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 C5 Dtef Global Dialogues Gd3 AiConcern%3Aequally Concerned And Excited C5 - Run 15e0cb8...

Global Dialogues GD3 - Equally concerned and excited (5 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Demographic & Cultural Nuance

Best Models (Coverage)

1.Claude 3.7 Sonnet
85.7%
2.Claude Sonnet 4.5
85.1%
3.GPT 5
84.5%
4.Claude Haiku 4.5
84.1%
5.GPT 5.1
83.5%

🔀 Least Similar Models

Claude Sonnet 4vsGPT 4o Mini

73.7% similarity

👯 Most Similar Models

Claude Haiku 4.5vsClaude Sonnet 4.5

90.0% 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 85.7%	4th 84.1%	6th 83.2%	2nd 85.1%	8th 82.0%	14th 77.7%	9th 81.4%	10th 81.0%	12th 80.6%	11th 80.7%	7th 83.1%	21st 65.1%	13th 80.3%	20th 69.6%	3rd 84.5%	5th 83.5%	15th 77.6%	19th 73.1%	18th 74.2%	17th 76.0%	16th 77.0%
84.7%	92%	85%	89%	94%	81%	80%	90%	89%	90%	84%	88%	88%	89%	49%	95%	89%	83%	76%	71%	83%	93%
82.8%	86%	81%	86%	91%	57%	73%	80%	81%	72%	91%	92%	86%	92%	72%	92%	93%	85%	70%	92%	77%	89%
69.9%	66%	81%	83%	80%	70%	94%	70%	74%	62%	62%	83%	62%	62%	77%	62%	66%	66%	62%	62%	62%	62%
89.9%	93%	87%	90%	90%	91%	86%	88%	91%	92%	90%	94%	92%	90%	86%	93%	99%	87%	85%	88%	87%	89%
87.8%	94%	96%	95%	91%	85%	81%	86%	97%	91%	86%	89%	76%	98%	82%	93%	91%	87%	83%	89%	89%	64%
87.7%	85%	91%	88%	90%	99%	89%	89%	96%	95%	86%	91%	74%	86%	93%	76%	85%	87%	88%	85%	74%	95%
80.3%	82%	90%	82%	93%	89%	69%	90%	94%	87%	82%	90%	40%	72%	30%	86%	86%	82%	86%	87%	78%	91%
82.6%	88%	86%	82%	86%	83%	69%	89%	93%	92%	83%	92%	80%	82%	68%	88%	87%	81%	80%	73%	75%	78%
84.2%	86%	84%	84%	80%	96%	69%	79%	94%	79%	91%	85%	70%	85%	76%	84%	78%	92%	95%	84%	86%	91%
90.0%	98%	95%	87%	91%	86%	97%	91%	77%	88%	91%	90%	94%	87%	91%	89%	93%	76%	90%	91%		98%
79.7%	89%	91%	94%	91%	78%	88%	81%	86%	88%	80%	86%	66%	70%	85%	82%	86%	77%	51%	82%	66%	57%
89.8%	91%	93%	89%	96%	90%	94%	86%	96%	83%	92%	88%	95%	90%	92%	90%	88%	91%	86%	90%	80%	86%
84.9%	82%	96%	81%	86%	88%	79%	81%	81%	89%	92%	95%	65%	91%	79%	96%	93%	82%	71%	85%	77%	93%
78.4%	88%	82%	84%	84%	83%	61%	86%	76%	85%	79%	75%	77%	82%	30%	86%	86%	84%	69%	88%	81%	81%
84.6%	91%	88%	93%	86%	93%	89%	87%	85%	87%	85%	87%	78%	90%	80%	89%	85%	85%	69%	83%	84%	63%
79.4%	95%	78%	94%	96%	83%	71%	83%	91%	80%	79%	87%	81%	84%	54%	87%	87%	75%	74%	51%	77%	61%
65.9%	74%	91%	77%	74%	67%	57%	69%	50%	67%	61%	71%	36%	46%	77%	80%	74%	56%	41%	71%	71%	74%
