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 Gender%3Afemale Ctx - Run fc89a56...

Global Dialogues GD3 - Female (with context)

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

AI Safety & Robustness

Best Models (Coverage)

1.Claude 3.7 Sonnet
88.3%
2.GPT 5
86.0%
3.Claude Sonnet 4.5
86.0%
4.GPT 5.1
85.8%
5.Claude Sonnet 4
84.6%

🔀 Least Similar Models

Llama 4 MaverickvsGPT OSS 20b

75.7% similarity

👯 Most Similar Models

Claude 3.7 SonnetvsClaude Sonnet 4

90.2% 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 88.3%	12th 82.7%	5th 84.6%	3rd 86.0%	13th 82.3%	21st 78.5%	6th 84.0%	8th 83.4%	7th 83.8%	9th 83.3%	10th 83.0%	20th 79.7%	11th 82.8%	18th 79.9%	2nd 86.0%	4th 85.8%	17th 79.9%	16th 80.1%	19th 79.7%	15th 82.2%	14th 82.3%
84.4%		87%	86%	86%	85%	82%	84%	83%	85%	86%	88%	77%	86%	79%	91%	87%	79%	80%	88%	86%	82%
82.8%	77%	89%	75%	83%	80%	90%	91%	75%	81%	87%	89%	83%	83%	92%	91%	85%	72%	76%	83%	78%	78%
64.4%		66%	55%	66%	45%	95%	95%	55%	66%	69%	66%	43%	66%	45%	69%	69%	69%	66%	45%	69%	69%
87.7%	96%	86%	95%	94%	86%	86%	94%	94%	89%	86%	85%	93%	94%	80%	84%	94%	84%	79%	93%	86%	63%
81.5%		77%	80%	88%	77%	77%	88%	85%	79%	86%	77%	77%	85%	77%	94%	90%	77%	77%	77%	77%	86%
85.6%		92%	89%	92%	96%	78%	89%	95%	90%	81%	82%	88%	79%	83%	87%	83%	77%	90%	75%	77%	90%
86.3%	93%	79%	89%	93%	92%	79%	83%	94%	89%	84%	81%	75%	86%	79%	92%	98%	97%	81%	79%	79%	90%
77.0%	82%	72%	84%	82%	74%	65%	69%	78%	79%	87%	80%	76%	75%	71%	79%	86%	74%	76%	71%	75%	81%
75.6%	71%	72%	72%	73%	50%	69%	84%	72%	86%	85%	75%	89%	82%	78%	88%	77%	75%	79%	65%	70%	76%
87.9%	93%	93%	87%	93%	93%	95%	79%	79%	86%	87%	69%	93%	90%	93%	85%	90%	76%	83%	93%	93%	96%
81.2%		90%	90%	93%	87%	85%	79%	92%	79%	75%	89%	95%	71%	68%	88%	89%	68%	61%	89%		54%
87.9%	95%	92%	93%	97%	93%	70%	82%	96%	87%	82%	88%	93%	84%	83%	94%	89%	79%	78%	93%	88%	90%
90.4%	93%	93%	94%	93%	91%	85%	92%	94%	86%	89%	91%	94%	87%	91%	91%	91%	86%	87%	91%	91%	88%
91.2%	95%	90%	91%	89%	96%	80%	91%	94%	94%	90%	95%	75%	96%	92%	92%	94%	89%	93%	96%	96%	88%
92.1%	95%	95%	94%	90%	96%	94%	95%	96%	93%	94%	93%	91%	95%	95%	87%	90%	87%	85%	87%	91%	91%
90.9%	99%	87%	98%	96%	97%	88%	94%	91%	94%	89%	94%	66%	94%	99%	91%	83%	84%	97%	96%	78%	93%
72.3%		83%	74%	75%	74%	76%	70%	47%	63%	73%	82%	72%	55%	70%	77%	87%	78%	60%	72%	77%	81%
83.2%	89%	72%	87%	84%	84%	80%	82%	88%	87%	77%	82%	77%	84%	81%	81%	81%	91%	98%	74%	90%	78%
