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%3A46 55 C10 - Run 2cbae08...

Global Dialogues GD3 - 46-55 (10 context Qs)

DTEF: Predict response distributions for 46-55. Source: Global Dialogues GD3 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

Best Models (Coverage)

1.Claude 3.7 Sonnet
83.9%
2.Claude Haiku 4.5
83.8%
3.GPT 5.1
83.8%
4.Claude Sonnet 4.5
83.0%
5.Mistral Large 2411
82.1%

🔀 Least Similar Models

Claude Sonnet 4.5vsGPT OSS 20b

70.4% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

88.7% 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 83.9%	3rd 83.8%	20th 75.7%	4th 83.0%	14th 79.5%	19th 76.0%	10th 81.5%	5th 82.1%	13th 80.5%	6th 82.1%	11th 81.3%	18th 76.4%	9th 81.6%	17th 77.0%	7th 82.0%	2nd 83.8%	15th 79.2%	21st 75.1%	12th 80.8%	16th 78.1%	8th 81.8%
86.2%	90%	87%	80%	83%	81%	72%	88%	92%	88%	84%	92%	77%	89%	78%	91%	91%	95%	83%	85%	97%	88%
87.0%	95%	84%	95%	93%	46%	97%	86%	89%	72%	95%	98%	90%	97%	86%	97%	87%	85%	68%	90%	86%	90%
64.5%	68%	63%	0%	60%	60%	70%	67%	73%	63%	70%	70%	72%	61%	64%	70%	69%	64%	68%	62%	90%	70%
88.0%	91%	82%	88%	92%	95%	81%	88%	86%	85%	89%	83%	95%	89%	76%	84%	90%	92%	92%	86%	91%	92%
91.4%	91%	96%	92%	97%	87%	97%	92%	88%	90%	95%	91%	81%	93%	92%	97%	96%	98%	78%	97%	85%	87%
91.2%	94%	98%	94%	97%	100%	98%	92%	91%	84%	89%	92%	78%	88%	86%	90%	91%	85%	97%	88%	88%	95%
89.7%	87%	90%	88%	87%	89%	87%	90%	95%	92%	92%	93%	86%	92%	95%	91%	90%	79%	91%	88%	86%	95%
76.2%	75%	81%	75%	75%	75%	48%	73%	83%	75%	83%	75%	77%	75%	69%	82%	80%	80%	75%	68%	84%	92%
84.8%	90%	84%	77%	77%	85%	74%	82%	80%	82%	89%	87%	86%	86%	87%	84%	95%	87%	86%	86%	95%	81%
90.0%	93%	83%	97%	94%	95%	91%	84%	96%	95%	93%	83%	95%	95%	95%	86%	91%	85%	76%	95%		79%
74.9%	82%	81%	85%	85%	75%	86%	78%	84%	73%	69%	72%	84%	67%	62%	74%	72%	54%	62%	83%	71%	74%
76.3%	80%	78%	80%	81%	76%	71%	78%	82%	79%	68%	74%	76%	68%	66%	76%	80%	77%	77%	78%	78%	79%
80.8%	87%	91%	84%	89%	92%	90%	77%	75%	75%	85%	87%	73%	86%	87%	76%	77%	70%	70%	86%	70%	70%
86.4%	79%	81%	80%	83%	81%	90%	84%	89%	92%	89%	89%	73%	91%	78%	85%	89%	91%	91%	99%	90%	90%
80.7%	80%	91%	86%	86%	86%	82%	89%	88%	86%	84%	86%	86%	88%	83%	0%	86%	82%	74%	83%	81%	87%
84.2%	87%	85%	88%	92%	87%	66%	85%	93%	89%	80%	78%	75%	88%	73%	86%	90%	88%	90%	80%	83%	86%
62.9%	70%	79%	71%	72%	59%	55%	67%	45%	65%	58%	69%	57%	56%	56%	72%	65%	55%	55%	66%	60%	68%
63.3%	69%	65%	63%	70%	70%	43%	55%	77%	66%	58%	52%	58%	65%	47%	69%	67%	64%	65%	64%	72%	70%
