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 Excited Than Concerned C5 - Run 64bf85a...

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

DTEF: Predict response distributions for More excited than concerned. 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
85.8%
2.Claude Sonnet 4
84.8%
3.GPT 5.1
84.6%
4.Claude Sonnet 4.5
84.5%
5.GPT 5
84.1%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT 4.1 Nano

64.2% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

90.3% 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 85.8%	7th 82.8%	2nd 84.8%	4th 84.5%	17th 72.9%	19th 72.3%	11th 81.7%	12th 80.4%	10th 81.8%	9th 82.0%	6th 83.6%	21st 47.6%	13th 77.5%	14th 77.2%	5th 84.1%	3rd 84.6%	20th 71.4%	18th 72.4%	15th 76.9%	16th 73.4%	8th 82.0%
80.5%	93%	93%	90%	92%	66%	73%	90%	92%	90%	97%	86%	21%	84%	68%	91%	94%	74%	77%	76%	54%	89%
75.2%	84%	74%	91%	94%	57%	71%	87%	77%	70%	77%	85%	16%	79%	78%	85%	93%	74%	62%	68%	79%	78%
83.0%	82%	85%	85%	85%	89%	10%	74%	93%	81%	94%	98%	79%	79%	94%	77%	75%	92%	98%	98%	79%	96%
90.4%	97%	86%	89%	90%	92%	90%	93%	90%	96%	90%	95%	88%	96%	87%	94%	97%	87%	85%	88%	83%	86%
84.9%	90%	95%	79%	78%	85%	82%	83%	96%	87%	94%	86%	72%	81%	90%	87%	96%	83%	74%	80%	92%	72%
90.6%	87%	95%	88%	92%	81%	92%	96%	88%	92%	92%	92%	97%	95%	88%	82%	87%	94%	96%	84%	90%	94%
77.0%	89%	95%	88%	92%	59%	79%	84%	93%	88%	86%	95%	55%	70%	57%	87%	91%	22%	72%	59%		80%
81.0%	90%	82%	78%	91%	80%	69%	83%	87%	79%	94%	89%	64%	94%	65%	85%	92%	72%	68%	81%	68%	91%
78.8%	87%	83%	86%	84%	92%	53%	81%	83%	84%	78%	85%	51%	79%	78%	76%	80%	79%	79%	77%	84%	76%
88.0%	93%	93%	85%	93%	87%	93%	83%	81%	83%	85%	92%	91%	84%	88%	88%	83%	78%	90%	88%	95%	96%
78.4%	83%	85%	85%	85%	74%	88%	69%	87%	85%	68%	84%	52%	59%	82%	85%	75%	89%	55%	86%	86%	85%
89.5%	88%	95%	91%	95%	93%	89%	83%	91%	90%	96%	84%	93%	90%	88%	93%	85%	82%	87%	88%	89%	90%
77.0%	78%	83%	88%	80%	92%	84%	81%	74%	89%	78%	88%	16%	80%	87%	82%	91%	65%	55%	81%	54%	90%
64.0%	85%	76%	84%	78%	42%	66%	84%	64%	66%	72%	64%	39%	55%	48%	69%	75%	52%	72%	34%	62%	56%
81.2%	88%	87%	86%	86%	84%	94%	88%	73%	89%	90%	92%	18%	89%	85%	83%	94%	69%	62%	83%	84%	81%
78.9%	88%	88%	85%	90%	64%	66%	87%	88%	79%	90%	87%	57%	77%	73%	88%	88%	67%	60%	80%	67%	87%
79.9%	84%	93%	94%	75%	74%	89%	73%	73%	73%	77%	85%	35%	75%	86%	83%	83%	76%	86%	90%	88%	86%
74.4%	79%	79%	75%	81%	65%	47%	63%	76%	82%	76%	81%	28%	87%	85%	90%	79%	77%	75%	78%	74%	85%
