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%3Amore Concerned Than Excited C5 - Run 5714ab8...

Global Dialogues GD3 - More concerned than excited (5 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

AI Safety & Robustness

Best Models (Coverage)

1.GPT 5.1
83.0%
2.GPT 5
82.3%
3.Claude 3.7 Sonnet
81.8%
4.Mistral Large 2411
81.5%
5.Mistral Medium 3
80.3%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT 4.1 Nano

67.2% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

90.5% 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 81.8%	8th 79.3%	9th 76.5%	7th 79.4%	10th 76.0%	12th 73.3%	6th 80.0%	4th 81.5%	5th 80.3%	11th 75.5%	18th 71.3%	21st 49.0%	14th 72.8%	20th 68.8%	2nd 82.3%	1st 83.0%	17th 71.3%	16th 72.6%	19th 69.8%	13th 73.0%	15th 72.6%
76.3%	83%	88%	78%	76%	68%	77%	77%	90%	88%	82%	68%	38%	85%	66%	87%	84%	77%	75%	71%	74%	70%
82.3%	85%	91%	84%	88%	85%	85%	92%	89%	91%	92%	72%	42%	81%	80%	93%	81%	81%	80%	85%	87%	65%
53.2%	55%	50%	39%	53%	59%	31%	69%	70%	55%	37%	50%	11%	11%	80%	67%	59%	52%	34%	80%	97%	59%
87.2%	96%	84%	91%	92%	88%	78%	87%	93%	93%	95%	85%	94%	91%	71%	92%	93%	85%	86%	74%	77%	86%
87.8%	97%	81%	97%	97%	97%	95%	95%	89%	86%	89%	80%	95%	91%	77%	92%	89%	73%	74%	80%	82%	88%
83.1%	93%	91%	93%	94%	94%	95%	91%	75%	79%	70%	75%	99%	76%	79%	86%	86%	78%	81%	72%	64%	75%
69.7%	78%	81%	69%	76%	56%	84%	69%	75%	79%	76%	67%	25%	72%	66%	77%	88%	72%	72%	60%	53%	68%
69.3%	72%	78%	66%	79%	56%	62%	78%	78%	79%	74%	63%	40%	73%	65%	70%	97%	62%	75%	62%	63%	64%
75.8%	85%	77%	70%	70%	82%	64%	83%	81%	83%	79%	68%	73%	73%	60%	77%	85%	82%	78%	74%	70%	78%
85.7%	92%	90%	84%	85%	84%	86%	90%	87%	82%	85%	90%	94%	89%	87%	85%	86%	83%	78%	90%	70%	82%
75.1%	86%	85%	86%	85%	69%	75%	79%	81%	83%	73%	74%	68%	71%	61%	78%	84%	60%	65%	76%	68%	71%
89.2%	87%	97%	92%	92%	89%	95%	89%	89%	87%	94%	90%	95%	94%	85%	90%	84%	81%	91%	95%	82%	75%
83.0%	79%	84%	82%	84%	90%	87%	73%	81%	81%	87%	89%	74%	86%	86%	90%	82%	75%	78%	86%	83%	87%
80.3%	86%	86%	84%	84%	68%	70%	87%	87%	90%	92%	82%	7%	91%	82%	88%	92%	73%	94%	73%	84%	87%
79.2%	84%	91%	79%	83%	79%	61%	92%	90%	93%	82%	76%	29%	86%	79%	85%	82%	81%	78%	78%	80%	75%
71.4%	78%	83%	71%	74%	71%	75%	69%	86%	85%	73%	63%	12%	80%	62%	77%	81%	68%	77%	76%	72%	67%
53.7%	69%	75%	75%	66%	52%	58%	58%	49%	55%	40%	46%	36%	37%	37%	74%	74%	34%	33%	43%	55%	61%
59.3%	68%	61%	67%	61%	58%	53%	62%	74%	70%	66%	46%	25%	62%	46%	75%	64%	53%	57%	60%	48%	69%
