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 8ac74e6...

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:

Factual Accuracy & Hallucination

Reasoning

Instruction Following & Prompt Adherence

AI Safety & Robustness

Best Models (Coverage)

1.GPT 5
85.2%
2.Claude 3.7 Sonnet
85.0%
3.Claude Sonnet 4.5
84.6%
4.GPT 5.1
84.6%
5.GPT 4.1
83.8%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT 4o Mini

64.9% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsClaude Sonnet 4

89.4% similarity

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 3.7 Sonnet	Claude Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Large 2411	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o	GPT 4o Mini	GPT 5	GPT 5.1	GPT OSS 120b	GPT OSS 20b	Qwen3 30b A3B Instruct 2507	Qwen3 32b	Grok 4
Score	2nd 85.0%	16th 80.4%	7th 83.5%	3rd 84.6%	10th 83.3%	20th 75.2%	6th 83.5%	9th 83.4%	8th 83.4%	5th 83.8%	12th 81.7%	18th 78.4%	11th 82.3%	21st 74.6%	1st 85.2%	4th 84.6%	15th 80.6%	19th 77.6%	14th 80.7%	13th 81.5%	17th 80.4%
86.1%	86%	91%	90%	90%	87%	87%	85%	81%	87%	88%	91%	77%	89%	85%	89%	87%	84%	74%	85%	91%	85%
82.6%	75%	75%	84%	89%	87%	89%	78%	89%	83%	88%	78%	85%	87%	68%	91%	84%	74%	74%	84%	91%
60.3%	67%	60%	53%	53%	60%	47%	97%	63%	59%	67%	60%	47%	60%	47%	67%	67%	58%	47%	60%	60%	67%
88.4%	91%	82%	92%	90%	75%	85%	89%	88%	93%	89%	92%	90%	91%	84%	90%	90%	86%	93%	89%	91%	87%
85.5%	84%	80%	83%	89%	80%	80%	91%	89%	89%	99%	80%	80%	87%	80%	93%	97%	83%	83%	80%	80%	88%
88.8%	90%	85%	85%	94%	95%	83%	94%	89%	87%	84%	91%	97%	85%	80%	86%	88%	90%	96%	86%	90%
83.8%	90%	81%	86%	88%	81%	74%	81%	84%	84%	82%	76%	73%	81%	73%	96%	95%	93%	91%	74%	82%	95%
76.0%	81%	72%	86%	86%	75%	52%	76%	82%	76%	85%	79%	69%	71%	60%	89%	88%	70%	79%	70%	74%	76%
75.6%	73%	66%	71%	76%	84%	69%	78%	80%	86%	77%	75%	84%	73%	63%	74%	74%	76%	83%	77%		73%
87.3%	90%	90%	88%	94%	90%	90%	83%	86%	81%	86%	90%	92%	88%	90%	85%	87%	81%	67%	90%	90%	96%
74.0%	76%	83%	92%	86%	80%	85%	66%	90%	78%	68%	78%	82%	61%	57%	83%	70%	45%	48%	86%	77%	62%
87.5%	92%	93%	94%	95%	92%	76%	84%	97%	92%	90%	82%	92%	83%	82%	94%	93%	84%	63%	97%	82%	81%
87.1%	87%	90%	89%	91%	84%	90%	84%	91%	88%	87%	90%	90%	85%	89%	85%	85%	81%	90%	89%	85%	80%
89.2%	92%	87%	87%	90%	94%	86%	91%	92%	93%	88%	92%	73%	87%	92%	92%	91%	89%	88%	91%	93%	85%
88.7%	91%	90%	91%	87%	82%	92%	91%	89%	92%	93%	92%	92%	92%	76%	86%	86%	89%	92%	89%	92%	78%
90.0%	92%	85%	92%	90%	90%	93%	97%	89%	94%	94%	94%	89%	95%	89%	91%	92%	93%	75%	92%	71%	92%
70.1%	80%	79%	79%	81%	68%	62%	64%	50%	65%	78%	77%	66%	56%	61%	75%	82%	57%	75%	70%	75%	73%
