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 Environment%3Asuburban C10 - Run d7a9369...

Global Dialogues GD3 - Suburban (10 context Qs)

DTEF: Predict response distributions for Suburban. 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
84.7%
2.Claude Haiku 4.5
84.3%
3.Claude Sonnet 4
84.1%
4.GPT 5
83.8%
5.GPT 5.1
83.6%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT OSS 20b

70.9% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude 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 84.7%	2nd 84.3%	3rd 84.1%	19th 77.4%	7th 83.0%	17th 78.8%	10th 81.1%	11th 81.1%	12th 81.0%	6th 83.4%	9th 81.9%	14th 79.4%	8th 82.2%	16th 78.9%	4th 83.8%	5th 83.6%	15th 79.0%	21st 74.9%	13th 80.4%	18th 77.7%	20th 77.1%
85.2%	89%	89%	86%	83%	89%	80%	84%	89%	87%	84%	87%	88%	90%	85%	84%	88%	85%	76%	83%	85%	78%
88.2%	81%	85%	94%	94%	82%	95%	81%	84%	75%	91%	94%	87%	88%	90%	92%	90%	92%	86%	95%	83%	93%
66.1%	68%	63%	74%	0%	61%	77%	65%	73%	65%	77%	73%	80%	74%	72%	65%	68%	66%	70%	68%	61%	69%
90.0%	93%	82%	92%	92%	93%	85%	95%	90%	92%	93%	86%	92%	90%	79%	93%	93%	87%	86%	89%	96%	92%
87.7%	78%	90%	85%	85%	91%	83%	86%	88%	85%	96%	96%	92%	95%	95%	91%	93%	90%	79%	78%	88%	78%
86.1%	86%	92%	84%	91%	92%	95%	89%	92%	88%	81%	85%	95%	87%	78%	84%	86%	96%	80%	80%	74%	74%
88.9%	88%	91%	91%	91%	86%	92%	86%	95%	92%	88%	86%	92%	86%	89%	93%	94%	91%	89%	87%	91%	68%
78.9%	82%	85%	77%	76%	80%	55%	77%	88%	87%	81%	74%	81%	83%	72%	91%	87%	85%	76%	71%	75%	74%
81.4%	86%	77%	73%	77%	88%	64%	75%	74%	74%	86%	82%	86%	82%	83%	91%	92%	89%	93%	79%	75%	84%
89.8%	91%	87%	92%	91%	92%	94%	86%	80%	89%	91%	92%	92%	92%	92%	85%	87%	80%	92%	92%	94%	94%
83.4%	92%	90%	90%	91%	89%	86%	90%	85%	90%	73%	93%	89%	76%	87%	79%	75%	80%	51%	84%	78%
86.0%	91%	90%	93%	93%	91%	89%	82%	91%	90%	74%	84%	90%	78%	85%	86%	83%	82%	67%	92%	80%	94%
81.7%	80%	83%	83%	92%	91%	92%	76%	75%	82%	84%	89%	74%	82%	93%	83%	79%	76%	72%	86%	72%	72%
86.3%	86%	97%	94%	96%	85%	79%	95%	90%	92%	93%	82%	66%	93%	66%	82%	94%	85%	79%	87%	92%	80%
86.5%	91%	94%	82%	82%	92%	90%	90%	82%	81%	88%	89%	85%	94%	90%	94%	93%	72%	68%	84%	88%
82.8%	90%	84%	92%	90%	86%	76%	83%	89%	76%	84%	80%	82%	85%	76%	81%	87%	87%	81%	83%	80%	67%
61.3%	69%	81%	70%	70%	49%	64%	65%	46%	63%	57%	57%	66%	47%	53%	64%	66%	55%	70%	68%	51%	56%
69.5%	75%	73%	71%	80%	74%	51%	62%	76%	69%	66%	61%	71%	70%	60%	74%	82%	84%	58%	77%	62%	63%
