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 Excited Than Concerned C10 - Run b259408...

Global Dialogues GD3 - More excited than concerned (10 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 Sonnet 4
85.7%
2.Claude Sonnet 4.5
85.7%
3.GPT 5
85.4%
4.Claude 3.7 Sonnet
85.2%
5.GPT 4.1
84.0%

🔀 Least Similar Models

Claude Haiku 4.5vsGPT 4.1 Nano

67.1% similarity

👯 Most Similar Models

Claude Sonnet 4.5vsClaude Sonnet 4

90.7% 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
Score	4th 85.2%	6th 83.7%	1st 85.7%	2nd 85.7%	15th 79.2%	17th 78.5%	11th 81.3%	13th 79.5%	12th 80.5%	5th 84.0%	9th 81.7%	21st 61.5%	8th 82.1%	14th 79.3%	3rd 85.4%	7th 83.2%	19th 74.4%	20th 68.3%	10th 81.3%	18th 76.0%	16th 78.9%
78.8%	94%	87%	85%	93%	68%	69%	87%	90%	76%	94%	87%	67%	84%	64%	91%	85%	74%	43%	87%	51%
75.2%	75%	74%	91%	90%	55%	70%	79%	81%	61%	87%	85%	16%	82%	72%	89%	89%	92%	72%	61%	83%
83.9%	82%	72%	85%	85%	81%	85%	74%	81%	70%	89%	92%	94%	92%	94%	77%	79%	75%	86%	92%	92%
91.7%	98%	85%	95%	90%	86%	85%	95%	96%	96%	94%	91%	91%	89%	90%	93%	97%	88%	92%	89%	94%
87.2%	89%	90%	81%	87%	77%	82%	83%	97%	91%	96%	95%	87%	95%	75%	90%	95%	89%	78%	80%	87%
91.1%	92%	95%	88%	92%	85%	93%	95%	93%	91%	91%	94%	92%	95%	96%	86%	85%	93%	85%	92%	90%
88.2%	96%	93%	93%	94%	98%	95%	90%	92%	94%	96%	93%	97%	91%	97%	93%	92%	35%	42%	85%	97%
79.3%	88%	89%	84%	91%	57%	78%	95%	86%	80%	90%	86%	44%	82%	72%	90%	88%	81%	60%	72%	72%
82.3%	82%	84%	86%	84%	91%	67%	92%	83%	81%	88%	86%	82%	91%	78%	75%	86%	71%	74%	77%	87%
88.3%	95%	91%	89%	93%	91%	91%	80%	80%	91%	91%	91%	91%	95%	91%	87%	86%	79%	70%	91%	94%
75.0%	78%	85%	87%	86%	87%	59%	69%	88%	78%	65%	74%	52%	59%	71%	77%	68%	84%	60%	90%	84%
85.6%	89%	94%	91%	93%	96%	78%	83%	90%	90%	84%	84%	93%	83%	90%	85%	78%	82%	62%	94%	69%	90%
75.3%	72%	83%	88%	80%	92%	93%	68%	60%	78%	80%	86%	53%	80%	92%	77%	70%	69%	45%	80%	61%
82.5%	90%	79%	93%	93%	64%	76%	94%	91%	80%	85%	75%	75%	94%	67%	91%	84%	73%	80%	93%	75%	80%
82.7%	93%	86%	86%	86%	89%	92%	86%	80%	86%	87%	84%	60%	89%	88%	88%	84%	63%	66%	82%	78%
79.6%	87%	86%	88%	90%	56%	76%	88%	83%	73%	85%	86%	77%	78%	68%	86%	82%	75%	76%	86%	67%
76.9%	77%	91%	88%	72%	73%	64%	74%	57%	73%	74%	81%	90%	73%	86%	81%	81%	70%	67%	90%	75%
75.3%	86%	79%	81%	82%	78%	53%	64%	78%	76%	79%	82%	70%	79%	74%	87%	80%	80%	33%	78%	86%
