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 AgeGroup%3A46 55 C10 - Run 6b6c306...

Global Dialogues GD3 - 46-55 (10 context Qs)

DTEF: Predict response distributions for 46-55. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

Best Models (Coverage)

1.Claude 3.7 Sonnet
84.5%
2.GPT 5.1
84.1%
3.GPT 5
84.0%
4.Claude Haiku 4.5
84.0%
5.Claude Sonnet 4
82.9%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

71.1% similarity

👯 Most Similar Models

Llama 4 MaverickvsGPT 4.1

88.6% 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 84.5%	4th 84.0%	5th 82.9%	20th 76.0%	17th 78.3%	19th 76.4%	9th 81.5%	6th 82.4%	11th 80.7%	7th 81.8%	10th 81.2%	16th 78.5%	8th 81.5%	18th 76.8%	3rd 84.0%	2nd 84.1%	13th 80.3%	21st 75.7%	12th 80.5%	14th 79.3%	15th 78.8%
86.1%	87%	93%	80%	81%	80%	72%	88%	90%	92%	77%	90%	77%	88%	78%	93%	94%	95%	90%	84%	93%
86.8%	91%	84%	95%	93%	61%	97%	88%	88%	81%	95%	95%	90%	91%	86%	95%	94%	81%	69%	89%	74%
64.6%	66%	67%	78%	0%	60%	75%	70%	70%	63%	70%	72%	72%	64%	64%	64%	70%	65%	75%	62%
87.2%	92%	80%	88%	92%	82%	83%	88%	88%	86%	90%	83%	95%	91%	74%	88%	91%	88%	92%	85%
91.7%	91%	96%	94%	97%	86%	91%	95%	91%	90%	97%	89%	83%	92%	90%	88%	92%	99%	87%	95%
91.3%	96%	97%	95%	97%	96%	91%	92%	95%	89%	90%	92%	86%	84%	84%	88%	94%	89%	88%	88%	94%
88.7%	90%	90%	89%	87%	78%	93%	90%	94%	92%	91%	93%	88%	91%	92%	96%	91%	88%	82%	84%	75%
75.6%	78%	81%	75%	75%	69%	53%	73%	82%	75%	78%	74%	77%	81%	69%	78%	85%	83%	74%	72%	81%
84.2%	89%	83%	77%	77%	77%	72%	81%	85%	82%	89%	85%	90%	88%	88%	83%	89%	98%	86%	84%	81%
89.4%	91%	85%	95%	94%	95%	91%	84%	82%	95%	94%	76%	95%	94%	95%	84%	94%	91%	69%	95%		89%
76.3%	78%	81%	85%	85%	74%	83%	76%	84%	73%	70%	84%	84%	72%	73%	81%	77%	56%	49%	88%	73%
75.6%	81%	78%	80%	81%	79%	75%	78%	85%	79%	67%	74%	76%	61%	66%	77%	74%	72%	65%	81%	82%
81.7%	87%	91%	85%	89%	81%	90%	82%	74%	77%	88%	83%	79%	83%	91%	86%	79%	79%	56%	84%	70%
85.9%	77%	80%	83%	83%	82%	92%	84%	89%	88%	88%	89%	81%	91%	82%	88%	86%	80%	80%	99%	96%
84.4%	80%	90%	86%	84%	89%	78%	88%	87%	88%	84%	86%	88%	91%	84%	84%	85%	79%	74%	81%	82%
84.3%	90%	85%	88%	92%	87%	69%	83%	90%	84%	80%	83%	75%	89%	70%	90%	88%	81%	88%	87%	86%
64.3%	72%	79%	71%	72%	59%	57%	67%	57%	65%	60%	66%	73%	51%	56%	67%	75%	52%	57%	62%	67%
63.6%	69%	64%	65%	70%	73%	45%	55%	71%	64%	57%	55%	58%	68%	48%	74%	69%	72%	58%	62%	75%
