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 Dtef Global Dialogues Gd3 AiConcern%3Aequally Concerned And Excited - Run 6b3e815...

Global Dialogues GD3 - Equally concerned and excited

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

TAGS:

Instruction Following & Prompt Adherence

AI Safety & Robustness

Demographic Processes

Trust

Best Models (Coverage)

1.Claude Haiku 4.5
83.7%
2.Claude Sonnet 4.5
83.7%
3.Gemini 2.5 Flash
81.8%
4.Llama 4 Maverick
81.4%
5.Claude Sonnet 4
81.3%

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	1st 83.7%	5th 81.3%	2nd 83.7%	3rd 81.8%	12th 78.0%	4th 81.4%	10th 78.4%	7th 79.9%	8th 79.7%	13th 72.3%	11th 78.2%	9th 78.6%	6th 80.6%
85.8%	85%	89%	94%	86%	80%	89%	82%	91%	88%	86%	79%	84%	83%
85.8%	87%	88%	91%	83%	72%	91%	75%	89%	86%	83%	89%	93%	89%
67.2%	72%	63%	73%	62%	77%	66%	62%	65%	72%	62%	62%	62%	76%
74.9%	84%	70%	75%	74%	74%	78%	78%	61%	76%	59%	75%	86%	84%
91.9%	96%	95%	90%	85%	94%	86%	95%	90%	96%	92%	92%	96%	88%
87.0%	91%	86%	87%	92%	94%	88%	87%	82%	91%	77%	77%	88%	91%
85.9%	91%	85%	89%	92%	78%	82%	84%	89%	90%	85%	88%	78%	86%
81.1%	87%	81%	81%	83%	72%	91%	77%	84%	86%	79%	83%	71%	79%
87.4%	84%	79%	84%	95%	86%	87%	88%	89%	92%	89%	89%	84%	90%
74.2%	87%	66%	75%	77%	79%	74%	74%	57%	78%	50%	74%	87%	86%
84.5%	85%	89%	81%	86%	94%	93%	89%	91%	91%	63%	78%	83%	75%
70.5%	86%	63%	78%	79%	73%	69%	58%	58%	73%	48%	66%	79%	87%
86.3%	96%	89%	96%	87%	86%	77%	87%	96%	80%	64%	85%	85%	94%
84.5%	84%	84%	80%	84%	93%	99%	83%	81%	81%	82%	80%	86%	82%
86.1%	83%	97%	93%	88%	88%	89%	86%	93%	82%	66%	87%	82%	85%
82.1%	86%	87%	96%	88%	70%	84%	80%	84%	78%	76%	78%	78%	82%
68.5%	74%	73%	77%	67%	75%	57%	72%	61%	62%	69%	60%	70%	74%
70.2%	76%	71%	83%	74%	56%	66%	68%	66%	72%	71%	72%	68%	70%
67.8%	61%	82%	80%	55%	54%	84%	64%	85%	62%	72%	71%	59%	52%
89.8%	94%	85%	94%	93%	92%	84%	84%	91%	90%	90%	93%	87%	90%
85.1%	84%	92%	91%	85%	80%	95%	88%	96%	83%	71%	84%	74%	83%
87.5%	95%	88%	92%	90%	74%	93%	90%	90%	86%	74%	91%	82%	92%
80.8%	84%	89%	86%	85%	78%	80%	82%	76%	78%	66%	78%	84%	84%
87.4%	88%	92%	93%	85%	93%	90%	86%	95%	89%	70%	80%	81%	94%
83.5%	84%	82%	78%	82%	90%	90%	81%	79%	84%	76%	91%	88%	81%
76.2%	71%	81%	80%	75%	77%	76%	78%	82%	78%	68%	74%	73%	77%
73.8%	77%	82%	83%	75%	55%	74%	73%	76%	71%	72%	71%	73%	77%
81.1%	90%	80%	87%	92%	75%	78%	89%	75%	82%	75%	79%	75%	77%
68.5%	88%	72%	78%	71%	70%	75%	54%	56%	71%	44%	59%	73%	79%
75.2%	84%	73%	78%	90%	72%	63%	74%	67%	82%	67%	67%	78%	83%
84.8%	83%	94%	91%	87%	88%	85%	84%	90%	81%	71%	83%	76%	89%
79.7%	75%	84%	74%	86%	70%	81%	85%	79%	75%	86%	86%	84%	71%
60.3%	65%	57%	66%	55%	70%	59%	55%	60%	65%	55%	55%	57%	65%
82.3%	87%	84%	88%	94%	78%	75%	80%	85%	82%	82%	81%	71%	83%
74.5%	86%	67%	67%	79%	63%	67%	61%	66%	76%	83%	85%	90%	79%
82.2%	79%	90%	84%	83%	82%	92%	82%	85%	82%	76%	78%	78%	78%
86.1%	80%	90%	87%	89%	89%	89%	86%	88%	82%	77%	84%	86%	92%
82.6%	91%	90%	86%	76%	92%	94%	86%	92%	75%	71%	79%	74%	68%
79.5%	84%	89%	89%	84%	65%	84%	81%	84%	78%	75%	81%	68%	72%
93.5%	100%	92%	98%	90%	94%	94%	90%	96%	99%	90%	90%	92%	90%
85.3%	86%	84%	93%	92%	82%	91%	93%	83%	79%	81%	83%	75%	87%
49.2%	61%	43%	53%	67%	44%	61%	44%	58%	37%	37%	44%	58%	32%
81.9%	89%	80%	80%	76%	86%	79%	77%	76%	85%	81%	81%	85%	90%