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 AgeGroup%3A36 45 C5 - Run d41f2a9...

Global Dialogues GD3 - 36-45 (5 context Qs)

DTEF: Predict response distributions for 36-45. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Efficiency & Succinctness

AI Safety & Robustness

Best Models (Coverage)

1.GPT 5.1
84.8%
2.GPT 4.1 Mini
84.5%
3.Claude 3.7 Sonnet
84.1%
4.Claude Haiku 4.5
83.8%
5.GPT 4o
83.7%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

68.1% similarity

👯 Most Similar Models

Claude Haiku 4.5vsMistral Medium 3

89.0% 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	3rd 84.1%	4th 83.8%	21st 73.8%	7th 82.7%	6th 83.4%	18th 77.9%	11th 81.5%	17th 79.8%	8th 81.8%	12th 81.2%	2nd 84.5%	15th 80.2%	5th 83.7%	13th 81.1%	10th 81.5%	1st 84.8%	16th 80.0%	19th 77.3%	14th 81.1%	20th 77.1%	9th 81.6%
85.8%	92%	84%	75%	80%	90%	70%	88%	88%	84%	82%	92%	82%	90%	80%	92%	95%	89%	85%	90%	82%	91%
80.3%	78%	70%	84%	84%	74%	86%	81%	73%	70%	79%	85%	86%	78%	85%	83%	82%	85%	69%	87%	80%	88%
66.9%	67%	70%	0%	75%	72%	75%	69%	75%	70%	76%	75%	72%	72%	70%	70%	70%	65%	64%	62%	68%	68%
91.2%	94%	87%	98%	92%	92%	85%	88%	94%	92%	93%	93%	90%	94%	86%	95%	99%	89%	87%	88%	90%	90%
87.0%	83%	88%	78%	84%	90%	85%	83%	95%	90%	89%	95%	94%	98%	96%	89%	92%	91%	87%	80%	67%	72%
85.3%	87%	88%	83%	88%	93%	93%	90%	93%	94%	90%	92%	92%	93%	88%	0%	83%	86%	92%	84%	89%	93%
80.0%	80%	77%	77%	82%	84%	71%	81%	84%	86%	75%	87%	86%	76%	85%	73%	82%	79%	80%	82%	72%	81%
83.6%	87%	88%	80%	80%	80%	59%	87%	90%	92%	83%	94%	87%	81%	77%	87%	95%	92%	69%	76%	85%	87%
77.4%	83%	71%	66%	71%	81%	61%	68%	70%	69%	85%	79%	84%	77%	73%	86%	87%	83%	86%	72%	87%	87%
88.8%	91%	95%	87%	90%	92%	93%	83%	86%	83%	91%	89%	95%	91%	93%	89%	92%	75%	82%	92%	87%	88%
81.4%	89%	89%	87%	89%	80%	86%	88%	85%	83%	72%	87%	77%	73%	72%	83%	81%	68%	62%	85%	87%	86%
91.8%	87%	94%	95%	91%	93%	92%	85%	91%	94%	86%	93%	94%	96%	92%	94%	92%	88%	87%	97%	93%	93%
86.4%	86%	94%	80%	89%	91%	90%	88%	79%	88%	89%	92%	69%	94%	88%	96%	96%	85%	69%	90%	75%	86%
84.3%	86%	87%	82%	83%	88%	80%	89%	74%	87%	79%	87%	94%	87%	88%	76%	84%	72%	87%	90%		86%
86.3%	86%	94%	82%	90%	88%	88%	87%	80%	85%	89%	89%	74%	92%	91%	93%	90%	81%	72%	88%	86%	87%
82.9%	91%	79%	87%	91%	93%	72%	80%	79%	71%	83%	84%	80%	88%	75%	83%	93%	82%	84%	80%	84%	82%
70.1%	77%	94%	77%	77%	65%	74%	73%	53%	62%	70%	65%	62%	63%	61%	80%	83%	59%	57%	77%	68%	76%
