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 15e0cb8...

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

Efficiency & Succinctness

General Knowledge

Best Models (Coverage)

1.Claude Sonnet 4.5
86.0%
2.Claude Haiku 4.5
84.7%
3.Claude 3.7 Sonnet
84.3%
4.GPT 5
84.3%
5.Claude Sonnet 4
84.3%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT 4o Mini

71.8% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

89.9% 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	3rd 84.3%	2nd 84.7%	5th 84.3%	1st 86.0%	11th 81.2%	17th 78.1%	10th 82.2%	12th 81.0%	13th 81.0%	9th 82.6%	8th 82.9%	21st 71.6%	14th 80.2%	19th 73.9%	3rd 84.3%	7th 82.9%	16th 78.3%	20th 73.8%	15th 79.8%	18th 75.5%	6th 84.1%
84.5%	91%	74%	93%	97%	80%	87%	89%	86%	79%	94%	84%	81%	91%	49%	94%	91%	76%	75%	87%	91%
83.1%	83%	82%	91%	91%	61%	80%	80%	85%	78%	90%	95%	82%	91%	72%	87%	92%	88%	82%	67%	84%
67.7%	62%	68%	83%	73%	62%	77%	71%	72%	62%	62%	74%	62%	62%	77%	62%	70%	66%	66%	62%	62%
91.2%	97%	84%	96%	92%	91%	86%	92%	94%	94%	95%	94%	92%	95%	86%	89%	98%	86%	87%	90%	91%	87%
89.6%	95%	100%	93%	91%	83%	85%	88%	90%	89%	94%	90%	94%	95%	82%	91%	84%	88%	88%	88%	84%
86.7%	87%	91%	86%	90%	95%	94%	88%	95%	87%	85%	91%	74%	81%	89%	83%	81%	90%	98%	80%	69%
89.6%	91%	91%	88%	91%	87%	90%	90%	94%	91%	88%	90%	89%	89%	89%	93%	91%	93%	91%	83%	87%	86%
80.1%	90%	91%	80%	89%	82%	73%	94%	93%	88%	84%	90%	15%	84%	63%	84%	86%	81%	77%	81%	77%
86.8%	88%	87%	87%	84%	93%	67%	86%	88%	89%	89%	94%	89%	90%	76%	86%	82%	95%	92%	77%	96%
90.9%	93%	92%	93%	97%	92%	98%	87%	82%	92%	93%	92%	94%	93%	92%	94%	89%	84%	77%	92%	92%
82.8%	91%	91%	94%	93%	83%	71%	92%	84%	88%	79%	89%	81%	72%	72%	82%	79%	76%	63%	90%	87%
86.4%	90%	93%	90%	96%	90%	78%	87%	91%	88%	88%	88%	94%	70%	94%	80%	82%	83%	78%	90%	78%
81.8%	73%	87%	87%	91%	80%	91%	76%	77%	81%	89%	91%	72%	86%	87%	74%	84%	74%	74%	87%	74%
87.0%	94%	94%	95%	95%	92%	71%	91%	90%	94%	93%	82%	66%	92%	66%	92%	91%	82%	77%	87%	87%	95%
85.2%	91%	86%	91%	93%	91%	89%	86%	88%	88%	92%	87%	64%	89%	81%	90%	87%	84%	69%	83%	75%
83.5%	88%	85%	92%	95%	81%	80%	82%	86%	84%	83%	87%	82%	87%	64%	88%	85%	81%	83%	82%	74%
66.2%	74%	91%	73%	74%	61%	66%	70%	48%	67%	60%	71%	36%	60%	75%	64%	76%	58%	71%	63%	66%
75.8%	82%	83%	75%	83%	85%	62%	69%	74%	71%	70%	77%	67%	78%	83%	73%	76%	80%	76%	79%	74%