63.2%	65%	51%	67%	57%	76%	51%	61%	71%	72%	82%	62%	55%	67%	54%	77%	82%	53%	55%	52%	67%	51%
82.5%	88%	88%	89%	96%	93%	75%	89%	70%	72%	93%	73%	76%	81%	76%	95%	86%	82%	72%	80%	77%	82%
77.0%	84%	88%	89%	89%	68%	82%	83%	78%	84%	90%	72%	16%	91%	73%	87%	80%	70%	78%	67%	72%
80.8%	84%	84%	88%	89%	90%	80%	91%	74%	92%	86%	92%	10%	82%	90%	96%	87%	62%	78%	81%	81%
79.1%	75%	71%	76%	76%	83%	83%	92%	87%	75%	89%	85%	55%	89%	90%	82%	76%	80%	64%	88%	74%	72%
77.4%	80%	88%	95%	82%	94%	94%	70%	70%	85%	82%	84%	33%	86%	78%	80%	80%	67%	49%	79%	71%
82.3%	80%	78%	93%	94%	64%	78%	93%	79%	92%	85%	94%	76%	79%	76%	89%	87%	73%	78%	90%	69%
73.2%	77%	84%	85%	79%	68%	67%	77%	76%	78%	81%	73%	50%	79%	61%	74%	87%	66%	71%	76%	54%
76.7%	88%	83%	81%	87%	78%	59%	80%	85%	74%	86%	64%	65%	78%	75%	85%	82%	70%	75%	71%	68%
87.3%	93%	91%	90%	95%	87%	85%	95%	91%	84%	96%	96%	27%	97%	91%	87%	94%	90%	88%	85%	84%
76.5%	92%	90%	95%	95%	85%	66%	76%	70%	71%	74%	65%	78%	66%	70%	86%	75%	69%	65%	67%	75%
79.0%	81%	83%	78%	87%	73%	79%	73%	84%	79%	78%	84%	76%	84%	67%	84%	77%	87%	65%	85%	77%
75.0%	84%	77%	81%	82%	88%	94%	80%	79%	82%	77%	82%	8%	70%	89%	88%	84%	62%	57%	83%	52%
70.0%	73%	83%	70%	70%	74%	70%	81%	74%	85%	66%	64%	51%	64%	51%	80%	80%	68%	69%	63%	64%
81.7%	80%	70%	82%	82%	79%	83%	72%	79%	68%	87%	89%	96%	89%	96%	70%	60%	89%	84%	90%	89%
81.4%	86%	81%	82%	84%	88%	75%	76%	80%	82%	87%	79%	76%	79%	81%	83%	83%	84%	84%	77%	81%
73.9%	82%	95%	73%	73%	72%	68%	57%	51%	67%	64%	73%	58%	69%	75%	84%	72%	70%	90%	92%	93%
74.5%	78%	81%	82%	82%	42%	84%	78%	74%	71%	79%	74%	79%	77%	74%	69%	71%	75%	67%	78%	75%
74.6%	91%	78%	84%	84%	85%	90%	78%	67%	86%	76%	77%	8%	75%	83%	79%	86%	58%	54%	78%
83.1%	86%	87%	93%	96%	80%	81%	80%	93%	98%	89%	72%	51%	96%	86%	94%	95%	67%	66%	83%	70%
80.5%	88%	90%	94%	94%	85%	89%	89%	80%	81%	89%	75%	28%	89%	90%	85%	83%	67%	71%	88%	58%	77%
88.3%	94%	96%	91%	91%	94%	90%	98%	95%	94%	87%	84%	70%	84%	70%	99%	85%	89%	89%	83%	84%
82.8%	96%	87%	94%	94%	65%	91%	89%	91%	84%	91%	95%	39%	90%	89%	94%	93%	86%	27%	88%	72%
70.7%	100%	61%	66%	66%	100%	66%	62%	53%	63%	61%	63%	44%	59%	66%	100%	100%	58%	67%	63%	67%	100%
82.8%	76%	91%	90%	79%	71%	91%	79%	63%	77%	81%	91%	89%	79%	94%	84%	83%	83%	85%	91%	78%

Model Similarity Dendrogram

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