81.4%	88%	72%	88%	87%	88%	81%	81%	83%	79%	80%	81%	79%	82%	74%	84%	83%	90%	90%	58%	82%	80%
62.6%	65%	60%	63%	59%	72%	47%	68%	63%	65%	74%	63%	41%	70%	56%	78%	78%	68%	34%	49%	82%	60%
84.5%	94%	64%	84%	90%	87%	80%	84%	92%	91%	96%	57%	73%	93%	89%	86%	81%	91%	87%	95%	82%	79%
85.0%	90%	87%	90%	91%	89%	77%	87%	87%	87%	93%	87%	86%	88%	80%	86%	89%	81%	77%	83%	76%	75%
89.9%	88%	91%	87%	87%	93%	91%	90%	94%	91%	89%	93%	86%	91%	94%	93%	94%	84%	81%	93%	88%
83.1%	83%	80%	85%	86%	72%	69%	88%	85%	86%	92%	89%	71%	86%	81%	84%	86%	86%	83%	86%	82%	86%
89.0%	88%	81%	88%	97%	89%	86%	92%	95%	90%	95%	90%	87%	93%	89%	87%	95%	88%	88%	89%	89%	73%
89.4%	92%	90%	85%	90%	85%	86%	86%		91%	90%	90%	80%	93%	92%	91%	92%	89%	89%	94%	91%	91%
78.6%	85%	90%	84%	84%	85%	75%	78%	70%	78%	75%	78%	78%	72%	73%	84%	78%	71%	67%	87%	72%	86%
83.4%	96%	71%	86%	89%	86%	87%	85%	90%	83%	84%	70%	74%	81%	81%	82%	86%	90%	84%	79%	82%	86%
77.3%	84%	77%	77%	79%	89%	56%	83%	91%	79%	83%	79%	64%	77%	57%	94%	89%	86%	69%	58%	73%	79%
75.7%	82%	87%	78%	83%	84%	70%	82%	74%	74%	72%	71%	71%	73%	61%	81%	79%	77%	68%	75%	75%	73%
81.2%	93%	78%	92%	89%	81%	75%	86%	88%	86%	78%	77%	76%	81%	77%	87%	80%	80%	69%	79%	75%	78%
92.0%	95%	92%	94%	95%	91%	89%	91%	91%	93%	89%	93%	91%	92%	91%	93%	93%	93%	89%	92%	92%	92%
68.8%	61%	47%	68%	68%	86%	45%	61%	82%	86%	61%	86%	86%	86%	45%	61%	61%	61%	61%	86%	86%	61%
57.5%	64%	57%	51%	51%	57%	45%	64%	59%	57%	64%	57%	58%	64%	45%	64%	64%	64%	45%	57%	57%	64%
79.3%	90%	78%	83%	90%	87%	77%	74%	83%	83%	78%	73%	73%	78%	62%	88%	79%	82%	77%	69%	80%	81%
76.4%	77%	97%	88%	88%	77%	62%	71%	61%	68%	63%	69%	65%	74%	67%	86%	80%	77%	94%	92%	59%	89%
80.1%	80%	90%	77%	71%	71%	81%	92%	80%	81%	82%	84%	87%	93%	67%	73%	79%	84%	75%	83%		72%
91.5%	94%	90%	97%	93%	92%	87%	95%	91%	93%	89%	91%	91%	94%	86%	92%	93%	91%	88%	90%	91%	93%
87.0%	92%	96%	91%	86%	88%	75%	88%	83%	84%	97%	87%	80%	77%	80%	92%	87%	90%	96%	80%	88%	89%
83.6%	94%	82%	90%	85%	94%	69%	87%	90%	86%	94%	89%	72%	93%	74%	82%	92%	76%	81%	76%	74%	76%
81.9%	80%	57%	68%	65%	86%	86%	80%	99%	86%	80%	86%	96%	86%	86%	80%	80%	80%	86%	86%	86%	80%
82.0%	91%	81%	88%	94%	92%	55%	88%	93%	96%	85%	90%	62%	85%	40%	90%	94%	83%	77%	60%	92%	86%
83.0%	82%	87%	81%	87%	83%	58%	90%	82%	81%	84%	85%	83%	85%	95%	87%	83%	87%	77%	82%	79%	86%
84.8%	89%	88%	84%	85%	76%	83%	91%	68%	86%	94%	82%	83%	82%	88%	92%	85%	85%	85%	85%	86%	83%

Model Similarity Dendrogram

Hierarchical clustering of models based on response similarity. Models grouped closer are more similar.