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 AiConcern%3Aequally Concerned And Excited C5 - Run f7a64eb...

Global Dialogues GD3 - Equally concerned and excited (5 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

Reasoning

Factual Accuracy & Hallucination

Efficiency & Succinctness

Best Models (Coverage)

1.Claude 3.7 Sonnet
85.3%
2.Claude Sonnet 4.5
85.0%
3.GPT 5
84.1%
4.Claude Sonnet 4
83.6%
5.Claude Haiku 4.5
83.5%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT 4.1 Nano

69.3% 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	1st 85.3%	5th 83.5%	4th 83.6%	2nd 85.0%	9th 81.5%	18th 72.7%	8th 81.6%	13th 80.7%	12th 81.0%	11th 81.0%	6th 83.0%	21st 68.3%	14th 79.8%	20th 70.4%	3rd 84.1%	10th 81.4%	15th 77.6%	19th 72.3%	16th 77.2%	17th 76.0%	7th 82.9%
85.5%	92%	85%	90%	94%	74%	85%	90%	89%	90%	87%	88%	88%	89%	60%	95%	92%	77%	77%	80%	83%	90%
81.4%	83%	74%	91%	91%	57%	70%	76%	83%	76%	90%	85%	71%	82%	72%	86%	85%	90%	81%	92%	86%	89%
67.2%	67%	68%	83%	80%	97%	10%	64%	74%	62%	62%	81%	62%	62%	77%	62%	66%	70%	62%	62%	78%	62%
89.3%	93%	87%	90%	90%	90%	86%	89%	92%	91%	91%	90%	92%	92%	86%	93%	95%	87%	83%	83%	88%	88%
88.7%	94%	96%	94%	91%	88%	82%	86%	91%	89%	86%	82%	87%	98%	92%	93%	94%	88%	72%	89%	89%	82%
90.1%	90%	91%	86%	90%	99%	89%	94%	94%	95%	85%	91%	89%	88%	95%	84%	85%	98%	89%	87%	80%	94%
81.3%	83%	90%	82%	93%	88%	66%	87%	93%	86%	73%	90%	83%	82%	30%	77%	90%	89%	82%	84%	73%	86%
83.0%	87%	86%	79%	86%	81%	87%	87%	91%	91%	81%	89%	79%	80%	60%	86%	88%	81%	81%	77%	83%	84%
86.2%	87%	84%	84%	80%	91%	72%	79%	96%	89%	90%	93%	90%	94%	76%	84%	81%	95%	96%	81%	87%	82%
87.6%	99%	95%	88%	88%	88%	95%	91%	78%	88%	91%	90%	92%	89%	91%	90%	83%	74%	73%	95%	76%	85%
82.2%	89%	92%	94%	91%	72%	91%	81%	88%	88%	79%	89%	77%	70%	74%	86%	81%	67%	63%	81%	89%	85%
89.3%	90%	92%	89%	96%	87%	94%	86%	95%	89%	92%	89%	94%	91%	89%	95%	91%	76%	81%	90%	81%	89%
82.5%	84%	87%	84%	86%	93%	86%	80%	81%	89%	96%	93%	13%	91%	71%	93%	93%	82%	81%	84%	78%	87%
78.4%	86%	80%	84%	84%	84%	69%	86%	73%	77%	82%	85%	79%	72%	40%	86%	82%	75%	80%	88%	75%	79%
85.4%	89%	88%	93%	86%	95%	91%	88%	83%	85%	84%	90%	71%	85%	80%	91%	93%	87%	65%	84%	75%	91%
81.9%	93%	78%	94%	99%	73%	72%	83%	89%	81%	80%	87%	81%	87%	54%	87%	84%	77%	79%	80%	80%	81%
67.3%	74%	91%	74%	74%	68%	55%	69%	49%	67%	61%	71%	39%	44%	77%	71%	68%	70%	75%	64%	75%	78%
73.4%	82%	75%	69%	75%	83%	57%	65%	82%	72%	68%	78%	71%	78%	78%	69%	68%	69%	73%	79%	74%	77%
