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 AgeGroup%3A18 25 C5 - Run 44a0d1a...

Global Dialogues GD3 - 18-25 (5 context Qs)

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

Efficiency & Succinctness

AI Safety & Robustness

Best Models (Coverage)

1.Gemini 2.5 Flash
84.9%
2.Claude 3.7 Sonnet
84.0%
3.Claude Sonnet 4.5
83.6%
4.GPT 4.1 Mini
83.0%
5.GPT 5.1
82.8%

🔀 Least Similar Models

Claude Haiku 4.5vsQwen3 32b

72.1% similarity

👯 Most Similar Models

Claude Sonnet 4vsGPT 4.1

88.2% 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	2nd 84.0%	7th 82.5%	6th 82.8%	3rd 83.6%	1st 84.9%	16th 77.0%	9th 81.3%	12th 80.6%	10th 81.0%	11th 80.9%	4th 83.0%	20th 75.6%	7th 82.5%	14th 78.8%	13th 80.2%	5th 82.8%	17th 76.8%	18th 76.7%	15th 78.2%	19th 76.3%	21st 73.3%
83.1%	93%	88%	80%	89%	85%	77%	80%	78%	79%	80%	88%	72%	88%	86%	87%	93%	82%	86%	82%	76%	77%
86.3%	88%	90%	93%	86%	88%	91%	85%	86%	88%	93%	89%	81%	92%	83%	87%	91%	82%	82%	92%	85%	61%
71.4%	71%	65%	77%	77%	70%	73%	66%	71%	68%	76%	74%	66%	73%	68%	69%	73%	78%	84%	70%	62%	69%
90.8%	95%	84%	94%	89%	94%	91%	94%	95%	90%	92%	94%	90%	92%	89%	94%	95%	84%	86%	87%	86%	91%
90.0%	98%	98%	83%	88%	87%	98%	90%	98%	92%	91%	96%	95%	91%	89%	95%	92%	84%	90%	83%		63%
81.0%	83%	88%	84%	87%	89%	84%	84%	90%	83%	78%	86%	85%	84%	71%	73%	77%	78%	88%	75%	67%	68%
79.0%	80%	79%	81%	87%	89%	74%	85%	86%	84%	78%	88%	61%	79%	78%	78%	76%	93%	72%	84%	56%	72%
78.7%	84%	75%	73%	85%	73%	54%	77%	95%	86%	85%	81%	82%	81%	73%	87%	82%	80%	82%	68%	78%	72%
87.4%	81%	88%	90%	88%	99%	73%	79%	97%	83%	89%	95%	87%	94%	94%	87%	86%	90%	87%	84%	76%	88%
83.3%	93%	94%	81%	86%	81%	89%	84%	82%	80%	85%	80%	90%	83%	80%	83%	86%	62%	79%	85%	74%	93%
86.0%	94%	93%	95%	95%	82%	92%	92%	85%	92%	78%	93%	79%	77%	69%	83%	87%	85%	75%	85%		89%
90.1%	87%	94%	98%	91%	89%	94%	90%	87%	86%	93%	83%	91%	93%	87%	93%	95%	85%	81%	93%	94%	89%
83.2%	80%	88%	80%	82%	86%	85%	87%	79%	87%	86%	92%	71%	91%	90%	94%	92%	82%	79%	81%	85%	50%
77.3%	84%	83%	85%	79%	85%	74%	89%	69%	78%	72%	80%	72%	86%	88%	77%	83%	64%	62%	85%	64%	65%
86.8%	88%	91%	92%	89%	94%	86%	89%	83%	90%	84%	91%	78%	91%	86%	85%	84%	84%	87%	83%	80%
83.6%	92%	90%	93%	89%	93%	75%	84%	76%	77%	89%	83%	79%	93%	83%	94%	91%	74%	71%	86%	71%	73%
62.9%	69%	70%	71%	70%	60%	54%	67%	46%	56%	60%	70%	55%	52%	54%	64%	71%	59%	56%	70%	71%	76%
71.2%	80%	68%	72%	84%	90%	57%	61%	68%	63%	70%	59%	65%	78%	55%	79%		88%	53%	70%	85%	80%