69.0%	73%	61%	80%	68%	71%	52%	69%	67%	70%	83%	70%	51%	84%	72%	87%	72%	63%	56%	51%	81%	67%
88.0%	93%	88%	95%	96%	92%	83%	95%	93%	99%	91%	72%	71%	88%	89%	88%	96%	85%	83%	84%	83%	84%
88.9%	92%	86%	94%	95%	92%	87%	92%	87%	92%	96%	89%	88%	92%	91%	88%	93%	83%	82%	86%	81%	80%
89.1%	90%	90%	87%	87%	88%	89%	87%	93%	92%	88%	87%	88%	92%	94%	90%	95%	83%	81%	89%	89%	93%
79.6%	78%	82%	82%	82%	63%	75%	90%	89%	87%	91%	81%	70%	66%	79%	75%	83%	81%	71%	85%	82%	80%
88.7%	89%	82%	86%	93%	92%	86%	94%	86%	87%	91%	90%	91%	92%	91%	89%	88%	90%	87%	88%	91%	80%
92.1%	95%	95%	89%	96%	95%	88%	92%	96%	95%	92%	94%	73%	94%	90%	93%	95%	88%	96%	91%	93%	94%
78.1%		87%	82%	82%	83%	70%	74%	68%	75%	74%	83%	82%	74%	71%	82%	85%	71%	71%	86%	77%	86%
84.0%	90%	74%	87%	85%	84%	86%	84%	91%	81%	81%	69%	94%	90%	88%	88%	79%	85%	83%	80%	75%	89%
84.2%	84%	83%	90%	90%	95%	67%	84%	96%	90%	86%	84%	77%	86%	72%	94%	95%	78%	88%	73%	71%	85%
77.2%	82%	92%	82%	84%	79%	73%	77%	75%	71%	75%	79%	70%	75%	67%	86%	83%	71%	74%	75%	75%	76%
80.2%		78%	85%	88%	92%	76%	79%	87%	82%	74%	76%	74%	78%	74%	80%	76%	73%	88%	78%	83%	82%
91.7%	93%	91%	91%	91%	90%	91%	89%	93%	88%	89%	92%	94%	93%	94%	93%	94%	93%	92%	91%	92%	92%
60.3%		41%	63%	45%	78%	41%	41%	81%	78%	57%	78%	78%	57%	41%	57%	57%	57%	78%	43%	78%	57%
62.0%		61%	51%	61%	61%	61%	95%	50%	55%	63%	61%	61%	61%	61%	63%	63%	63%	61%	61%	63%	63%
84.5%	90%	83%	87%	94%	84%	81%	81%	85%	85%	83%	82%	79%	85%	82%	91%	86%	86%	84%	75%	86%	85%
72.7%	78%	82%	79%	78%	50%	68%	65%	54%	57%	61%	63%	79%	73%	69%	80%	88%	72%	83%	92%	69%	87%
84.0%	89%	90%	87%	81%	67%	80%	88%	90%	87%	87%	87%	82%	91%	81%	82%	84%	78%	76%	77%	87%	93%
94.6%	94%	97%	95%	97%	96%	97%	95%	92%	95%	86%	95%	94%	96%	96%	92%	94%	91%	94%	96%	96%	98%
85.4%		88%	91%	86%	83%	78%	90%	88%	90%	95%	98%	77%	86%	77%	91%	93%	76%	71%	77%	85%	87%
89.5%	93%	91%	95%	95%	94%	85%	97%	92%	88%	95%	92%	80%	96%	83%	95%	93%	83%	81%	81%	83%	87%
78.8%		66%	75%	94%	78%	61%	61%	96%	93%	87%	78%	74%	66%	66%	87%	87%	87%	78%	78%	78%	87%
84.8%	90%	79%	89%	98%	94%	70%	87%	88%	92%	86%	95%	69%	87%	73%	96%	85%	92%	82%	65%	88%	76%
77.0%	79%	80%	77%	80%	73%	65%	85%	76%	74%	81%	76%	81%	77%	84%	77%	75%	75%	76%	78%		72%
85.4%		95%	85%	85%	71%	90%	81%	64%	87%	85%	91%	91%	91%	93%	93%	87%	89%	83%	78%		84%

Model Similarity Dendrogram

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