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: Gd6uk C10 Dtef Global Dialogues Gd6uk AiConcern%3Aequally Concerned And Excited C10 - Run 76e9f49...

Global Dialogues GD6UK - Equally concerned and excited (10 context Qs)

DTEF: Predict response distributions for Equally concerned and excited. Source: Global Dialogues GD6UK (https://github.com/collect-intel/global-dialogues)

TAGS:

PERIODIC

Dtef

Demographic

Global Dialogues Gd6uk

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Efficiency & Succinctness

AI Safety & Robustness

Data Privacy & Bodily Autonomy

General Knowledge

Credibility

Best Models (Coverage)

1.Claude Haiku 4.5
77.0%
2.GPT 4.1 Mini
76.6%
3.Gemini 2.5 Flash
76.1%
4.Gemma 3 12b It
73.4%
5.GPT 4o Mini
68.1%

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	Gemini 2.5 Flash	Gemma 3 12b It	GPT 4.1 Mini	GPT 4.1 Nano	GPT 4o Mini
Score	1st 77.0%	3rd 76.1%	4th 73.4%	2nd 76.6%	6th 65.8%	5th 68.1%
78.2%	70%	65%	86%	88%	73%	87%
77.8%	78%	72%	68%	89%	78%	82%
70.2%	63%	74%	79%	76%	64%	65%
82.3%	90%	91%	80%	83%	68%	82%
81.7%	85%	83%	87%	85%	78%	72%
82.2%	87%	82%	90%	79%	82%	73%
65.2%	57%	84%	70%	59%	58%	63%
45.0%	36%	57%	55%	37%	41%	44%
77.5%	64%	87%	73%	86%	87%	68%
81.3%	81%	82%	77%	86%	90%	72%
59.7%	66%	71%	55%	36%	67%	63%
74.7%	73%	79%	86%	79%	58%	73%
60.3%	61%	69%	44%	73%	50%	65%
76.3%	88%	82%	86%	76%	55%	71%
82.0%	78%	86%	85%	84%	82%	77%
87.8%	87%	87%	92%	87%	87%	87%
71.7%	89%	83%	84%	79%	10%	85%
76.7%	79%	90%	68%	87%	68%	68%
60.3%	59%	96%	47%	63%	35%	62%
71.0%	72%	71%	89%	73%	66%	55%
73.0%	70%	84%	63%	76%	75%	70%
83.5%	84%	90%	82%	82%	90%	73%
86.3%	96%	81%	65%	96%	89%	91%
58.0%	72%	35%	78%	71%	54%	38%
66.5%	61%	67%	69%	75%	69%	58%
73.0%	77%	63%	70%	79%	75%	74%
72.0%	87%	80%	86%	84%	15%	80%
78.0%	76%	82%	94%	76%	85%	55%
76.7%	85%	66%	70%	87%	67%	85%
66.7%	84%	74%	81%	88%	3%	70%
74.0%	87%	76%	78%	74%	82%	47%
75.0%	78%	80%	66%	94%	66%	66%
75.2%	71%	77%	88%	87%	53%	75%
92.2%	87%	97%	93%	96%	87%	93%
80.7%	74%	83%	87%	81%	82%	77%
70.0%	80%	88%	82%	85%	31%	54%
70.2%	70%	67%	86%	80%	77%	41%
73.8%	79%	73%	72%	77%	75%	67%
71.0%	76%	71%	63%	78%	74%	64%
71.7%	73%	62%	78%	79%	70%	68%
81.0%	88%	87%	71%	84%	77%	79%
79.5%	79%	91%	89%	86%	58%	74%
70.2%	69%	91%	66%	57%	47%	91%
71.5%	73%	71%	71%	75%	69%	70%
80.8%	81%	79%	82%	88%	75%	80%
81.8%	80%	84%	82%	86%	81%	78%
61.3%	83%	78%	68%	62%	22%	55%
85.0%	88%	84%	92%	80%	79%	87%
70.0%	66%	72%	87%	75%	67%	53%
85.3%	85%	85%	83%	92%	81%	86%
36.7%	33%	53%	36%	36%	32%	30%
74.8%	75%	82%	93%	68%	72%	59%
69.0%	66%	84%	69%	78%	57%	60%
66.0%	66%	66%	66%	66%	66%	66%
74.5%	86%	78%	67%	74%	71%	71%
59.8%	83%	61%	66%	67%	43%	39%
69.3%	84%	78%	62%	62%	69%	61%
73.3%	82%	86%	67%	69%	68%	68%
70.5%	87%	29%	87%	69%	86%	65%
65.8%	71%	71%	81%	83%	43%	46%
73.3%	69%	75%	85%	85%	58%	68%
51.5%	61%	67%	18%	53%	59%	51%
70.7%	76%	86%	81%	73%	37%	71%
66.2%	88%	76%	63%	93%	45%	32%
80.5%	94%	87%	79%	76%	73%	74%
65.8%	66%	89%	33%	48%	89%	70%
78.3%	71%	73%	78%	87%	83%	78%
74.2%	71%	75%	80%	80%	61%	78%
63.5%	69%	70%	43%	69%	45%	85%
75.2%	86%	86%	64%	78%	54%	83%
77.7%	82%	84%	70%	84%	77%	69%
80.8%	81%	75%	84%	79%	83%	83%
71.8%	82%	62%	70%	87%	70%	60%
73.3%	87%	40%	65%	85%	75%	88%
71.7%	80%	91%	66%	65%	66%	62%
81.3%	93%	90%	79%	80%	70%	76%
71.5%	93%	76%	54%	80%	72%	54%
81.8%	83%	96%	87%	77%	80%	68%
77.7%	89%	81%	53%	86%	87%	70%
74.3%	79%	75%	74%	73%	69%	76%
75.3%	78%	75%	73%	76%	74%	76%
66.2%	69%	74%	59%	61%	66%	68%
81.3%	87%	81%	75%	84%	82%	79%
79.2%	82%	81%	83%	84%	79%	66%
70.8%	78%	49%	79%	69%	83%	67%
72.3%	86%	64%	75%	91%	64%	54%
66.7%	76%	84%	82%	81%	28%	49%
80.0%	87%	90%	79%	84%	70%	70%
87.2%	84%	84%	88%	91%	88%	88%
56.7%	72%	46%	63%	67%	56%	36%
81.2%	91%	63%	87%	75%	81%	90%
47.3%	37%	56%	51%	40%	50%	50%