57.3%	66%	48%	72%	68%	66%	43%	62%	54%	64%	60%	59%	49%	59%	49%	79%	71%	48%	48%	37%	55%	47%
88.0%	88%	91%	87%	93%	93%	84%	91%	91%	89%	91%	96%	87%	88%	77%	79%	87%	86%	72%	92%	93%	94%
82.1%	88%	88%	91%	93%	87%	94%	92%	78%	90%	90%	90%	20%	93%	68%	88%	87%	75%	58%	77%	83%	95%
82.5%	82%	88%	85%	83%	85%	89%	90%	82%	86%	83%	92%	31%	90%	80%	91%	93%	86%	67%	76%	82%	91%
78.1%	74%	74%	79%	79%	88%	87%	89%	82%	77%	74%	87%	66%	79%	77%	74%	81%	78%	66%	74%	77%	79%
82.5%	87%	94%	92%	92%	87%	83%	79%	85%	81%	90%	89%	24%	92%	72%	95%	88%	85%	60%	79%	88%	90%
75.4%	87%	89%	82%	83%	82%	66%	73%	77%	83%	77%	82%	79%	69%	27%	79%	74%	74%	61%	83%	78%	78%
73.3%	76%	74%	77%	80%	77%	73%	63%	62%	71%	83%	77%	61%	77%	60%	80%	73%	74%	77%	76%	72%	76%
74.6%	87%	79%	76%	79%	77%	66%	71%	74%	71%	77%	69%	75%	74%	71%	84%	74%	74%	75%	71%	65%	78%
82.6%	91%	89%	80%	89%	97%	83%	85%	97%	86%	80%	87%	41%	76%	87%	94%	85%	81%	82%	75%	67%	82%
75.5%	83%	92%	86%	86%	93%	72%	85%	71%	70%	69%	72%	66%	71%	66%	85%	70%	68%	68%	68%	72%	73%
72.9%	78%	82%	87%	90%	85%	67%	72%	85%	84%	70%	79%	75%	77%	68%	73%	73%	62%	73%	28%	51%	72%
82.2%	83%	82%	86%	82%	83%	86%	83%	80%	82%	88%	88%	62%	83%	77%	91%	92%	78%	68%	86%	79%	87%
70.3%	78%	79%	64%	66%	50%	10%	83%	72%	86%	86%	66%	86%	86%	32%	86%	80%	77%	86%	86%	32%	86%
60.6%	61%	62%	76%	73%	90%	10%	58%	67%	55%	55%	74%	55%	55%	84%	55%	60%	63%	55%	55%	55%	55%
85.4%	84%	91%	84%	88%	89%	87%	93%	96%	89%	85%	88%	81%	72%	66%	87%	88%	88%	89%	79%	75%	94%
76.9%	91%	89%	87%	83%	50%	79%	71%	80%	76%	86%	67%	65%	91%	83%	59%	57%	68%	83%	83%	87%	80%
80.9%	88%	83%	95%	88%	72%	82%	85%	92%	84%	91%	83%	74%	84%	73%	73%	69%	75%	70%	78%	77%	83%
81.8%	86%	81%	85%	86%	87%	91%	89%	74%	85%	90%	89%	23%	89%	77%	90%	89%	87%	73%	83%	78%	86%
87.2%	97%	87%	96%	92%	85%	94%	91%	86%	87%	93%	80%	90%	94%	79%	96%	89%	72%	74%	82%	71%	96%
82.6%	95%	85%	88%	90%	87%	81%	87%	83%	85%	86%	83%	64%	85%	76%	87%	90%	75%	62%	73%	92%	81%
85.2%	95%	97%	88%	90%	74%	10%	93%	97%	90%	90%	90%	90%	90%	53%	90%	95%	98%	90%	90%	90%	90%
85.1%	87%	94%	86%	94%	95%	87%	93%	88%	91%	88%	93%	80%	80%	90%	90%	91%	70%	28%	88%	83%	91%
55.9%	100%	46%	43%	53%	43%	56%	72%	37%	44%	56%	41%	44%	44%	41%	100%	51%	68%	48%	43%	44%	100%
77.3%	75%	89%	75%	82%	74%	88%	79%	57%	71%	69%	89%	89%	58%	91%	84%	76%	73%	83%	77%	73%	72%

Model Similarity Dendrogram

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