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 Dtef Global Dialogues Gd3 AgeGroup%3A18 25 - Run 3de6c63...

Global Dialogues GD3 - 18-25

DTEF: Predict response distributions for 18-25. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

AI Safety & Robustness

Social interaction

Best Models (Coverage)

1.Claude 3.7 Sonnet
89.1%
2.Gemini 2.5 Flash
82.2%
3.Claude Haiku 4.5
82.2%
4.Claude Sonnet 4.5
81.7%
5.GPT 5.1
81.7%

🔀 Least Similar Models

Claude 3.7 SonnetvsQwen3 32b

75.9% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsMistral Large 2411

90.3% 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 89.1%	3rd 82.2%	6th 81.5%	4th 81.7%	2nd 82.2%	21st 73.9%	9th 80.3%	11th 80.2%	15th 78.0%	7th 81.0%	12th 79.9%	19th 74.8%	8th 80.9%	14th 78.0%	10th 80.3%	5th 81.7%	18th 75.9%	20th 74.2%	17th 76.4%	16th 77.3%	13th 79.1%
87.0%		87%	91%	94%	88%	64%	88%	90%	84%	91%	90%	83%	88%	90%	92%	92%	89%	79%	82%	85%	92%
86.5%		91%	95%	79%	90%	90%	92%	93%	88%	89%	88%	83%	92%	88%	89%	88%	71%	71%	90%	83%	80%
66.3%		65%	68%	60%	65%	73%	62%	68%	62%	73%	68%	75%	68%	68%	64%	70%	65%	66%	60%	62%	63%
62.5%		63%	54%	57%	63%	80%	69%	56%	55%	63%	65%	63%	60%	75%	46%	61%	57%	62%	88%	52%	62%
91.3%		98%	93%	88%	87%	93%	91%	92%	94%	87%	95%	94%	86%	90%	96%	83%	90%	95%	98%	84%	93%
71.0%		83%	69%	77%	75%	51%	71%	75%	75%	70%	68%	70%	71%	73%	72%	71%	73%	85%	68%	63%	59%
87.7%	93%	86%	89%	91%	89%	86%	81%	92%	87%	97%	86%	90%	89%	78%	87%	94%	95%	78%	78%	85%	91%
74.1%		73%	72%	73%	78%	64%	72%	76%	77%	84%	76%	75%	75%	77%	83%	83%	75%	65%	59%	82%	63%
90.6%		88%	90%	88%	92%	90%	90%	91%	87%	96%	91%	92%	90%	92%	93%	93%	92%	83%	94%	93%	87%
59.7%		62%	52%	65%	72%	71%	60%	51%	47%	58%	69%	50%	64%	58%	41%	65%	67%	60%	80%	52%	51%
86.9%		92%	95%	84%	82%	94%	93%	93%	89%	91%	93%	68%	90%	80%	84%	92%	77%	63%	93%	93%	92%
66.6%		81%	56%	70%	79%	66%	62%	53%	49%	58%	81%	48%	63%	66%	68%	70%	68%	79%	84%	46%	84%
86.7%	80%	89%	94%	87%	91%	81%	88%	82%	91%	92%	89%	70%	88%	86%	93%	90%	86%	79%	83%	92%	90%
83.8%	91%	95%	83%	80%	83%	83%	93%	89%	82%	76%	89%	77%	93%	96%	78%	83%	76%	73%	87%	76%	77%
85.9%		88%	96%	92%	84%	76%	92%	86%	88%	85%	86%	80%	90%	84%	91%	87%	83%	83%	82%	84%	81%
83.9%		85%	89%	93%	94%	72%	85%	91%	84%	92%	83%	79%	86%	79%	88%	90%	85%	59%	73%	81%	89%
60.3%		69%	69%	70%	67%	54%	53%	45%	52%	58%	57%	66%	53%	52%	61%	71%	56%	52%	68%	66%	67%