63.3%	69%	45%	75%	72%	87%	49%	62%	62%	58%	74%	55%	60%	61%	55%	76%	65%	56%	72%	40%	69%	68%
74.0%	76%	70%	75%	78%	81%	93%	81%	83%	85%	76%	74%	9%	82%	57%	76%	82%	75%	77%	76%	73%	76%
80.6%	79%	84%	81%	79%	78%	73%	84%	87%	86%	88%	86%	26%	87%	78%	87%	87%	90%	86%	86%	80%	80%
84.0%	79%	84%	83%	82%	87%	76%	83%	87%	89%	90%	90%	25%	94%	90%	89%	91%	95%	90%	88%	86%	85%
77.0%	78%	77%	67%	76%	80%	80%	82%	83%	79%	77%	79%	68%	79%	82%	77%	77%	80%	71%	76%	71%	78%
78.0%	80%	83%	82%	82%	78%	66%	85%	88%	92%	83%	79%	23%	82%	86%	84%	87%	82%	73%	67%	79%	77%
81.0%	83%	86%	86%	86%	74%	91%	86%	81%	87%	88%	81%	8%	89%	82%	92%	90%	87%	90%	78%	74%
79.1%	81%	84%	79%	80%	90%	82%	81%	76%	80%	87%	80%	21%	83%	77%	89%	85%	87%	77%	82%	83%	77%
70.0%	81%	75%	70%	68%	62%	65%	65%	86%	80%	74%	63%	34%	84%	60%	76%	82%	66%	63%	67%	72%	77%
67.2%	82%	71%	69%	74%	68%	71%	72%	83%	76%	50%	51%	60%	62%	58%	83%	75%	49%	77%	45%		69%
75.6%	86%	82%	82%	87%	79%	61%	83%	78%	73%	71%	74%	72%	66%	71%	77%	78%	74%	72%	82%	71%	68%
61.8%	71%	77%	63%	69%	55%	68%	68%	91%	78%	65%	43%	32%	64%	41%	62%	78%	46%	55%	56%	65%	51%
79.3%	85%	84%	80%	80%	85%	87%	82%	79%	85%	79%	79%	25%	83%	81%	84%	86%	83%	70%	83%	81%	84%
78.0%	98%	96%	85%	100%	94%	75%	83%	82%	98%	82%	96%	49%	49%	39%	100%	98%	90%	79%	39%	68%	39%
48.2%	51%	46%	35%	49%	55%	27%	65%	65%	51%	33%	46%	7%	7%	84%	47%	51%	40%	31%	84%	84%	55%
69.2%	80%	76%	71%	84%	80%	76%	77%	81%	69%	66%	56%	91%	62%	44%	79%	80%	51%	67%	51%	59%	53%
78.0%	83%	83%	79%	81%	47%	83%	86%	81%	78%	79%	75%	73%	90%	85%	67%	68%	77%	77%	79%	86%	80%
79.6%	93%	81%	94%	93%	87%	82%	90%	85%	82%	84%	69%	77%	82%	66%	88%	86%	60%	74%	62%	62%	74%
77.6%	85%	86%	81%	84%	79%	78%	88%	90%	88%	77%	72%	22%	74%	70%	82%	85%	81%	74%	73%	75%	86%
87.2%	96%	92%	95%	93%	80%	95%	93%	94%	97%	91%	89%	65%	94%	62%	98%	93%	84%	93%	70%	93%	65%
73.3%	87%	76%	76%	74%	73%	80%	85%	90%	83%	62%	62%	81%	68%	56%	77%	87%	61%	67%	55%	60%	79%
74.2%	87%	85%	73%	88%	95%	63%	94%	94%	90%	70%	85%	40%	40%	49%	98%	95%	78%	68%	49%	68%	49%
80.3%	90%	73%	82%	90%	90%	77%	86%	89%	82%	83%	54%	80%	84%	69%	89%	88%	68%	90%	55%	88%	80%
65.7%	100%	52%	55%	60%	63%	56%	66%	60%	53%	64%	55%	55%	55%	58%	100%	100%	63%	59%	50%	55%	100%
71.4%	66%	89%	63%	67%	74%	68%	72%	66%	76%	66%	89%	49%	59%	91%	80%	84%	74%	63%	74%	56%	73%

Model Similarity Dendrogram

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