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 Environment%3Asuburban C5 - Run c6daff9...

Global Dialogues GD3 - Suburban (5 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

Efficiency & Succinctness

Reasoning

Best Models (Coverage)

1.Claude 3.7 Sonnet
83.7%
2.GPT 5.1
83.5%
3.GPT 4.1 Mini
83.5%
4.Claude Haiku 4.5
83.1%
5.GPT 5
83.0%

🔀 Least Similar Models

Claude Sonnet 4.5vsQwen3 32b

72.8% similarity

👯 Most Similar Models

Claude Haiku 4.5vsQwen3 30b A3B Instruct 2507

89.5% 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 4.1 Fast
Score	1st 83.7%	4th 83.1%	7th 81.9%	6th 82.2%	8th 81.5%	21st 75.6%	10th 80.6%	14th 79.2%	13th 79.5%	11th 79.8%	3rd 83.5%	17th 78.3%	9th 81.4%	12th 79.6%	5th 83.0%	2nd 83.5%	16th 78.8%	20th 75.8%	15th 79.0%	19th 77.0%	18th 78.2%
83.6%	93%	82%	72%	85%	90%	75%	78%	81%	80%	80%	86%	83%	88%	88%	87%	87%	87%	82%	86%	86%	80%
86.0%	84%	77%	94%	94%	64%	92%	86%	78%	64%	89%	93%	93%	86%	91%	85%	85%	93%		88%	92%	92%
73.6%	74%	71%	80%	80%	61%	77%	71%	74%	73%	82%	80%	74%	74%	74%	69%	71%	76%	78%	68%	69%	69%
87.9%	93%	84%	90%	89%	92%	84%	93%	87%	91%	92%	88%	86%	90%	81%	92%	94%	85%	84%	85%	77%	89%
89.1%	86%	100%	85%	85%	90%	81%	85%	95%	85%	91%	97%	97%	94%	97%	90%	97%	87%	91%	78%	84%	77%
87.7%	86%	91%	84%	91%	89%	90%	89%	96%	90%	86%	86%	90%	92%	78%	77%	87%	82%	98%	86%	81%	92%
79.0%	78%	76%	82%	93%	79%	70%	78%	93%	79%	68%	89%	73%	73%	73%	75%	83%	90%		73%	87%	68%
82.8%	80%	84%	76%	74%	80%	57%	84%	93%	91%	77%	88%	81%	77%	80%	93%	91%	94%	84%	81%	86%	88%
79.9%	86%	77%	73%	68%	81%	58%	75%	76%	74%	86%	82%	77%	82%	82%	91%	86%	95%	78%	79%	84%	88%
86.4%	91%	92%	84%	89%	89%	93%	89%	77%	86%	86%	88%	92%	84%	88%	90%	91%	78%	70%	89%	84%	84%
82.1%	92%	89%	90%	83%	81%	90%	86%	83%	88%	78%	89%	90%	67%	79%	77%	80%	74%	59%	82%	87%	81%
88.6%	91%	88%	93%	90%	91%	91%	83%	88%	87%	90%	89%	89%	90%	88%	92%	91%	84%	88%	87%	85%	86%
86.6%	87%	93%	79%	87%	92%	91%	88%	80%	86%	86%	94%	69%	88%	89%	87%	92%	76%		91%	93%	84%
74.7%	84%	85%	82%	82%	86%	65%	87%	70%	77%	70%	85%	66%	73%	85%	80%	72%	71%	54%	85%	51%	59%
87.2%	92%	94%	82%	81%	93%	88%	86%	79%	87%	87%	90%	78%	95%	88%	91%	91%	81%		87%	82%	92%
77.7%	88%	79%	85%	88%	83%	62%	74%	91%	70%	74%	73%	83%	80%	72%	90%	85%	79%	64%	77%	65%	69%
63.8%	69%	81%	86%	70%	58%	55%	65%	46%	63%	64%	67%	55%	62%	63%	62%	71%	47%	55%	67%	63%	71%
64.2%	73%	65%	62%	69%	60%	50%	55%	66%	59%	61%	59%	70%	68%	59%	69%	68%	78%	67%	62%	59%	69%
