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%3Amore Concerned Than Excited C10 - Run b965c63...

Global Dialogues GD3 - More concerned than excited (10 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

Social interaction

Knowledge, learning and memory

Best Models (Coverage)

1.GPT 5.1
85.1%
2.Claude 3.7 Sonnet
84.4%
3.GPT 5
83.4%
4.Claude Haiku 4.5
83.0%
5.Claude Sonnet 4.5
81.8%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT 4.1 Nano

70.4% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

91.2% 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	2nd 84.4%	4th 83.0%	10th 79.4%	5th 81.8%	12th 78.0%	18th 74.4%	8th 81.2%	7th 81.4%	6th 81.7%	9th 80.6%	19th 73.7%	21st 48.7%	15th 76.0%	20th 70.6%	3rd 83.4%	1st 85.1%	14th 76.7%	17th 74.9%	13th 76.8%	16th 75.9%	11th 78.6%
80.1%	86%	92%	83%	78%	75%	78%	84%	91%	88%	92%	70%	38%	94%	65%	82%	95%	81%	66%	84%	77%	84%
81.1%	83%	81%	87%	90%	75%	87%	82%	89%	97%	92%	71%	16%	96%	80%	85%	84%	89%	62%	93%	79%	86%
50.8%	59%	55%	39%	78%	59%	39%	69%	70%	59%	49%	53%	11%	11%	80%	59%	55%	43%	39%	53%	43%	43%
89.0%	96%	73%	91%	92%	90%	83%	93%	94%	93%	93%	89%	94%	94%	88%	93%	93%	91%	84%	84%	74%	86%
89.8%	98%	95%	97%	97%	93%	95%	94%	88%	90%	89%	77%	77%	92%	77%	95%	95%	92%	75%	95%	82%	93%
83.4%	94%	94%	93%	93%	88%	77%	78%	78%	76%	74%	70%	95%	78%	90%	84%	90%	71%	89%	75%	82%	82%
83.3%	83%	87%	81%	84%	70%	87%	83%	88%	93%	83%	78%	74%	89%	90%	85%	91%	88%	78%	83%	72%	83%
71.3%	76%	86%	66%	72%	68%	62%	80%	82%	84%	79%	63%	27%	83%	67%	77%	87%	73%	64%	62%	63%	76%
77.0%	89%	84%	70%	70%	91%	68%	84%	71%	75%	79%	75%	76%	78%	67%	78%	88%	83%	73%	69%	78%	70%
90.5%	91%	94%	94%	96%	94%	94%	92%	83%	88%	95%	89%	95%	93%	94%	87%	89%	84%	84%	94%	85%	85%
77.7%	87%	87%	86%	85%	66%	84%	79%	79%	83%	72%	79%	79%	74%	58%	78%	83%	72%	65%	87%	69%	79%
86.9%	86%	95%	90%	96%	95%	80%	90%	94%	91%	76%	88%	95%	67%	81%	89%	81%	79%	87%	95%	85%	85%
78.5%	78%	81%	84%	81%	85%	82%	77%	79%	79%	78%	86%	56%	73%	86%	79%	74%	78%	81%	86%	78%	68%
88.5%	89%	92%	90%	91%	88%	91%	90%	87%	93%	94%	90%	56%	95%	86%	91%	96%	93%	85%	93%	82%	87%
81.8%	88%	91%	79%	87%	77%	80%	94%	90%	89%	89%	76%	8%	89%	73%	89%	92%	87%	85%	79%	85%	91%
77.4%	82%	87%	78%	82%	79%	83%	78%	88%	82%	87%	65%	12%	86%	62%	80%	82%	89%	82%	86%	83%	73%
53.7%	65%	75%	66%	66%	50%	46%	58%	46%	54%	49%	46%	40%	38%	37%	70%	73%	41%	51%	40%	61%	56%
