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%3A26 35 C10 - Run 533472f...

Global Dialogues GD3 - 26-35 (10 context Qs)

DTEF: Predict response distributions for 26-35. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Safety

Best Models (Coverage)

1.Claude Sonnet 4.5
85.7%
2.Claude 3.7 Sonnet
85.7%
3.GPT 5.1
85.2%
4.Claude Haiku 4.5
85.2%
5.GPT 4.1
83.9%

🔀 Least Similar Models

Claude Sonnet 4vsGPT OSS 20b

70.2% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

89.4% 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	2nd 85.7%	4th 85.2%	20th 77.4%	1st 85.7%	14th 80.3%	17th 79.3%	11th 81.9%	8th 83.1%	10th 82.7%	5th 83.9%	7th 83.4%	15th 79.8%	6th 83.5%	18th 79.3%	9th 83.0%	3rd 85.2%	19th 78.1%	21st 77.4%	12th 81.9%	16th 79.4%	13th 81.0%
88.5%	93%	96%	82%	92%	92%	73%	86%	95%	90%	89%	85%	90%	95%	86%	90%	93%	89%	82%	90%	88%	83%
84.5%	81%	72%	90%	92%	55%	86%	79%	87%	82%	89%	93%	89%	85%	88%	92%	95%	89%	78%	83%	78%	92%
69.8%	76%	70%	0%	73%	63%	78%	67%	76%	63%	82%	75%	75%	77%	73%	63%	73%	75%	67%	70%	98%	72%
88.0%	92%	82%	89%	89%	90%	84%	91%	90%	91%	89%	86%	89%	90%	82%	90%	92%	87%	79%	90%	87%	88%
89.8%	89%	90%	83%	88%	90%	98%	89%	88%	92%	97%	99%	93%	97%	91%	98%	94%	87%	72%	81%	92%	77%
87.2%	90%	95%	90%	88%	91%	95%	90%	93%	86%	78%	88%	74%	89%	82%	80%	81%	86%	95%	88%	80%	93%
91.3%	92%	87%	90%	89%	86%	96%	86%	94%	95%	93%	87%	91%	92%	91%	95%	95%	94%	87%	85%	96%	96%
83.0%	90%	82%	77%	79%	74%	62%	81%	96%	84%	80%	80%	81%	86%	77%	86%	91%	93%	86%	80%	82%	95%
84.9%	82%	81%	81%	83%	86%	70%	78%	81%	82%	93%	91%	90%	87%	87%	93%	94%	90%	97%	81%	74%	81%
88.6%	95%	91%	89%	92%	89%	89%	84%	85%	85%	87%	89%	89%	88%	89%	90%	90%	82%	88%	89%	89%	92%
82.8%	89%	89%	90%	90%	80%	88%	89%	89%	83%	73%	89%	90%	76%	68%	78%	81%	80%	65%	84%		84%
86.2%	91%	87%	93%	95%	95%	86%	76%	94%	86%	76%	84%	94%	70%	87%	89%	81%	74%	80%	94%	87%	91%
82.4%	79%	85%	87%	93%	86%	94%	81%	79%	87%	87%	89%	78%	91%	92%	79%	78%	72%	70%	84%	70%	70%
87.9%	92%	88%	87%	93%	92%	76%	87%	96%	94%	94%	90%	80%	94%	70%	90%	92%	81%	88%	93%	82%	86%
83.5%	90%	91%	92%	86%	91%	88%	90%	88%	90%	90%	93%	85%	91%	86%	0%	91%	74%	85%	85%	85%	83%
84.3%	95%	90%	93%	91%	88%	69%	81%	90%	87%	85%	79%	79%	90%	75%	88%	88%	78%	83%	85%	87%	69%
67.0%	73%	90%	73%	73%	67%	72%	69%	47%	66%	60%	60%	74%	58%	57%	69%	73%	56%	60%	70%	68%	71%
74.7%	88%	74%	84%	84%	71%	55%	63%	83%	71%	79%	67%	75%	78%	62%	77%	76%	81%	65%	80%	78%	78%