72.3%		73%	75%	79%	72%	59%	73%	74%	65%	81%	72%	68%	76%	63%	70%	74%	69%	81%	67%	82%	73%
74.1%		77%	82%	79%	63%	58%	89%	71%	78%	84%	68%	67%	81%	66%	77%	85%	72%	54%	54%	92%	85%
87.0%		81%	93%	94%	84%	82%	95%	92%	90%	94%	90%	89%	90%	89%	92%	86%	81%	65%	79%	95%	78%
87.0%	95%	97%	92%	91%	88%	68%	98%	95%	93%	86%	83%	82%	91%	80%	93%	89%	78%	83%	74%	87%	83%
83.5%	86%	86%	80%	86%	83%	69%	90%	83%	90%	85%	87%	87%	91%	89%	85%	83%	86%	76%	75%	71%	85%
82.8%		84%	83%	84%	81%	81%	85%	87%	83%	86%	84%	66%	87%	80%	88%	91%	77%	85%	82%	81%	82%
87.3%		91%	90%	93%	91%	88%	90%	91%	87%	92%	88%	75%	84%	86%	95%	92%	84%	76%	79%		86%
83.1%	84%	87%	83%	80%	92%	78%	86%	86%	81%	74%	85%	76%	84%	92%	84%	82%	82%	76%	88%	86%	80%
79.3%		80%	83%	80%	87%	79%	72%	68%	78%	74%	82%	70%	80%	86%	86%	80%	79%	84%	83%	72%	82%
71.9%		70%	80%	82%	70%	51%	69%	75%	72%	80%	61%	75%	77%	67%	78%	78%	74%	65%	67%	75%	72%
75.6%		84%	76%	80%	89%	54%	77%	83%	81%	78%	73%	77%	77%	61%	84%	81%	76%	62%	56%	79%	84%
65.5%		82%	67%	73%	78%	65%	67%	68%	49%	54%	67%	34%	63%	63%	71%	71%	55%	62%	69%	67%	84%
71.4%		73%	78%	78%	91%	64%	56%	65%	53%	74%	79%	71%	68%	78%	77%	69%	80%	44%	70%	84%	77%
84.1%	93%	86%	93%	92%	85%	78%	82%	87%	84%	92%	88%	64%	87%	83%	88%	90%	81%	76%	75%	81%	82%
80.8%		82%	78%	87%	82%	73%	84%	78%	85%	73%	78%	71%	78%	78%	81%	78%	82%	80%	87%	89%	92%
59.8%		59%	62%	54%	59%	67%	57%	62%	56%	67%	62%	69%	62%	62%	57%	58%	56%	60%	54%	56%	57%
87.3%		87%	90%	90%	86%	85%	95%	93%	92%	93%	81%	85%	87%	80%	87%	94%	92%	78%	72%	90%	89%
71.4%		82%	76%	67%	67%	77%	57%	60%	69%	80%	68%	83%	84%	88%	62%	61%	57%	82%	88%	62%	58%
84.2%	93%	90%	94%	91%	89%	77%	91%	91%	81%	83%	82%	80%	85%	80%	90%	81%	74%	86%	70%	77%	84%
86.9%		91%	86%	87%	87%	78%	91%	93%	93%	93%	90%	80%	92%	86%	88%	91%	84%	76%	85%	81%	85%
83.5%		90%	94%	93%	90%	75%	88%	90%	86%	87%	75%	73%	90%	69%	93%	88%	69%	90%	75%	68%	88%
73.5%	87%	72%	78%	87%	81%	51%	81%	79%	76%	73%	71%	77%	78%	64%	79%	84%	62%	70%	63%	58%	73%
94.9%		95%	99%	90%	95%	96%	93%	99%	92%	96%	99%	94%	99%	99%	95%	94%	95%	97%	90%	92%	90%
79.3%		79%	82%	88%	96%	69%	88%	93%	92%	78%	78%	79%	77%	67%	66%	81%	59%	82%	63%	88%	80%
79.9%		83%	78%	79%	78%	77%	81%	80%	77%	84%	80%	83%	83%	83%	76%	81%	78%	78%	76%	83%	80%
81.6%		77%	78%	81%	91%	91%	77%	81%	78%	83%	90%	79%	83%	82%	84%	88%	78%	90%	76%	73%	71%

Model Similarity Dendrogram

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