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: Gd5 Dtef Global Dialogues Gd5 AiConcern%3Amore Concerned Than Excited - Run b741d02...

Global Dialogues GD5 - More concerned than excited

DTEF: Predict response distributions for More concerned than excited. Source: Global Dialogues GD5 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

AI Safety & Robustness

Environmental Justice & Activism

Best Models (Coverage)

1.Claude Sonnet 4.5
80.7%
2.Claude Haiku 4.5
80.7%
3.Claude Sonnet 4
79.0%
4.GPT 4.1
78.9%
5.Llama 4 Maverick
78.6%

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 Haiku 4.5	Claude Sonnet 4	Claude Sonnet 4.5	Gemini 2.5 Flash	Gemma 3 12b It	Llama 4 Maverick	Mistral Medium 3	GPT 4.1	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini	Qwen3 30b A3B Instruct 2507	Qwen3 Next 80b A3B Instruct
Score	2nd 80.7%	3rd 79.0%	1st 80.7%	8th 77.0%	13th 72.8%	5th 78.6%	7th 77.1%	4th 78.9%	6th 77.6%	12th 73.5%	9th 76.2%	11th 75.0%	10th 75.9%
77.9%	83%	79%	78%	83%	70%	93%	75%	65%	86%	74%	75%	81%	71%
79.1%	89%	89%	88%	74%	70%	80%	86%	89%	71%	72%	68%	80%	72%
62.5%	66%	71%	80%	60%	63%	59%	61%	56%	57%	57%	57%	58%	67%
60.2%	59%	57%	68%	75%	50%	62%	52%	62%	58%	63%	71%	53%	52%
86.2%	90%	90%	92%	85%	76%	87%	91%	93%	93%	56%	91%	89%	87%
84.3%	87%	79%	77%	90%	76%	81%	85%	92%	85%	89%	86%	87%	82%
89.2%	82%	95%	97%	76%	89%	95%	87%	92%	92%	91%	87%	84%	93%
64.5%	63%	72%	72%	72%	40%	77%	67%	82%	59%	63%	51%	58%	63%
75.2%	76%	89%	87%	91%	69%	85%	90%	84%	51%	78%	66%	46%	65%
77.8%	85%	69%	82%	87%	62%	82%	71%	77%	85%	78%	83%	75%	76%
77.5%	81%	78%	88%	81%	75%	80%	72%	76%	81%	73%	81%	63%	79%
85.2%	91%	92%	68%	68%	94%	90%	88%	78%	82%	92%	80%	94%	91%
69.9%	67%	73%	80%	82%	68%	64%	74%	74%	76%	58%	53%	68%	72%
73.8%	72%	70%	81%	87%	63%	76%	64%	77%	77%	77%	86%	66%	64%
67.4%	68%	69%	70%	67%	64%	66%	66%	72%	64%	60%	72%	70%	68%
69.5%	80%	66%	65%	69%	69%	73%	72%	55%	63%	68%	79%	73%	72%
82.8%	89%	95%	95%	79%	72%	89%	87%	87%	85%	65%	77%	81%	76%
83.5%	91%	91%	83%	79%	73%	84%	94%	94%	85%	73%	77%	88%	74%
76.9%	80%	82%	78%	75%	69%	76%	85%	83%	80%	80%	70%	72%	70%
75.5%	93%	76%	85%	70%	77%	67%	75%	81%	74%	74%	74%	61%	74%
72.4%	72%	67%	67%	77%	77%	64%	74%	75%	76%	63%	74%	79%	76%
81.6%	90%	84%	86%	71%	76%	78%	78%	68%	83%	86%	90%	86%	85%
90.4%	95%	86%	95%	90%	80%	95%	95%	90%	86%	92%	90%	95%	86%
69.0%	68%	69%	66%	76%	63%	68%	76%	67%	67%	68%	73%	67%	69%
68.9%	66%	72%	79%	81%	66%	63%	72%	73%	76%	57%	52%	67%	72%
86.1%	93%	84%	84%	89%	94%	87%	73%	92%	89%	83%	83%	84%	84%
82.7%	95%	77%	80%	90%	91%	78%	79%	90%	84%	71%	83%	72%	85%
80.5%	80%	78%	80%	81%	88%	87%	77%	87%	85%	77%	80%	76%	70%
88.2%	95%	95%	98%	89%	55%	79%	71%	99%	96%	99%	96%	79%	96%
80.5%	85%	90%	86%	75%	69%	91%	85%	91%	80%	69%	84%	70%	72%
73.8%	80%	65%	83%	80%	70%	91%	71%	55%	69%	67%	68%	79%	82%
60.4%	68%	62%	64%	44%	59%	57%	61%	64%	60%	70%	57%	64%	55%
74.0%	82%	67%	78%	70%	60%	80%	68%	78%	79%	72%	84%	71%	73%
77.4%	81%	70%	68%	92%	68%	84%	76%	84%	74%	87%	80%	77%	65%
85.1%	83%	87%	82%	89%	83%	86%	90%	84%	88%	80%	82%	85%	87%
77.8%	75%	81%	77%	78%	76%	81%	79%	80%	78%	79%	70%	76%	82%
86.5%	90%	93%	95%	66%	88%	93%	87%	82%	80%	87%	85%	87%	92%
63.3%	70%	60%	65%	61%	64%	64%	69%	68%	59%	68%	64%	60%	51%
65.2%	68%	67%	69%	56%	67%	61%	61%	80%	78%	45%	69%	60%	67%
83.4%	87%	84%	87%	69%	86%	88%	72%	69%	90%	87%	90%	84%	91%
85.6%	95%	93%	93%	84%	84%	87%	87%	86%	87%	59%	87%	84%	87%
75.7%	71%	73%	70%	89%	80%	80%	77%	82%	78%	73%	72%	66%	73%
70.5%	79%	79%	80%	63%	54%	77%	74%	72%	64%	92%	53%	74%	56%
79.9%	75%	88%	85%	72%	82%	71%	79%	74%	87%	65%	89%	86%	86%
90.0%	92%	93%	90%	91%	94%	90%	87%	83%	85%	93%	89%	90%	93%
81.2%	84%	88%	91%	71%	88%	69%	86%	88%	89%	53%	76%	85%	88%