65.7%	76%	76%	69%	69%	64%	58%	64%	78%	74%	72%	52%	52%	74%	46%	69%	72%	57%	58%	67%	61%	72%
68.7%	75%	60%	77%	71%	66%	56%	66%	67%	70%	76%	59%	56%	79%	77%	83%	73%	71%	83%	55%	72%	51%
80.4%	85%	85%	85%	83%	77%	74%	88%	80%	81%	87%	83%	72%	83%	73%	88%	82%	75%	77%	77%	72%	82%
82.5%	84%	81%	81%	81%	89%	72%	86%	85%	88%	94%	87%	15%	95%	77%	83%	93%	88%	87%	84%	94%	88%
84.2%	84%	89%	85%	82%	91%	74%	85%	88%	88%	93%	82%	17%	93%	83%	93%	87%	88%	90%	92%	94%	91%
79.1%	80%	81%	77%	76%	85%	72%	82%	83%	78%	83%	79%	78%	81%	76%	78%	84%	82%	71%	82%	77%	77%
79.5%	83%	83%	80%	80%	85%	74%	83%	84%	89%	85%	80%	25%	83%	82%	85%	84%	81%	77%	85%	77%	84%
87.8%	90%	89%	89%	87%	79%	88%	86%	91%	96%	95%	89%	55%	89%	89%	94%	93%	92%	83%	96%	84%	89%
78.3%	79%	81%	83%	79%	84%	79%	81%	70%	80%	88%	81%	24%	81%	80%	79%	86%	84%	80%	84%		82%
75.4%	85%	84%	78%	75%	73%	68%	75%	88%	87%	85%	61%	12%	83%	55%	83%	91%	72%	82%	80%	84%	83%
71.2%	85%	94%	74%	82%	82%	70%	80%	84%	73%	61%	54%	48%	64%	43%	85%	91%	58%	84%	57%	68%	58%
76.1%	85%	87%	84%	89%	87%	64%	87%	71%	72%	72%	75%	66%	71%	71%	76%	77%	72%	72%	78%	71%	71%
70.0%	83%	83%	74%	81%	67%	75%	71%	88%	79%	77%	46%	53%	75%	41%	69%	79%	50%	79%	58%	69%	73%
79.4%	85%	79%	83%	77%	85%	82%	82%	79%	86%	85%	79%	21%	85%	78%	85%	84%	83%	75%	82%	89%	84%
85.3%	94%	98%	85%	74%	94%	85%	83%	82%	94%	96%	100%	49%	49%	39%	94%	98%	98%	89%	100%	93%	98%
50.0%	55%	51%	35%	73%	55%	35%	65%	65%	55%	45%	49%	7%	7%	84%	55%	55%	47%	39%	49%	84%	41%
76.2%	89%	72%	80%	85%	85%	67%	67%	81%	80%	82%	70%	72%	75%	68%	79%	84%	79%	68%	70%	72%	76%
78.8%	87%	86%	82%	91%	47%	68%	77%	74%	73%	72%	73%	81%	85%	85%	87%	83%	76%	83%	86%	77%	82%
81.3%	89%	87%	97%	92%	78%	89%	89%	92%	91%	94%	66%	34%	91%	67%	80%	85%	80%	69%	65%	82%	90%
81.6%	88%	86%	82%	85%	81%	88%	88%	89%	90%	88%	79%	25%	89%	69%	90%	89%	84%	81%	77%	79%	86%
87.3%	97%	79%	95%	95%	82%	95%	93%	95%	97%	96%	97%	46%	93%	84%	91%	90%	80%	80%	70%	88%	90%
74.2%	87%	87%	77%	74%	90%	69%	86%	86%	72%	74%	62%	31%	80%	55%	91%	85%	68%	73%	64%	67%	81%
79.0%	95%	91%	73%	85%	95%	73%	94%	94%	95%	84%	88%	40%	40%	49%	95%	90%	86%	77%	88%	49%	79%
81.5%	89%	92%	87%	90%	66%	80%	93%	93%	92%	78%	63%	63%	85%	46%	97%	94%	88%	88%	64%	77%	87%
65.3%	100%	49%	57%	55%	57%	53%	63%	57%	53%	66%	55%	52%	55%	66%	100%	100%	51%	63%	53%	67%	100%
70.2%	71%	89%	72%	67%	67%	75%	73%	61%	67%	66%	94%	53%	53%	71%	75%	83%	72%	63%	81%	64%	58%

Model Similarity Dendrogram

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