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%3Amore Concerned Than Excited C10 - Run 5c843db...

Global Dialogues GD6UK - More concerned than excited (10 context Qs)

DTEF: Predict response distributions for More concerned than 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

Best Models (Coverage)

1.Claude Haiku 4.5
78.2%
2.Gemini 2.5 Flash
75.2%
3.GPT 4.1 Mini
73.5%
4.Gemma 3 12b It
71.0%
5.GPT 4o Mini
69.7%

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 78.2%	2nd 75.2%	4th 71.0%	3rd 73.5%	6th 53.7%	5th 69.7%
68.5%	80%	49%	86%	66%	67%	63%
75.3%	88%	67%	83%	70%	85%	59%
75.8%	70%	80%	84%	83%	54%	84%
82.2%	85%	83%	80%	85%	77%	83%
68.5%	89%	82%	78%	71%	19%	72%
80.2%	86%	71%	79%	88%	81%	76%
75.7%	54%	89%	64%	85%	73%	89%
62.2%	46%	86%	49%	63%	63%	66%
78.2%	56%	92%	70%	79%	90%	82%
73.7%	75%	76%	73%	80%	75%	63%
44.2%	56%	42%	44%	29%	68%	26%
81.5%	71%	96%	80%	94%	76%	72%
64.8%	65%	87%	40%	66%	60%	71%
89.8%	96%	90%	93%	85%	85%	90%
73.3%	71%	53%	74%	85%	75%	82%
87.3%	90%	90%	92%	81%	81%	90%
69.5%	92%	82%	70%	70%	20%	83%
81.7%	92%	88%	76%	88%	58%	88%
66.8%	56%	80%	31%	71%	71%	92%
68.2%	77%	67%	92%	81%	61%	31%
65.3%	74%	81%	64%	75%	34%	64%
82.5%	88%	73%	86%	81%	91%	76%
79.8%	91%	77%	66%	85%	89%	71%
57.2%	66%	41%	69%	63%	41%	63%
67.2%	75%	57%	80%	55%	86%	50%
78.3%	88%	79%	72%	76%	80%	75%
58.8%	80%	53%	81%	67%	18%	54%
80.3%	75%	85%	88%	69%	82%	83%
61.0%	83%	52%	74%	71%	19%	67%
86.7%	80%	96%	92%	83%	86%	83%
79.5%	86%	62%	88%	96%	71%	74%
81.7%	94%	69%	77%	95%	61%	94%
67.8%	83%	74%	73%	84%	6%	87%
88.8%	92%	93%	72%	90%	93%	93%
69.8%	78%	57%	80%	66%	77%	61%
79.3%	88%	90%	72%	87%	53%	86%
65.2%	79%	70%	65%	70%	45%	62%
60.8%	80%	76%	69%	49%	38%	53%
52.8%	74%	29%	73%	64%	13%	64%
59.5%	77%	70%	74%	64%	8%	64%
84.3%	91%	90%	71%	84%	85%	85%
68.3%	88%	81%	78%	78%	8%	77%
74.3%	71%	91%	78%	59%	56%	91%
58.7%	68%	65%	57%	63%	42%	57%
61.8%	86%	53%	85%	75%	17%	55%
65.2%	80%	57%	63%	71%	45%	75%
67.2%	80%	78%	73%	80%	12%	80%
67.3%	74%	76%	72%	69%	56%	57%
48.3%	68%	66%	65%	45%	5%	41%
85.8%	90%	86%	76%	89%	88%	86%
55.5%	38%	94%	36%	54%	35%	76%
71.7%	79%	76%	79%	79%	46%	71%
78.3%	68%	85%	84%	81%	70%	82%
66.0%	66%	66%	66%	66%	66%	66%
75.0%	85%	75%	71%	70%	67%	82%
72.2%	84%	84%	85%	85%	7%	88%
72.7%	89%	84%	71%	70%	54%	68%
76.3%	87%	91%	68%	76%	67%	69%
80.2%	89%	90%	79%	83%	82%	58%
66.5%	75%	81%	61%	75%	46%	61%
76.3%	76%	79%	87%	87%	49%	80%
45.2%	66%	75%	18%	61%	0%	51%
65.3%	75%	78%	79%	73%	22%	65%
63.8%	89%	91%	70%	67%	15%	51%
81.7%	88%	96%	84%	80%	76%	66%
70.2%	74%	94%	42%	47%	94%	70%
65.8%	79%	28%	84%	75%	59%	70%
62.7%	84%	36%	85%	79%	25%	67%
62.7%	71%	78%	46%	64%	40%	77%
59.2%	83%	79%	65%	61%	24%	43%
72.2%	79%	73%	66%	83%	53%	79%
75.3%	78%	63%	76%	87%	74%	74%
63.3%	88%	68%	57%	72%	23%	72%
66.3%	85%	83%	71%	65%	45%	49%
78.3%	84%	87%	77%	71%	78%	73%
76.3%	85%	93%	73%	75%	66%	66%
75.0%	88%	84%	48%	73%	76%	81%
78.3%	83%	86%	93%	68%	72%	68%
57.8%	84%	72%	46%	65%	15%	65%
73.3%	77%	76%	69%	73%	69%	76%
66.5%	69%	79%	69%	63%	62%	57%
37.7%	62%	48%	38%	40%	2%	36%
67.8%	82%	79%	77%	83%	76%	10%
69.7%	80%	75%	77%	78%	45%	63%
46.0%	74%	50%	57%	53%	1%	41%
62.8%	84%	70%	60%	72%	19%	72%
76.3%	86%	86%	69%	82%	51%	84%
74.7%	75%	85%	72%	93%	36%	87%
78.5%	88%	64%	82%	86%	70%	81%
81.5%	76%	91%	84%	89%	69%	80%
86.2%	85%	88%	90%	84%	86%	84%
58.7%	36%	78%	47%	55%	68%	68%