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 AiConcern%3Aequally Concerned And Excited C10 - Run f7a64eb...

Global Dialogues GD3 - Equally concerned and excited (10 context Qs)

DTEF: Predict response distributions for Equally concerned and excited. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Knowledge, learning and memory

Best Models (Coverage)

1.Claude Sonnet 4.5
86.5%
2.Claude Sonnet 4
84.6%
3.GPT 5
84.4%
4.GPT 5.1
84.2%
5.Claude 3.7 Sonnet
84.1%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT OSS 20b

71.8% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

89.8% 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	5th 84.1%	6th 84.0%	2nd 84.6%	1st 86.5%	9th 82.1%	16th 78.5%	10th 81.7%	13th 80.8%	12th 80.9%	8th 82.2%	7th 82.6%	21st 67.8%	14th 80.7%	19th 74.3%	3rd 84.4%	4th 84.2%	18th 77.0%	20th 73.6%	15th 80.0%	17th 77.2%	11th 81.3%
84.8%	93%	77%	92%	97%	83%	87%	89%	86%	90%	94%	84%	56%	91%	55%	96%	90%	83%	65%	93%	88%	91%
82.3%	81%	81%	91%	91%	62%	80%	83%	82%	71%	88%	93%	79%	90%	76%	90%	90%	79%	76%	67%	89%	90%
67.8%	62%	68%	83%	72%	62%	77%	70%	74%	62%	62%	81%	62%	62%	77%	62%	65%	60%	62%	62%	77%	62%
90.5%	93%	84%	95%	92%	88%	86%	91%	93%	94%	90%	91%	92%	95%	80%	90%	93%	87%	88%	94%	92%	92%
89.4%	94%	90%	93%	91%	86%	85%	86%	95%	91%	90%	99%	93%	95%	82%	90%	95%	86%	76%	84%	89%	87%
87.0%	90%	91%	86%	90%	93%	94%	88%	95%	87%	78%	89%	74%	81%	92%	84%	80%	87%	94%	88%	75%	90%
89.9%	88%	91%	89%	91%	91%	90%	90%	90%	94%	89%	89%	89%	88%	89%	91%	92%	93%	91%	80%	90%	93%
82.7%	89%	86%	80%	89%	83%	84%	88%	92%	93%	84%	89%	42%	85%	71%	88%	85%	79%	82%	79%	81%	87%
86.9%	91%	84%	87%	83%	93%	67%	87%	93%	89%	92%	93%	89%	92%	76%	81%	85%	89%	95%	85%	96%	78%
91.7%	92%	92%	93%	96%	92%	97%	87%	86%	92%	93%	94%	94%	92%	92%	94%	92%	89%	73%	92%	97%	97%
81.4%	91%	93%	94%	92%	92%	71%	92%	90%	88%	78%	79%	81%	70%	87%	84%	84%	67%	51%	83%	85%	57%
86.0%	91%	93%	90%	96%	92%	78%	86%	92%	86%	86%	88%	94%	69%	85%	94%	77%	70%	78%	92%	81%	89%
80.7%	74%	87%	87%	92%	84%	87%	76%	77%	82%	89%	82%	72%	81%	79%	77%	80%	74%	74%	92%	74%	74%
86.6%	95%	91%	95%	95%	91%	71%	92%	80%	94%	92%	90%	70%	94%	66%	91%	90%	80%	87%	90%		78%
84.0%	90%	88%	93%	93%	87%	91%	87%	88%	88%	91%	87%	6%	92%	85%	93%	90%	84%	77%	82%	83%	90%
82.2%	91%	85%	92%	95%	85%	74%	82%	83%	81%	83%	86%	83%	87%	58%	85%	79%	77%	85%	71%	79%	86%
66.0%	74%	91%	73%	74%	70%	55%	70%	47%	67%	61%	76%	36%	47%	75%	68%	76%	57%	70%	72%	55%	71%
