	60%	53%	66%	60%	47%	67%	59%	67%	60%	47%	47%	47%	60%
86.8%	84%	92%	90%	78%	85%	89%	91%	86%	90%	90%	79%	86%	88%
83.9%	80%	83%	89%	80%	80%	91%	82%	91%	80%	80%	95%	80%	80%
88.5%	85%	85%	94%	96%	85%	94%	91%	86%	89%	93%	78%	82%	92%
79.1%	77%	86%	89%	79%	73%	83%	80%	82%	78%	84%	68%	73%	76%
74.2%	67%	86%	87%	86%	53%	76%	73%	85%	80%	69%	60%	73%	70%
73.2%	68%	71%	72%	79%	58%	80%	86%	80%	77%	75%	66%	63%	76%
88.4%	90%	88%	92%	90%	90%	82%	81%	84%	90%	92%	90%	90%	90%
77.6%	83%	92%	87%	74%	80%	66%	78%	68%	79%	82%	57%	83%	80%
88.2%	93%	93%	96%	92%	75%	84%	90%	86%	81%	92%	82%	91%	91%
88.4%	90%	87%	91%	89%	90%	83%	86%	87%	89%	90%	89%	89%	89%
88.8%	86%	86%	91%	94%	83%	91%	94%	89%	92%	73%	92%	91%	92%
90.0%	92%	89%	87%	83%	93%	91%	92%	92%	91%	92%	84%	93%	91%
91.8%	85%	92%	92%	89%	98%	96%	94%	94%	95%	89%	89%	92%	88%
72.2%	79%	79%	81%	68%	65%	63%	64%	79%	76%	72%	61%	73%	79%
80.4%	73%	84%	87%	83%	84%	81%	79%	79%	80%	79%	77%	78%	81%
59.6%	61%	63%	60%	71%	41%	67%	65%	71%	68%	41%	55%	47%	65%
83.8%	68%	91%	91%	84%	74%	84%	92%	95%	57%	73%	92%	95%	93%
85.5%	78%	88%	90%	89%	78%	86%	88%	90%	89%	86%	82%	83%	84%
89.6%	93%	87%	89%	90%	88%	89%	93%	89%	90%	86%	88%	93%	90%
83.3%	87%	87%	86%	69%	77%	90%	86%	94%	88%	71%	81%	81%	86%
89.2%	81%	83%	92%	91%	88%	92%	89%	94%	90%	85%	89%	94%	92%
88.6%	90%	84%	90%	89%	87%	87%	90%	89%	91%	78%	93%	91%	93%
80.6%	90%	84%	84%	86%	73%	79%	79%	77%	79%	79%	73%	87%	78%
81.3%	71%	85%	89%	89%	85%	87%	91%	83%	74%	74%	81%	75%	73%
73.7%	77%	77%	81%	91%	59%	83%	79%	84%	70%	72%	57%	65%	63%
75.3%	86%	78%	83%	82%	70%	82%	74%	75%	71%	71%	62%	72%	73%
81.1%	82%	92%	89%	84%	75%	86%	85%	77%	78%	76%	77%	75%	78%
91.8%	92%	94%	96%	92%	88%	91%	94%	89%	91%	91%	91%	92%	93%
68.9%	47%	68%	68%	86%	45%	45%	87%	61%	86%	86%	86%	86%	45%
52.5%	57%	51%	51%	45%	45%	64%	57%	64%	57%	45%	45%	57%	45%
77.2%	78%	83%	91%	84%	75%	74%	83%	79%	75%	73%	64%	68%	77%
75.5%	97%	94%	88%	66%	61%	71%	67%	64%	70%	74%	71%	73%	86%
82.4%	91%	77%	77%	75%	82%	92%	87%	82%	84%	83%	74%	81%	86%
91.2%	90%	97%	94%	93%	89%	94%	94%	89%	88%	91%	84%	90%	93%
87.2%	95%	88%	87%	89%	88%	88%	92%	93%	93%	80%	80%	80%	80%
82.2%	82%	90%	82%	90%	75%	89%	86%	93%	89%	72%	73%	76%	72%
79.8%	57%	68%	89%	86%	86%	80%	95%	80%	86%	81%	86%	86%	57%
77.5%	81%	89%	94%	89%	54%	89%	95%	82%	95%	63%	49%	53%	75%
83.2%	87%	82%	87%	75%	61%	90%	81%	86%	84%	90%	95%	81%	82%
84.8%	81%	85%	85%	64%	85%	91%	88%	93%	81%	83%	88%	89%	89%