61.1%	69%	45%	69%	58%	72%	51%	62%	60%	67%	73%	48%	38%	72%	60%	72%	69%	68%	59%	51%	58%	63%
84.5%	96%	93%	94%	93%	91%	74%	96%	82%	74%	92%	76%	73%	85%	75%	91%	95%	75%	77%	80%	74%	88%
84.0%	90%	86%	81%	81%	87%	68%	89%	88%	87%	82%	85%	81%	85%	81%	92%	90%	88%	76%	74%	82%	90%
85.0%	86%	86%	81%	81%	86%	79%	90%	88%	87%	87%	83%	82%	88%	84%	85%	88%	84%	87%	81%	86%	85%
77.9%	74%	79%	79%	79%	87%	86%	82%	79%	73%	82%	82%	80%	72%	77%	75%	78%	79%	67%	83%	76%	67%
81.8%	91%	94%	91%	87%	90%	82%	84%	81%	79%	91%	87%	74%	84%	85%	89%	92%	78%	54%	76%	52%	76%
83.2%	86%	83%	80%	83%	84%	83%	82%	86%	83%	87%	84%	76%	84%	74%	84%	86%	80%	84%	92%	83%	83%
82.6%	87%	83%	85%	85%	88%	75%	82%	77%	85%	92%	88%	85%	85%	79%	88%	83%	69%	61%	85%	84%	89%
76.9%	85%	82%	79%	75%	74%	56%	73%	87%	76%	78%	61%	72%	80%	65%	87%	80%	84%	82%	70%	85%	83%
81.8%	89%	89%	82%	85%	87%	65%	84%	89%	86%	83%	84%	73%	81%	64%	90%	89%	80%	80%	75%	82%	81%
75.1%	77%	88%	85%	90%	82%	68%	80%	71%	72%	70%	67%	74%	67%	66%	78%	76%	72%	77%	74%	71%	73%
76.7%	83%	81%	86%	88%	90%	66%	68%	84%	82%	79%	76%	51%	73%	64%	82%	73%	73%	81%	77%	77%	76%
84.0%	85%	84%	83%	88%	82%	87%	86%	85%	86%	87%	88%	85%	85%	90%	87%	87%	71%	56%	88%	87%	86%
81.1%	87%	88%	0%	92%	92%	81%	84%	78%	88%	81%	81%	79%	90%	87%	87%	85%	87%	83%	89%	84%	81%
58.6%	63%	60%	0%	56%	56%	66%	63%	69%	60%	66%	66%	68%	58%	61%	60%	65%	60%	64%	59%	45%	66%
77.0%	82%	74%	81%	86%	86%	68%	69%	78%	78%	81%	72%	72%	75%	70%	81%	84%	75%	83%	71%	73%	79%
77.2%	86%	92%	77%	88%	46%	76%	73%	68%	73%	69%	82%	79%	80%	81%	80%	70%	85%	74%	92%	77%	73%
83.7%	88%	92%	96%	90%	66%	72%	91%	93%	84%	87%	87%	74%	91%	76%	87%	87%	82%	75%	79%	78%	82%
88.0%	93%	93%	89%	88%	92%	87%	92%	84%	91%	91%	92%	86%	93%	82%	92%	93%	88%	60%	84%	88%	90%
87.6%	77%	94%	91%	91%	79%	92%	84%	86%	85%	85%	90%	79%	88%	87%	96%	93%	85%	90%	92%		87%
81.8%	90%	89%	82%	82%	81%	67%	87%	88%	86%	85%	81%	68%	86%	75%	89%	88%	81%	73%	76%	80%	84%
89.0%	96%	91%	0%	87%	87%	98%	95%	99%	91%	98%	98%	100%	89%	92%	94%	98%	92%	96%	90%	81%	98%
80.7%	93%	93%	88%	90%	63%	73%	92%	92%	94%	93%	88%	56%	89%	84%	92%	87%	77%	41%	91%	30%	88%
82.3%	85%	83%	80%	74%	81%	74%	84%	81%	78%	77%	90%	85%	84%	90%	84%	84%	87%	79%	84%	84%	80%
71.7%	62%	83%	71%	61%	52%	76%	76%	52%	64%	63%	89%	75%	71%	80%	73%	78%	74%	73%	76%	78%	78%

Model Similarity Dendrogram

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