75.0%	83%	80%	75%	83%	84%	62%	67%	75%	74%	70%	73%	67%	78%	72%	67%	74%	76%	81%	73%	78%	83%
64.7%	70%	54%	70%	69%	83%	48%	62%	68%	69%	82%	56%	45%	69%	56%	82%	84%	59%	58%	51%	67%	57%
84.3%	94%	91%	86%	97%	93%	78%	88%	79%	77%	94%	79%	76%	83%	76%	95%	94%	78%	78%	80%	76%	79%
82.5%	79%	88%	93%	94%	87%	92%	83%	85%	90%	93%	87%	22%	88%	68%	88%	92%	84%	67%	78%	83%	92%
85.1%	80%	88%	82%	83%	86%	88%	88%	84%	88%	90%	91%	79%	88%	88%	88%	93%	79%	73%	78%	89%	84%
81.7%	85%	89%	80%	79%	89%	85%	89%	89%	77%	88%	85%	70%	78%	90%	82%	81%	74%	73%	85%	76%	71%
82.4%	86%	95%	92%	95%	76%	88%	75%	82%	81%	85%	86%	67%	85%	77%	85%	84%	77%	77%	83%	77%	77%
83.8%	83%	80%	95%	94%	93%	68%	89%	81%	93%	94%	91%	64%	88%	64%	90%	91%	66%	86%	88%	78%	84%
72.0%	72%	74%	77%	82%	79%	64%	64%	69%	74%	79%	80%	69%	69%	50%	75%	70%	75%	59%	75%	77%	78%
76.2%	84%	82%	82%	85%	80%	67%	75%	80%	75%	77%	69%	71%	79%	65%	85%	78%	73%	65%	75%		77%
81.9%	91%	93%	80%	89%	92%	75%	83%	94%	88%	76%	91%	21%	84%	87%	90%	91%	85%	82%	75%	74%	79%
75.7%	82%	93%	85%	86%	87%	67%	76%	72%	71%	67%	75%	78%	73%	66%	77%	80%	70%	70%	68%	72%	74%
79.1%	86%	82%	83%	94%	77%	81%	75%	83%	83%	75%	84%	78%	83%	68%	74%	75%	82%	73%	83%	62%	80%
80.7%	83%	83%	86%	82%	81%	85%	84%	80%	84%	84%	83%	76%	83%	78%	82%	85%	68%	68%	86%	66%	87%
78.0%	86%	79%	64%	75%	86%	70%	77%	73%	86%	86%	66%	86%	86%	32%	86%	80%	84%	77%	86%	86%	86%
62.7%	55%	62%	76%	66%	55%	70%	63%	67%	55%	55%	74%	55%	55%	84%	55%	55%	57%	63%	55%	84%	55%
82.0%	90%	81%	84%	90%	91%	78%	80%	81%	82%	84%	79%	76%	79%	76%	82%	85%	91%	80%	76%	76%	82%
76.0%	86%	95%	82%	81%	45%	74%	68%	69%	63%	64%	69%	79%	75%	80%	82%	78%	81%	71%	96%	79%	79%
82.2%	87%	82%	93%	90%	69%	86%	82%	89%	80%	85%	82%	77%	88%	73%	81%	87%	79%	77%	79%	77%	84%
81.8%	87%	81%	86%	85%	88%	86%	88%	80%	83%	86%	87%	9%	91%	83%	87%	89%	88%	85%	86%	84%	78%
84.9%	94%	87%	91%	91%	74%	93%	91%	91%	86%	98%	84%	71%	89%	80%	95%	92%	73%	62%	88%	65%	87%
83.8%	96%	88%	91%	89%	86%	83%	87%	86%	86%	88%	84%	79%	83%	80%	87%	84%	82%	64%	74%	82%	81%
88.3%	90%	97%	88%	100%	90%	94%	98%	97%	90%	90%	90%	90%	90%	53%	90%	93%	92%	90%	90%	53%	90%
86.0%	91%	93%	86%	94%	97%	87%	87%	94%	92%	84%	92%	79%	86%	92%	92%	90%	82%	27%	95%	73%	93%
52.5%	48%	36%	43%	39%	63%	56%	72%	30%	35%	49%	37%	44%	39%	41%	100%	100%	43%	51%	39%	37%	100%
75.1%	70%	86%	75%	77%	67%	77%	78%	52%	69%	73%	89%	77%	72%	89%	74%	74%	74%	83%	90%	65%	66%

Model Similarity Dendrogram

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