71.0%	83%	75%	69%	75%	84%	56%	65%	80%	69%	63%	70%	71%	78%	78%	70%	76%	69%	56%	73%	67%	65%
58.6%	67%	48%	65%	67%	79%	46%	61%	63%	58%	59%	58%	48%	57%	49%	82%	74%	54%	53%	40%	54%	48%
87.5%	94%	91%	87%	92%	93%	84%	87%	88%	89%	91%	91%	79%	92%	53%	92%	88%	89%	82%	93%	93%	90%
82.0%	87%	87%	91%	93%	84%	94%	93%	80%	89%	91%	89%	20%	93%	63%	92%	86%	80%	69%	75%	79%	88%
84.4%	83%	95%	85%	84%	89%	88%	90%	80%	86%	84%	86%	76%	89%	81%	92%	94%	87%	70%	76%	84%	73%
78.4%	72%	74%	79%	79%	87%	86%	86%	82%	77%	77%	89%	66%	82%	78%	82%	79%	72%	73%	74%	73%	79%
81.3%	85%	94%	90%	92%	87%	84%	79%	82%	80%	92%	89%	13%	81%	72%	92%	94%	84%	74%	81%	82%
70.8%	87%	89%	83%	83%	82%	64%	72%	73%	82%	76%	83%	9%	76%	38%	80%	86%	68%	72%	27%	75%	82%
72.3%	74%	74%	77%	80%	77%	61%	65%	67%	71%	87%	77%	69%	80%	36%	79%	80%	71%	68%	78%	72%	75%
75.4%	83%	80%	80%	79%	77%	63%	71%	76%	73%	72%	74%	75%	77%	74%	81%	81%	74%	77%	75%	65%	77%
77.9%	90%	89%	80%	89%	92%	77%	82%	97%	89%	75%	90%	41%	87%	82%	88%	83%	86%	81%	0%	66%	72%
75.1%	86%	90%	86%	86%	87%	72%	86%	71%	70%	68%	73%	71%	71%	66%	74%	74%	67%	66%	67%	73%	73%
75.4%	81%	82%	87%	95%	91%	67%	69%	85%	84%	66%	86%	75%	79%	63%	76%	71%	73%	74%	69%	58%	53%
79.0%	84%	85%	82%	82%	82%	85%	83%	79%	82%	89%	89%	57%	90%	77%	86%	92%	80%	76%	85%	72%	21%
75.5%	78%	66%	64%	66%	77%	53%	77%	73%	86%	86%	64%	86%	86%	32%	86%	81%	81%	86%	86%	86%	86%
63.5%	62%	74%	76%	73%	63%	87%	63%	67%	55%	55%	76%	55%	55%	84%	55%	59%	55%	55%	55%	55%	55%
83.6%	92%	87%	83%	88%	76%	87%	83%	93%	94%	80%	88%	84%	71%	66%	87%	89%	88%	88%	75%	79%	78%
77.5%	92%	86%	81%	83%	59%	87%	71%	78%	76%	85%	75%	65%	88%	84%	64%	63%	65%	81%	73%	85%	87%
80.5%	90%	83%	93%	88%	72%	82%	87%	88%	81%	93%	83%	74%	87%	73%	76%	75%	78%	72%	78%	79%	58%
82.0%	88%	81%	86%	86%	93%	85%	88%	74%	87%	88%	83%	26%	89%	83%	89%	93%	91%	70%	85%	72%	86%
86.1%	94%	87%	96%	92%	88%	95%	92%	85%	87%	93%	86%	71%	94%	84%	97%	92%	69%	66%	82%	65%	94%
79.8%	97%	84%	88%	90%	78%	78%	87%	83%	86%	86%	83%	21%	83%	80%	89%	89%	80%	74%	73%	83%	63%
89.3%	97%	90%	88%	90%	98%	77%	98%	97%	90%	90%	88%	90%	90%	53%	90%	95%	94%	90%	90%	90%	90%
88.4%	87%	94%	86%	94%	94%	92%	92%	94%	85%	89%	89%	80%	80%	92%	91%	90%	80%	84%	85%	87%	92%
53.9%	100%	46%	43%	53%	43%	56%	68%	37%	44%	53%	37%	44%	37%	41%	100%	67%	48%	22%	39%		100%
77.6%	70%	89%	75%	82%	77%	87%	79%	62%	69%	66%	93%	72%	64%	89%	74%	75%	78%	87%	83%	73%	86%

Model Similarity Dendrogram

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