70.7%	85%	64%	91%	70%	69%	51%	72%	72%	73%	88%	64%	50%	77%	74%	86%	86%	72%	59%	52%	63%	67%
84.6%	95%	96%	89%	92%	93%	75%	98%	75%	77%	94%	79%	76%	85%	77%	88%	95%	77%	69%	77%	76%	93%
87.2%	89%	92%	87%	85%	95%	77%	92%	89%	93%	86%	94%	86%	94%	91%	86%	81%	89%	79%	81%		78%
86.1%	88%	88%	84%	83%	84%	86%	88%	88%	88%	91%	90%	84%	95%	91%	91%	94%	87%	66%	85%	82%	75%
81.0%	86%	80%	79%	80%	82%	88%	87%	82%	77%	91%	87%	87%	79%	69%	78%	73%	78%	77%	83%	78%	79%
83.9%	92%	94%	88%	94%	91%	90%	78%	78%	85%	87%	92%	69%	86%	82%	85%	85%	76%	76%	82%	76%	76%
87.0%	88%	92%	89%	92%	89%	86%	91%	89%	94%	94%	90%	68%	90%	68%	83%	91%	80%	87%	91%	92%	82%
76.6%	84%	80%	81%	82%	83%	74%	75%	74%	76%	84%	78%	75%	82%	82%	75%	78%	76%	70%	74%	72%	53%
75.8%	84%	82%	76%	80%	80%	67%	70%	82%	78%	80%	67%	79%	78%	68%	85%	72%	67%	80%	80%	76%	61%
80.6%	91%	88%	78%	83%	93%	63%	80%	93%	90%	83%	77%	72%	82%	70%	92%	86%	82%	80%	67%	84%	59%
72.3%	77%	82%	89%	84%	77%	67%	77%	68%	69%	69%	67%	74%	68%	64%	73%	69%	67%	69%	68%	69%
77.2%	75%	87%	86%	84%	84%	74%	63%	85%	80%	79%	76%	68%	74%	65%	85%	74%	89%	65%	86%	65%
83.8%	87%	84%	80%	82%	89%	91%	83%	79%	80%	85%	89%	89%	85%	93%	91%	92%	72%	65%	86%	85%	72%
73.3%	73%	84%	73%	0%	86%	70%	82%	75%	82%	70%	74%	67%	73%	76%	78%	79%	82%	78%	79%	79%	79%
59.8%	66%	55%	65%	0%	54%	69%	57%	64%	57%	68%	65%	72%	65%	63%	61%	60%	58%	61%	60%	62%	73%
81.0%	92%	79%	88%	87%	92%	71%	75%	83%	83%	83%	79%	74%	78%	74%	83%	86%	80%	82%	73%	74%	85%
75.6%	74%	87%	74%	81%	73%	75%	64%	66%	65%	62%	65%	82%	73%	77%	77%	76%	79%	72%	92%	85%	88%
82.0%	91%	87%	93%	89%	76%	82%	88%	89%	76%	90%	85%	73%	85%	76%	79%	80%	81%	76%	74%	74%	78%
86.0%	93%	83%	89%	90%	93%	91%	86%	81%	87%	90%	93%	84%	90%	92%	95%	93%	76%	75%	85%	59%	80%
89.6%	92%	91%	97%	97%	90%	97%	91%	92%	90%	96%	96%	75%	97%	87%	97%	99%	74%	56%	90%	86%	91%
82.6%	99%	86%	90%	90%	80%	73%	88%	91%	87%	93%	82%	78%	85%	75%	90%	82%	72%	65%	74%	80%	75%
89.2%	90%	88%	98%	0%	86%	98%	90%	97%	90%	98%	98%	95%	98%	96%	94%	93%	90%	94%	93%	95%	93%
86.6%	90%	85%	87%	91%	96%	80%	93%	82%	91%	90%	88%	74%	83%	81%	90%	90%	71%	82%	94%	89%	91%
73.0%	78%	76%	71%	71%	70%	67%	78%	72%	74%	74%	71%	79%	72%	76%	78%	73%	72%	74%	72%	66%	70%
72.4%	65%	84%	73%	69%	54%	79%	76%	53%	63%	73%	86%	76%	70%	80%	73%	71%	66%	92%	75%	72%	71%

Model Similarity Dendrogram

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