66.4%	66%	56%	73%	60%	61%	56%	69%	72%	86%	81%	73%	52%	70%	64%	80%	82%	64%	57%	51%	64%	57%
85.9%	93%	95%	93%	92%	89%	79%	97%	79%	77%	95%	82%	78%	87%	79%	91%	96%	78%	83%	80%	78%	83%
86.6%	88%	93%	90%	90%	96%	81%	93%	83%	92%	88%	92%	89%	95%	89%	88%	89%	67%	77%	76%	82%	80%
87.0%	88%	89%	86%	86%	83%	85%	94%	90%	89%	90%	86%	80%	90%	89%	93%	93%	76%	85%	78%	87%	90%
83.0%	82%	77%	77%	82%	93%	91%	86%	92%	80%	89%	90%	73%	82%	89%	82%	81%	75%	78%	88%	82%	74%
85.4%	92%	92%	94%	91%	91%	82%	82%	87%	85%	92%	93%	74%	88%	87%	87%	95%	76%	69%	84%	76%	76%
86.0%	89%	88%	88%	93%	92%	80%	92%	83%	93%	91%	93%	67%	88%	70%	87%	89%	91%	74%	88%		84%
76.4%	77%	79%	80%	80%	79%	73%	77%	75%	78%	81%	82%	74%	80%	84%	85%	83%	57%	70%	81%	54%	76%
76.3%	87%	78%	80%	84%	72%	58%	69%	81%	74%	78%	65%	71%	78%	64%	85%	79%	79%	88%	78%	78%	77%
82.5%	89%	97%	78%	88%	87%	67%	82%	89%	91%	83%	79%	72%	80%	68%	90%	91%	86%	80%	75%	81%	80%
77.2%	85%	92%	94%	95%	79%	71%	77%	72%	68%	72%	72%	68%	71%	69%	85%	76%	74%	76%	72%	80%	73%
77.8%	81%	85%	83%	95%	89%	73%	66%	79%	83%	79%	80%	74%	73%	69%	77%	74%	67%	85%	82%	75%	64%
86.0%	89%	83%	83%	89%	86%	87%	84%	81%	86%	89%	90%	83%	88%	91%	90%	92%	77%	90%	83%	81%	85%
75.3%	74%	83%	0%	90%	90%	74%	86%	77%	90%	70%	77%	77%	75%	79%	80%	80%	78%	86%	83%	52%	80%
63.6%	70%	64%	0%	57%	57%	72%	61%	70%	57%	76%	69%	69%	71%	67%	57%	64%	69%	61%	64%	95%	66%
82.5%	89%	86%	86%	93%	83%	78%	80%	82%	84%	87%	78%	76%	79%	74%	87%	87%	83%	84%	76%	81%	80%
72.2%	80%	83%	78%	78%	41%	70%	60%	66%	62%	62%	63%	77%	73%	65%	81%	78%	68%	78%	92%	87%	74%
82.9%	85%	79%	92%	86%	63%	87%	88%	89%	84%	83%	85%	83%	87%	84%	86%	78%	82%	72%	83%	80%	85%
85.9%	86%	87%	83%	85%	88%	94%	86%	76%	88%	85%	88%	85%	89%	89%	88%	89%	79%	78%	89%	81%	90%
86.0%	89%	88%	97%	98%	83%	92%	93%	92%	92%	97%	91%	72%	94%	72%	91%	93%	68%	69%	95%	45%	96%
84.1%	94%	90%	90%	89%	84%	77%	89%	85%	84%	89%	84%	85%	85%	79%	93%	87%	86%	71%	76%	72%	78%
90.9%	98%	96%	0%	88%	88%	96%	93%	98%	88%	91%	99%	99%	96%	99%	97%	99%	99%	93%	96%	97%	98%
83.7%	89%	91%	88%	88%	64%	84%	92%	94%	89%	86%	94%	81%	89%	85%	83%	87%	75%	38%	88%	84%	89%
76.4%	78%	82%	74%	74%	79%	67%	82%	77%	77%	84%	74%	78%	75%	83%	78%	76%	73%	73%	75%	71%	74%
72.6%	69%	89%	73%	64%	50%	79%	76%	54%	66%	70%	83%	77%	74%	79%	80%	68%	65%	87%	76%	73%	73%

Model Similarity Dendrogram

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