65.8%	69%	54%	68%	69%	93%	48%	62%	71%	69%	85%	61%	45%	66%	61%	77%	81%	55%	51%	51%	82%	64%
84.9%	89%	93%	93%	97%	96%	78%	93%	78%	77%	93%	77%	76%	83%	76%	96%	94%	78%	74%	81%	76%
82.5%	87%	88%	89%	94%	83%	89%	79%	81%	94%	96%	90%	6%	92%	68%	95%	88%	83%	72%	86%	89%
83.9%	83%	86%	82%	81%	83%	92%	87%	84%	86%	89%	93%	78%	88%	88%	92%	92%	78%	75%	77%	63%
81.8%	79%	89%	80%	79%	93%	85%	89%	89%	83%	89%	85%	65%	77%	70%	88%	81%	79%	73%	86%	77%
83.4%	87%	94%	92%	92%	79%	91%	75%	81%	85%	91%	89%	74%	81%	74%	84%	84%	77%	77%	83%	77%
83.6%	83%	80%	93%	94%	92%	68%	89%	78%	94%	89%	89%	64%	80%	64%	90%	92%	90%	77%	88%	77%	85%
71.0%	70%	81%	77%	77%	79%	64%	66%	69%	72%	79%	80%	69%	66%	50%	74%	74%	58%	62%	77%	77%
76.9%	87%	82%	80%	85%	81%	64%	79%	80%	75%	78%	68%	72%	79%	74%	80%	78%	76%	68%	77%	75%
83.0%	93%	93%	79%	90%	92%	75%	85%	93%	89%	75%	86%	85%	79%	91%	89%	92%	78%	47%	75%	75%
75.3%	86%	93%	85%	86%	84%	58%	75%	75%	71%	72%	75%	78%	71%	67%	79%	77%	68%	66%	68%	72%
79.0%	88%	82%	82%	94%	63%	82%	75%	85%	83%	71%	86%	75%	76%	68%	84%	81%	79%	71%	78%	77%
82.5%	86%	83%	86%	82%	86%	89%	84%	79%	85%	84%	86%	79%	81%	78%	81%	88%	77%	83%	86%	77%	72%
75.7%	86%	79%	64%	74%	86%	70%	75%	74%	86%	86%	73%	86%	86%	32%	86%	81%	87%	86%	86%	32%
61.0%	55%	62%	76%	66%	55%	70%	65%	66%	55%	55%	67%	55%	55%	84%	55%	59%	55%	55%	55%	55%
81.1%	90%	81%	84%	90%	77%	73%	79%	81%	81%	85%	78%	76%	79%	76%	87%	87%	84%	83%	76%	76%
75.1%	84%	94%	82%	81%	52%	69%	71%	71%	58%	64%	75%	79%	74%	71%	73%	73%	97%	64%	98%	71%
83.1%	89%	86%	91%	89%	74%	86%	82%	90%	83%	88%	80%	77%	85%	79%	85%	84%	81%	76%	78%	79%
82.2%	85%	81%	86%	85%	84%	86%	89%	80%	85%	88%	88%	72%	89%	68%	87%	81%	72%	64%	89%	84%
85.3%	94%	86%	90%	91%	81%	91%	91%	89%	86%	98%	79%	71%	95%	84%	95%	88%	74%	61%	91%	71%
82.7%	95%	84%	91%	89%	79%	76%	88%	87%	80%	87%	80%	82%	86%	78%	89%	86%	76%	74%	74%	73%
90.7%	90%	97%	88%	98%	90%	94%	100%	99%	90%	90%	97%	90%	90%	53%	90%	94%	94%	90%	90%	90%
85.7%	90%	93%	81%	83%	96%	82%	91%	94%	93%	74%	91%	69%	83%	92%	88%	84%	80%	85%	94%	71%
50.6%	52%	41%	43%	39%	55%	56%	72%	37%	44%	49%	36%	44%	39%	44%	100%	49%	50%	33%	42%	37%	100%
75.0%	70%	89%	75%	77%	70%	78%	77%	56%	68%	68%	90%	77%	64%	89%	77%	74%	77%	83%	76%	65%

Model Similarity Dendrogram

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