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 C10 Dtef Global Dialogues Gd3 Religion%3Ai Do Not Identify With Any Religious Group Or Faith C10 - Run d6a9aeb...

Global Dialogues GD3 - 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 GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Reasoning

Factual Accuracy & Hallucination

Efficiency & Succinctness

Best Models (Coverage)

1.Claude 3.7 Sonnet
86.8%
2.Claude Sonnet 4.5
86.6%
3.Claude Haiku 4.5
84.3%
4.GPT 4.1
83.3%
5.GPT 5
83.3%

🔀 Least Similar Models

Claude Sonnet 4vsGPT OSS 20b

70.8% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsClaude Sonnet 4.5

88.7% 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	1st 86.8%	3rd 84.3%	14th 79.2%	2nd 86.6%	8th 83.1%	16th 77.5%	9th 83.0%	6th 83.2%	11th 81.5%	4th 83.3%	10th 81.5%	18th 76.0%	12th 81.3%	20th 75.7%	5th 83.3%	7th 83.2%	17th 76.3%	21st 73.3%	13th 79.9%	15th 77.6%	19th 75.8%
87.0%		88%	92%	92%	89%	78%	89%	88%	89%	91%	92%	87%	87%	89%	90%	89%	86%	64%	85%	86%	89%
81.7%		90%	84%	83%	75%	88%	88%	88%	83%	75%	76%	77%	85%	73%	89%	86%	80%	76%	77%	74%	86%
61.1%		66%	0%	61%	59%	58%	69%	66%	59%	69%	69%	71%	55%	55%	70%	59%	63%	65%	53%	89%	66%
88.1%	93%	84%	92%	90%	91%	81%	92%	88%	90%	92%	88%	90%	91%	84%	92%	89%	83%	83%	88%	82%	87%
89.9%		94%	94%	94%	88%	89%	92%	90%	89%	93%	90%	88%	85%	91%	84%	91%	89%	87%	85%	96%
87.1%		85%	82%	92%	96%	89%	89%	93%	87%	84%	89%	87%	84%	90%	81%	81%	93%	93%	86%	84%	76%
89.4%	92%	89%	93%	93%	84%	91%	87%	95%	92%	92%	88%	88%	91%	96%	89%	98%	87%	87%	81%	88%	77%
83.7%		94%	88%	88%	86%	55%	92%	92%	86%	94%	88%	86%	87%	68%	84%	86%	85%	80%	69%	83%	83%
82.3%		79%	79%	79%	92%	71%	79%	83%	88%	87%	82%	86%	84%	82%	79%	81%	83%	84%	79%	84%	84%
89.1%	89%	90%	94%	95%	90%	93%	83%	85%	82%	87%	90%	93%	84%	90%	88%	95%	83%	84%	90%	90%	96%
74.6%		84%	86%	86%	72%	86%	84%	91%	77%	65%	86%	82%	65%	68%	76%	71%	56%	46%	88%	77%	45%
85.6%	92%	89%	93%	96%	87%	79%	82%	97%	87%	84%	81%	92%	80%	82%	92%	93%	73%	64%	95%	82%	77%
74.7%	78%	79%	88%	95%	82%	88%	73%	74%	74%	75%	82%	70%	78%	90%	67%	72%	58%	51%	81%	57%	57%
87.8%	92%	94%	93%	93%	92%	92%	93%	92%	96%	86%	87%	63%	96%	76%	92%	90%	74%	79%	92%	94%	78%
83.7%		87%	86%	86%	86%	79%	91%	90%	85%	85%	85%	75%	86%	74%	90%	90%	82%	75%	78%	82%	81%
83.5%		85%	83%	84%	82%	75%	90%	89%	83%	91%	90%	76%	84%	78%	91%	81%	86%	71%	86%	80%	84%
67.2%		79%	77%	72%	64%	61%	73%	55%	67%	66%	66%	59%	59%	61%	83%	80%	55%	61%	77%	69%	60%