57.1%	60%	48%	70%	64%	81%	47%	68%	52%	64%	57%	55%	44%	52%	49%	70%	73%	51%	48%	40%	54%	53%
78.0%	92%	96%	87%	92%	68%	85%	89%	83%	75%	82%	87%	21%	89%	57%	89%	84%	56%	69%	78%	73%	85%
78.4%	85%	89%	85%	86%	67%	82%	93%	85%	85%	84%	83%	32%	80%	78%	77%	89%	65%	61%	84%	69%	87%
79.8%	80%	85%	86%	87%	60%	94%	93%	87%	91%	84%	92%	23%	73%	93%	96%	93%	65%	68%	69%	72%	84%
75.4%	70%	71%	71%	76%	89%	86%	87%	81%	75%	72%	72%	64%	72%	90%	73%	85%	75%	64%	71%	70%	70%
76.7%	86%	91%	96%	86%	80%	86%	74%	82%	85%	90%	88%	16%	67%	59%	95%	90%	59%	46%	78%	73%	84%
66.2%	81%	87%	84%	79%	52%	76%	82%	80%	70%	70%	72%	22%	51%	52%	80%	89%	54%	63%	36%	45%	66%
70.2%	80%	80%	82%	79%	42%	62%	74%	73%	79%	77%	72%	44%	72%	66%	75%	81%	61%	66%	77%	59%	74%
74.8%	88%	83%	82%	86%	73%	45%	70%	79%	79%	85%	70%	21%	83%	78%	86%	86%	70%	78%	79%	62%	87%
85.3%	90%	97%	90%	87%	79%	84%	95%	89%	84%	90%	97%	27%	85%	89%	88%	95%	81%	78%	91%	84%	92%
77.1%	93%	90%	96%	94%	87%	74%	84%	71%	70%	67%	73%	78%	69%	70%	77%	72%	70%	67%	70%	72%	75%
77.5%	76%	83%	78%	85%	67%	75%	64%	85%	81%	84%	92%	67%	84%	67%	86%	74%	68%	73%	78%	73%	88%
76.7%	86%	77%	82%	82%	83%	90%	82%	72%	85%	77%	85%	17%	70%	80%	86%	90%	71%	65%	83%	64%	83%
59.3%	73%	70%	70%	70%	66%	10%	81%	62%	74%	61%	55%	41%	41%	51%	69%	72%	64%	60%	54%	41%	60%
79.6%	82%	0%	82%	82%	86%	10%	72%	91%	79%	92%	99%	81%	81%	96%	88%	85%	89%	93%	100%	89%	94%
83.0%	87%	93%	85%	88%	50%	78%	85%	85%	93%	83%	91%	37%	94%	79%	92%	82%	85%	92%	75%	94%	94%
74.6%	90%	81%	78%	77%	36%	87%	65%	75%	90%	79%	68%	70%	87%	87%	56%	57%	79%	80%	80%	80%	65%
74.9%	80%	80%	82%	82%	40%	80%	83%	87%	71%	81%	86%	32%	82%	77%	71%	70%	71%	73%	82%	83%	79%
74.5%	84%	78%	84%	84%	84%	88%	85%	62%	80%	74%	78%	8%	84%	83%	82%	76%	56%	68%	84%	49%	93%
83.4%	94%	87%	90%	87%	79%	78%	80%	97%	98%	96%	99%	71%	85%	79%	89%	96%	60%	54%	84%	65%	83%
82.3%	91%	93%	95%	91%	72%	90%	88%	82%	86%	85%	79%	22%	83%	90%	85%	86%	75%	81%	89%	75%	90%
78.7%	94%	91%	91%	91%	87%	10%	98%	82%	94%	81%	74%	58%	58%	70%	99%	87%	84%	80%	74%	70%	80%
84.3%	96%	87%	90%	94%	66%	89%	90%	92%	83%	92%	95%	39%	89%	89%	91%	92%	80%	78%	75%	76%	88%
72.3%	100%	66%	72%	66%	77%	76%	70%	52%	63%	61%	72%	59%	59%	66%	100%	100%	68%	67%	72%	72%	80%
85.3%	86%	91%	91%	79%	88%	93%	78%	67%	80%	89%	91%	79%	90%	97%	93%	77%	83%	88%	86%	89%	76%

Model Similarity Dendrogram

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