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 Excited Than Concerned C10 - Run 76e44f9...

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

DTEF: Predict response distributions for More excited than concerned. 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

General Knowledge

Efficiency & Succinctness

Best Models (Coverage)

1.Claude Haiku 4.5
76.3%
2.Gemini 2.5 Flash
75.8%
3.GPT 4.1 Mini
75.2%
4.Gemma 3 12b It
71.1%
5.GPT 4o Mini
70.7%

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 76.3%	2nd 75.8%	4th 71.1%	3rd 75.2%	6th 56.6%	5th 70.7%
77.8%	77%	65%	79%	89%	73%	84%
75.5%	78%	74%	64%	81%	78%	78%
60.7%	66%	54%	81%	78%	16%	69%
73.2%	86%	81%	66%	83%	54%	69%
71.7%	88%	88%	87%	77%	8%	82%
72.7%	74%	78%	73%	70%	77%	64%
72.0%	59%	85%	82%	71%	68%	67%
68.2%	66%	100%	66%	63%	55%	59%
73.3%	66%	87%	65%	78%	81%	63%
71.7%	68%	66%	60%	75%	83%	78%
59.7%	64%	74%	53%	38%	65%	64%
73.8%	79%	97%	90%	67%	47%	63%
79.3%	81%	91%	58%	83%	77%	86%
87.7%	95%	90%	93%	89%	79%	80%
85.2%	83%	84%	87%	88%	88%	81%
82.5%	81%	90%	81%	81%	81%	81%
63.2%	83%	73%	71%	75%	6%	71%
75.5%	77%	67%	77%	79%	77%	76%
55.0%	51%	90%	39%	64%	28%	58%
62.8%	68%	72%	83%	66%	52%	36%
72.2%	76%	84%	59%	80%	66%	68%
83.8%	81%	89%	83%	83%	80%	87%
73.3%	79%	97%	10%	89%	73%	92%
52.8%	0%	49%	75%	79%	43%	71%
66.5%	67%	65%	67%	75%	54%	71%
69.8%	74%	54%	71%	76%	70%	74%
69.5%	84%	81%	81%	78%	13%	80%
72.2%	61%	68%	99%	64%	93%	48%
72.3%	87%	59%	59%	88%	53%	88%
72.5%	83%	83%	91%	89%	6%	83%
72.0%	80%	83%	78%	66%	74%	51%
72.5%	75%	64%	71%	83%	76%	66%
62.2%	68%	57%	84%	77%	3%	84%
85.7%	87%	83%	87%	87%	83%	87%
80.5%	80%	83%	82%	79%	83%	76%
66.2%	79%	80%	66%	76%	36%	60%
58.7%	65%	40%	74%	70%	51%	52%
74.3%	81%	72%	74%	76%	73%	70%
74.5%	79%	86%	65%	84%	49%	84%
60.3%	78%	57%	72%	82%	16%	57%
83.5%	84%	84%	85%	86%	76%	86%
73.5%	85%	90%	84%	89%	8%	85%
77.2%	79%	91%	72%	62%	68%	91%
63.3%	73%	55%	70%	82%	48%	52%
80.5%	84%	84%	78%	84%	69%	84%
75.8%	87%	82%	78%	75%	58%	75%
58.0%	63%	88%	66%	59%	23%	49%
89.0%	90%	91%	91%	83%	83%	96%
62.0%	72%	52%	81%	62%	58%	47%
79.5%	78%	72%	83%	78%	81%	85%
39.7%	33%	60%	35%	38%	34%	38%
62.0%	76%	82%	78%	60%	21%	55%
63.8%	67%	73%	80%	69%	9%	85%
69.0%	69%	69%	69%	69%	69%	69%
80.7%	84%	90%	69%	73%	75%	93%
62.5%	95%	67%	75%	77%	11%	50%
75.2%	93%	86%	56%	70%	84%	62%
70.0%	88%	62%	66%	69%	68%	67%
74.3%	86%	64%	80%	66%	82%	68%
57.7%	70%	41%	82%	66%	42%	45%
62.3%	72%	68%	82%	67%	4%	81%
68.8%	69%	87%	58%	75%	62%	62%
74.0%	76%	88%	83%	74%	47%	76%
72.2%	79%	67%	73%	86%	41%	87%
78.5%	86%	82%	76%	74%	74%	79%
72.8%	69%	87%	55%	69%	87%	70%
73.8%	72%	80%	58%	84%	66%	83%
69.0%	75%	70%	77%	77%	41%	74%
67.2%	79%	71%	42%	75%	54%	82%
73.0%	87%	88%	71%	86%	27%	79%
81.2%	83%	91%	75%	83%	82%	73%
79.8%	82%	71%	82%	83%	80%	81%
65.0%	78%	77%	56%	77%	43%	59%
79.7%	83%	79%	69%	80%	83%	84%
83.2%	85%	93%	90%	81%	70%	80%
83.2%	88%	68%	84%	92%	85%	82%
72.0%	92%	88%	59%	90%	46%	57%
67.3%	71%	89%	69%	62%	50%	63%
61.5%	78%	78%	46%	67%	42%	58%
76.5%	82%	75%	75%	77%	67%	83%
74.8%	87%	91%	66%	65%	67%	73%
67.5%	74%	79%	48%	79%	60%	65%
66.3%	79%	74%	10%	79%	77%	79%
61.3%	77%	84%	65%	64%	20%	58%
77.7%	80%	59%	82%	80%	87%	78%
65.0%	82%	74%	63%	77%	38%	56%
65.5%	79%	77%	70%	76%	34%	57%
79.2%	77%	91%	79%	88%	75%	65%
83.7%	80%	82%	85%	87%	84%	84%
53.8%	75%	51%	80%	50%	29%	38%
75.3%	93%	45%	85%	71%	82%	76%
46.5%	44%	49%	48%	48%	45%	45%