76.9%		78%	90%	89%	71%	56%	82%	86%	75%	79%	68%	68%	79%	63%	84%	80%	77%	76%	79%	76%	81%
61.1%	67%	45%	68%	63%	82%	45%	59%	64%	67%	77%	63%	41%	69%	56%	64%	76%	53%	56%	48%	61%	59%
83.7%	90%	92%	95%	88%	92%	75%	94%	82%	73%	93%	77%	74%	88%	74%	86%	94%	75%	75%	75%	73%	92%
81.0%	90%	89%	92%	92%	87%	77%	85%	85%	81%	90%	87%	74%	88%	77%	74%	67%	81%	65%	76%	77%	66%
84.9%	88%	94%	92%	87%	87%	83%	89%	90%	86%	90%	88%	80%	88%	85%	91%	87%	80%	71%	85%	79%	62%
82.7%	81%	84%	83%	80%	86%	87%	88%	92%	79%	88%	89%	59%	81%	81%	81%	85%	85%	77%	87%	82%	81%
78.2%		86%	97%	96%	83%	90%	70%	74%	82%	84%	84%	58%	78%	79%	81%	81%	64%	65%	81%	65%	65%
86.0%	91%	92%	92%	92%	94%	92%	95%	90%	97%	92%	92%	63%	82%	76%	75%	86%	73%	94%	90%	80%	67%
76.8%		85%	84%	84%	85%	80%	76%	72%	78%	79%	86%	76%	74%	84%	78%	74%	68%	69%	82%	59%	62%
79.8%		85%	89%	89%	85%	62%	84%	85%	80%	84%	69%	77%	82%	65%	89%	83%	74%	77%	82%	77%	78%
81.4%	94%	87%	84%	91%	97%	65%	85%	90%	86%	89%	80%	66%	86%	57%	88%	90%	81%	70%	68%	81%	74%
76.8%	84%	89%	86%	87%	81%	72%	82%	72%	74%	73%	74%	75%	72%	64%	79%	79%	78%	71%	72%	74%	74%
80.2%		80%	89%	90%	91%	78%	80%	84%	83%	81%	79%	71%	77%	67%	85%	82%	78%	71%	76%	74%	88%
86.3%	93%	86%	91%	92%	89%	80%	89%	87%	84%	90%	90%	84%	90%	81%	91%	92%	76%	76%	86%	76%	90%
79.8%		80%	0%	85%	87%	88%	76%	79%	87%	76%	76%	74%	91%	91%	87%	87%	82%	80%	93%	98%	79%
57.1%		63%	0%	59%	57%	56%	67%	64%	57%	66%	67%	69%	53%	53%	57%	57%	61%	63%	51%	57%	64%
79.3%	91%	77%	86%	89%	85%	71%	75%	81%	80%	79%	74%	73%	75%	70%	87%	82%	81%	82%	73%	76%	78%
73.6%	77%	87%	89%	87%	66%	68%	65%	65%	66%	66%	64%	70%	75%	72%	79%	79%	72%	78%	92%	54%	74%
76.8%	76%	77%	81%	73%	63%	81%	80%	83%	81%	71%	78%	83%	82%	80%	65%	73%	68%	81%	82%	77%	78%
81.4%		85%	92%	91%	81%	83%	88%	82%	85%	90%	85%	72%	87%	73%	82%	84%	74%	75%	74%	78%	67%
82.9%		85%	91%	95%	89%	92%	89%	86%	89%	93%	71%	69%	95%	84%	90%	87%	66%	69%	86%	78%	54%
81.5%	96%	87%	82%	92%	84%	71%	87%	88%	83%	90%	81%	76%	85%	60%	89%	87%	74%	71%	68%	85%	76%
88.9%		94%	0%	99%	99%	98%	90%	93%	99%	90%	90%	88%	95%	95%	99%	99%	96%	94%	93%	69%	99%
81.6%		90%	93%	93%	83%	80%	87%	97%	80%	91%	91%	86%	86%	57%	86%	88%	76%	35%	85%	68%	81%
81.4%	82%	87%	76%	83%	84%	64%	86%	83%	79%	85%	82%	88%	82%	87%	88%	81%	85%	78%	76%	76%	78%
81.7%		85%	81%	79%	71%	87%	73%	69%	78%	79%	89%	82%	76%	79%	88%	86%	87%	81%	85%	90%	90%

Model Similarity Dendrogram

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