64.2%	72%	50%	69%	58%	72%	43%	61%	67%	72%	81%	53%	38%	75%	60%	77%	82%	63%	62%	51%	78%
84.5%	95%	93%	94%	89%	94%	74%	96%	84%	76%	94%	76%	76%	86%	74%	92%	93%	74%	80%	76%	73%
82.8%	87%	90%	81%	81%	87%	71%	85%	87%	85%	83%	85%	80%	84%	73%	95%	89%	79%	80%	75%	78%
84.5%	85%	85%	81%	81%	87%	79%	90%	85%	83%	85%	81%	82%	90%	86%	89%	86%	85%	88%	80%	83%
77.7%	81%	79%	79%	79%	81%	86%	82%	81%	75%	86%	80%	79%	62%	77%	74%	75%	71%	72%	80%	74%
84.4%	91%	94%	87%	84%	90%	82%	84%	82%	82%	91%	90%	68%	84%	87%	90%	87%	85%	81%	73%	76%
83.5%	83%	80%	80%	83%	84%	82%	82%	86%	85%	86%	80%	74%	86%	78%	83%	84%	86%	90%	91%	87%
84.5%	86%	83%	85%	85%	89%	79%	82%	77%	85%	92%	86%	86%	89%	78%	93%	81%	86%	82%	84%	82%
77.2%	83%	81%	79%	75%	79%	56%	73%	85%	79%	74%	58%	72%	84%	66%	88%	83%	85%	88%	79%	76%
81.1%	88%	88%	81%	88%	71%	65%	84%	92%	86%	80%	81%	74%	82%	66%	90%	86%	84%	80%	75%	81%
74.4%	78%	88%	85%	90%	82%	70%	80%	69%	72%	70%	67%	74%	69%	63%	75%	74%	70%	67%	74%	73%	72%
75.8%	81%	81%	86%	88%	90%	62%	68%	84%	81%	77%	76%	51%	72%	60%	82%	76%	75%	76%	71%	80%
84.5%	90%	84%	83%	88%	82%	88%	86%	80%	85%	86%	89%	88%	83%	89%	88%	92%	82%	71%	90%	78%	72%
78.5%	83%	84%	72%	0%	92%	76%	81%	81%	88%	81%	79%	79%	87%	87%	79%	82%	83%	85%	89%	81%
60.9%	65%	63%	75%	0%	56%	71%	66%	66%	60%	66%	68%	68%	60%	61%	59%	61%	64%	64%	59%	66%
77.5%	85%	74%	81%	86%	81%	68%	69%	80%	79%	83%	74%	74%	76%	69%	84%	84%	81%	80%	71%	73%	76%
77.2%	87%	92%	77%	88%	46%	80%	73%	68%	69%	66%	72%	79%	81%	81%	73%	81%	81%	82%	92%	75%	78%
83.5%	93%	92%	94%	90%	60%	84%	91%	96%	87%	84%	90%	81%	90%	71%	74%	80%	82%	71%	79%	81%
87.8%	92%	93%	88%	88%	91%	86%	92%	83%	89%	93%	92%	89%	90%	81%	91%	86%	88%	70%	84%	89%
87.5%	87%	92%	91%	91%	77%	92%	84%	88%	86%	85%	92%	79%	91%	86%	96%	99%	76%	79%	92%
82.3%	91%	89%	82%	82%	88%	68%	87%	88%	82%	83%	84%	82%	84%	72%	92%	86%	81%	74%	70%	80%
88.8%	92%	95%	93%	0%	87%	97%	98%	98%	91%	98%	100%	100%	92%	92%	87%	93%	96%	96%	90%	81%
84.2%	94%	93%	83%	88%	57%	74%	92%	94%	85%	90%	95%	77%	91%	84%	94%	94%	84%	41%	88%	87%
82.3%	88%	83%	80%	74%	83%	71%	80%	89%	77%	78%	86%	85%	75%	91%	87%	79%	88%	82%	87%	80%	86%
72.0%	71%	83%	71%	61%	54%	76%	76%	51%	69%	60%	89%	75%	73%	79%	78%	76%	74%	73%	80%	71%

Model Similarity Dendrogram

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