61.0%	66%	47%	77%	67%	69%	53%	64%	57%	68%	64%	67%	45%	57%	56%	74%	86%	60%	50%	45%	59%	50%
85.0%	93%	70%	86%	90%	96%	87%	92%	84%	88%	88%	92%	77%	91%	89%	78%	85%	82%	74%	87%	82%	75%
86.3%	86%	91%	85%	86%	94%	78%	95%	80%	93%	88%	94%	93%	97%	91%	83%	82%	88%	82%	77%	70%	79%
84.9%	84%	89%	79%	82%	90%	81%	89%	89%	92%	80%	92%	69%	94%	88%	85%	91%	85%	86%	72%	81%
71.7%	65%	64%	72%	71%	83%	85%	86%	85%	67%	70%	85%	56%	71%	87%	65%	71%	68%	63%	65%	68%	58%
84.0%	91%	84%	83%	87%	88%	87%	84%	82%	88%	87%	92%	75%	89%	92%	91%	90%	86%	73%	78%	56%	81%
79.1%	78%	85%	83%	80%	91%	77%	82%	70%	76%	70%	91%	71%	74%	90%	69%	83%	71%	79%	89%	83%	70%
72.4%	78%	73%	77%	77%	81%	71%	73%	63%	74%	70%	75%	68%	73%	79%	76%	73%	66%	88%	79%	53%	54%
72.2%	85%	72%	77%	79%	77%	56%	67%	67%	70%	80%	64%	75%	78%	59%	82%	79%	78%	60%	69%	77%	65%
78.7%	83%	83%	75%	79%	83%	56%	73%	87%	84%	82%	79%	86%	80%	64%	94%	89%	67%	89%	63%	82%	74%
67.4%	82%	91%	77%	78%	78%	63%	85%	61%	64%	60%	65%	56%	58%	57%	64%	63%	58%	61%	59%	69%	67%
76.0%	74%	85%	78%	85%	91%	67%	63%	79%	79%	74%	79%	58%	78%	76%	81%	63%	71%	85%	80%	77%	72%
84.1%	87%	86%	88%	89%	89%	82%	83%	81%	84%	88%	86%	63%	87%	84%	86%	89%	81%	84%	86%	81%	83%
74.9%	75%	82%	69%	69%	76%	73%	80%	76%	78%	70%	73%	80%	73%	78%	78%	73%	68%	62%	77%	84%	78%
65.4%	65%	59%	71%	71%	64%	67%	60%	65%	62%	70%	67%	60%	67%	62%	63%	67%	72%	78%	64%	57%	63%
84.6%	93%	86%	86%	92%	87%	75%	89%	88%	93%	92%	96%	63%	85%	79%	88%	92%	91%	60%	72%	93%	76%
80.5%	90%	82%	80%	79%	90%	91%	63%	90%	71%	81%	59%	73%	91%	91%	80%	71%	80%	86%	89%	87%	66%
83.3%	94%	90%	96%	96%	78%	74%	90%	92%	87%	95%	81%	86%	89%	72%	81%	81%	76%	75%	68%	76%	73%
82.7%	86%	92%	86%	86%	88%	78%	92%	81%	91%	85%	94%	87%	91%	86%	0%	94%	88%	85%	86%	92%	69%
86.3%	97%	96%	94%	94%	89%	97%	90%	95%	94%	98%	89%	73%	98%	71%	90%	82%	58%	63%	88%	76%	80%
81.0%	93%	80%	87%	84%	84%	68%	82%	95%	83%	79%	79%	83%	80%	74%	92%	86%	72%	76%	65%	83%	76%
94.5%	99%	95%	92%	92%	99%	96%	97%	99%	99%	93%	96%	97%	96%	99%	99%	96%	91%	85%	99%	93%	73%
83.2%	82%	82%	83%	82%	97%	76%	77%	92%	94%	80%	89%	86%	76%	80%	84%	80%	62%	82%	82%	92%	90%
80.2%	81%	82%	78%	83%	84%	73%	81%	82%	77%	85%	75%	89%	81%	79%	82%	82%	77%	75%	83%	75%	80%
75.6%	64%	77%	78%	77%	72%	77%	78%	56%	63%	71%	90%	81%	77%	81%	75%	75%	72%	97%	77%	74%	76%

Model Similarity Dendrogram

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