65.1%	71%	65%	68%	69%	61%	48%	56%	64%	61%	60%	59%	61%	68%	56%	67%	68%	81%	78%	68%		73%
57.9%	64%	54%	71%	65%	63%	45%	63%	59%	60%	59%	68%	50%	57%	45%	79%	81%	50%	42%	41%	52%	47%
85.7%	84%	75%	81%	80%	90%	89%	84%	84%	94%	84%	91%	89%	89%	87%	78%	75%	93%	94%	92%	74%	92%
85.2%	83%	86%	80%	81%	91%	79%	94%	76%	92%	82%	94%	90%	91%	91%	75%	90%	80%	72%	81%	96%	86%
84.4%	82%	85%	76%	76%	90%	84%	90%	77%	82%	83%	87%	77%	88%	87%	86%	89%	90%	78%	92%	91%	83%
83.8%	83%	83%	81%	85%	88%	89%	88%	86%	86%	82%	88%	82%	85%	89%	85%	84%	85%	74%	80%	79%	78%
87.2%	90%	95%	83%	91%	93%	95%	80%	81%	89%	89%	88%	71%	88%	90%	93%	96%	91%	74%	85%	81%	88%
82.1%	89%	80%	81%	82%	92%	77%	88%	82%	87%	76%	92%	89%	82%	88%	76%	87%	69%	75%	91%	68%	74%
77.0%	84%	79%	79%	83%	81%	73%	76%	65%	74%	81%	78%	78%	80%	77%	81%	79%	70%	73%	80%	75%	70%
75.0%	88%	79%	74%	74%	75%	53%	70%	73%	76%	74%	63%	82%	85%	67%	81%	79%	75%	83%	73%		75%
86.7%	92%	95%	85%	90%	90%	75%	87%	93%	93%	90%	87%	84%	89%	72%	94%	93%	93%	82%	70%	79%	87%
79.6%	85%	88%	83%	86%	89%	75%	86%	76%	76%	77%	76%	74%	77%	76%	84%	79%	76%	75%	78%	78%	78%
79.7%	84%	91%	82%	86%	95%	71%	68%	89%	78%	71%	80%	67%	79%	80%	81%	82%	87%	76%	81%	72%	73%
80.4%	80%	80%	77%	76%	83%	82%	80%	74%	80%	82%	89%	76%	83%	88%	84%	85%	74%	68%	89%	75%	84%
75.7%	78%	81%	0%	76%	79%	76%	81%	76%	81%	75%	76%	79%	79%	81%	83%	79%	76%	79%	89%	83%	83%
63.5%	67%	65%	0%	73%	67%	70%	65%	70%	65%	70%	70%	67%	67%	65%	63%	66%	70%	71%	57%	63%	63%
84.6%	87%	87%	78%	85%	79%	75%	87%	90%	90%	84%	89%	85%	81%	75%	89%	90%	92%	89%	80%	78%	86%
75.2%	87%	80%	74%	84%	63%	81%	71%	75%	77%	80%	77%	73%	86%	91%	60%	62%	76%	65%	73%	80%	65%
81.4%	82%	85%	88%	82%	75%	83%	85%	81%	81%	86%	84%	82%	85%	83%	82%	70%	81%	76%	76%	77%	86%
81.2%	86%	83%	82%	82%	87%	80%	84%	66%	82%	81%	81%	79%	86%	84%	83%	83%	76%	72%	88%	72%	89%
85.6%	89%	90%	90%	86%	80%	90%	83%	93%	83%	90%	92%	80%	95%	80%	96%	93%	74%	85%	94%	55%	79%
86.6%	94%	90%	96%	95%	90%	77%	91%	82%	91%	90%	89%	86%	89%	85%	84%	91%	80%	84%	77%	73%	84%
91.3%	96%	98%	0%	93%	96%	93%	98%	93%	98%	92%	93%	96%	96%	98%	100%	96%	96%	91%	94%	100%	100%
80.7%	90%	89%	87%	90%	87%	77%	86%	85%	82%	90%	90%	64%	85%	80%	90%	85%	76%	81%	72%	26%	82%
82.0%	85%	87%	77%	77%	83%	74%	84%	89%	83%	81%	82%	83%	83%	85%	81%	86%	82%	78%	82%	79%	82%
79.7%	74%	84%	82%	72%	74%	80%	71%	62%	75%	73%	92%	88%	84%	88%	81%	82%	80%	89%	84%	77%	81%

Model Similarity Dendrogram

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