63.8%	77%	49%	91%	67%	68%	48%	66%	62%	64%	74%	62%	50%	60%	56%	95%	65%	56%	58%	52%	65%	54%
85.5%	84%	75%	81%	81%	90%	81%	89%	80%	91%	81%	94%	88%	84%	89%	87%	88%	79%	81%	90%	91%	91%
86.9%	86%	90%	85%	84%	89%	73%	96%	77%	93%	86%	92%	91%	94%	91%	80%	89%	78%	87%	83%	92%	88%
86.8%	86%	92%	83%	82%	95%	86%	90%	81%	88%	86%	95%	82%	92%	88%	89%	90%	84%	86%	80%	89%	79%
78.9%	80%	80%	78%	79%	83%	84%	80%	85%	78%	78%	91%	65%	80%	84%	72%	75%	83%	84%	79%	73%	65%
84.9%	88%	90%	89%	88%	91%	90%	77%	83%	78%	89%	90%	69%	90%	82%	95%	93%	77%	75%	83%	78%	88%
77.6%	86%	81%	80%	80%	83%	76%	83%	78%	74%	69%	89%	86%	75%	86%	68%	80%	75%	77%	81%	57%	65%
77.2%	84%	78%	76%	80%	83%	68%	74%	66%	73%	80%	79%	83%	82%	78%	75%	77%	80%	83%	78%	80%	64%
71.3%	85%	75%	72%	76%	75%	61%	63%	66%	70%	64%	63%	73%	79%	62%	78%	79%	63%	80%	70%	74%	70%
81.9%	86%	84%	78%	85%	91%	61%	82%	90%	88%	83%	78%	85%	84%	65%	95%	91%	73%	80%	74%	85%	82%
72.2%	75%	89%	82%	83%	76%	69%	84%	69%	69%	67%	70%	65%	68%	68%	67%	75%	68%	69%	67%	69%	68%
74.1%	73%	86%	76%	79%	88%	73%	65%	85%	69%	69%	76%	67%	72%	65%	77%	79%	83%	69%	76%	62%	68%
85.5%	90%	84%	82%	82%	92%	90%	83%	78%	85%	88%	90%	85%	87%	88%	89%	92%	77%	73%	90%	79%	91%
73.7%	75%	76%	67%	67%	86%	70%	76%	73%	74%	65%	67%	73%	73%	73%	75%	80%	71%	69%	79%	79%	79%
65.4%	64%	63%	72%	72%	54%	69%	63%	66%	65%	73%	72%	65%	65%	66%	61%	64%	68%	70%	60%	61%	61%
83.1%	90%	87%	85%	90%	93%	71%	86%	86%	92%	83%	91%	77%	78%	69%	89%	87%	98%	80%	68%	61%	84%
73.4%	86%	86%	67%	68%	56%	78%	66%	64%	65%	69%	67%	73%	82%	92%	76%	69%	68%	74%	86%	91%	58%
82.0%	88%	87%	93%	91%	70%	70%	87%	90%	76%	89%	83%	73%	88%	73%	90%	86%	81%	71%	73%	81%	82%
86.8%	93%	93%	91%	88%	91%	82%	91%	74%	87%	84%	89%	86%	92%	90%	85%	86%	81%	68%	89%	90%	93%
86.0%	87%	95%	92%	92%	89%	92%	90%	97%	90%	88%	95%	74%	97%	84%	91%	96%	74%	65%	90%	47%	80%
83.5%	95%	84%	90%	90%	77%	75%	88%	94%	84%	88%	85%	80%	82%	77%	92%	89%	84%	61%	73%	78%	88%
95.7%	99%	96%	95%	95%	86%	98%	96%	99%	98%	93%	95%	98%	98%	99%	93%	96%	99%	97%	93%	93%	93%
88.0%	90%	93%	87%	96%	95%	65%	92%	83%	94%	94%	92%	74%	86%	82%	95%	91%	87%	87%	86%	87%	92%
75.0%	74%	79%	73%	71%	70%	71%	78%	74%	78%	84%	74%	76%	78%	81%	80%	76%	75%	72%	72%	67%	71%
72.7%	53%	75%	76%	69%	76%	79%	69%	54%	64%	60%	87%	83%	72%	81%	77%	77%	71%	88%	75%	69%	71%

Model Similarity Dendrogram

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