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: Gd4 C5 Dtef Global Dialogues Gd4 AiConcern%3Amore Excited Than Concerned C5 - Run 2a8fc1d...

Global Dialogues GD4 - More excited than concerned (5 context Qs)

DTEF: Predict response distributions for More excited than concerned. Source: Global Dialogues GD4 (https://github.com/collect-intel/global-dialogues)

TAGS:

Instruction Following & Prompt Adherence

Reasoning

General Knowledge

Mathematics & Statistics

Social interaction

AI Safety & Robustness

Economic Disruption & Reskilling Advice

Mental Health & Crisis Support

Best Models (Coverage)

1.Claude Haiku 4.5
81.1%
2.GPT 4.1 Mini
79.3%
3.Gemma 3 12b It
79.2%
4.Gemini 2.5 Flash
70.2%
5.GPT 4o Mini
69.2%

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 81.1%	4th 70.2%	3rd 79.2%	2nd 79.3%	6th 60.9%	5th 69.2%
70.5%	83%	80%	48%	86%	44%	82%
73.0%	61%	73%	63%	81%	87%	73%
74.3%	71%	69%	85%	75%	68%	78%
73.3%	82%	64%	77%	82%	78%	57%
55.2%	67%	68%	61%	59%	29%	47%
77.7%	96%	48%	91%	92%	68%	71%
71.2%	85%	81%	64%	71%	71%	55%
85.8%	80%	81%	95%	84%	97%	78%
77.8%	82%	75%	76%	85%	83%	66%
61.7%	60%	24%	77%	64%	73%	72%
80.3%	94%	71%	94%	94%	51%	78%
67.7%	94%	77%	84%	79%	16%	56%
83.5%	90%	86%	87%	90%	58%	90%
86.0%	95%	86%	88%	79%	89%	79%
52.2%	58%	28%	57%	69%	36%	65%
82.3%	84%	82%	86%	85%	78%	79%
86.8%	91%	82%	78%	91%	88%	91%
62.2%	88%	63%	75%	76%	32%	39%
72.3%	78%	82%	90%	81%	22%	81%
68.5%	66%	80%	75%	72%	55%	63%
51.2%	74%	45%	59%	73%	20%	36%
79.7%	82%	81%	85%	85%	65%	80%
81.2%	95%	69%	84%	81%	87%	71%
55.2%	72%	62%	65%	44%	55%	33%
74.5%	80%	86%	88%	60%	85%	48%
86.0%	91%	79%	90%	88%	87%	81%
74.3%	93%	84%	88%	90%	23%	68%
74.5%	93%	51%	80%	86%	70%	67%
71.8%	86%	72%	84%	82%	27%	80%
68.5%	83%	54%	78%	85%	54%	57%
77.5%	92%	85%	91%	81%	48%	68%
81.7%	93%	84%	79%	92%	73%	69%
84.8%	97%	66%	89%	94%	81%	82%
61.2%	52%	78%	83%	47%	72%	35%
80.3%	86%	90%	83%	82%	76%	65%
73.5%	93%	63%	88%	77%	54%	66%
66.5%	82%	61%	80%	91%	32%	53%
84.2%	82%	83%	84%	86%	86%	84%
69.3%	91%	65%	91%	85%	28%	56%
75.5%	67%	88%	77%	80%	63%	78%
83.7%	92%	82%	95%	92%	82%	59%
78.3%	89%	79%	64%	88%	56%	94%
88.3%	90%	89%	83%	87%	95%	86%
56.5%	56%	61%	73%	55%	42%	52%
66.5%	84%	62%	81%	70%	46%	56%
72.2%	91%	83%	74%	81%	52%	52%
71.8%	78%	68%	70%	76%	84%	55%
79.8%	87%	85%	74%	99%	62%	72%
81.8%	94%	81%	81%	83%	69%	83%
70.8%	80%	87%	89%	71%	11%	87%
75.2%	85%	83%	93%	85%	22%	83%
58.7%	69%	26%	71%	63%	54%	69%
74.8%	81%	66%	82%	81%	77%	62%
60.0%	49%	83%	75%	38%	77%	38%
75.2%	90%	86%	91%	72%	54%	58%
71.8%	90%	59%	81%	92%	35%	74%
52.2%	43%	79%	43%	52%	50%	46%
84.2%	92%	86%	87%	90%	64%	86%
66.5%	61%	92%	73%	58%	73%	42%
61.7%	75%	55%	70%	61%	56%	53%
78.8%	84%	46%	86%	88%	89%	80%
61.7%	83%	49%	54%	74%	35%	75%
84.2%	83%	81%	83%	85%	88%	85%
72.0%	87%	65%	90%	88%	37%	65%
76.3%	83%	87%	85%	89%	47%	67%
83.2%	91%	72%	87%	94%	64%	91%
75.7%	94%	57%	85%	91%	40%	87%
71.7%	85%	59%	76%	84%	57%	69%
80.2%	88%	77%	72%	79%	82%	83%
85.8%	88%	85%	90%	88%	74%	90%
58.5%	69%	39%	64%	65%	65%	49%
73.2%	72%	66%	83%	80%	70%	68%
81.2%	80%	49%	96%	82%	96%	84%
66.5%	68%	85%	79%	61%	50%	56%
68.5%	72%	62%	76%	86%	59%	56%
72.7%	65%	40%	86%	76%	87%	82%
66.0%	79%	64%	78%	64%	47%	64%
63.8%	89%	57%	82%	81%	17%	57%
85.7%	94%	77%	94%	85%	84%	80%
74.2%	84%	85%	86%	75%	59%	56%
87.0%	91%	91%	86%	93%	76%	85%
78.8%	87%	81%	80%	97%	50%	78%
66.3%	79%	42%	82%	72%	47%	76%
80.7%	82%	89%	79%	85%	70%	79%
73.8%	92%	76%	85%	85%	43%	62%
76.5%	86%	67%	87%	86%	69%	64%
50.7%	70%	43%	75%	58%	20%	38%
52.5%	74%	43%	69%	65%	14%	50%
52.3%	60%	86%	67%	63%	9%	29%
81.5%	87%	88%	76%	90%	69%	79%
82.0%	82%	72%	88%	92%	80%	78%
53.5%	67%	31%	48%	85%	49%	41%
83.3%	87%	73%	87%	68%	88%	97%
76.0%	87%	74%	83%	82%	57%	73%
55.5%	63%	50%	69%	54%	53%	44%
81.8%	92%	74%	83%	81%	89%	72%
60.5%	73%	55%	70%	80%	15%	70%
74.2%	77%	38%	85%	81%	76%	88%
78.8%	84%	90%	70%	88%	49%	92%
55.8%	74%	47%	60%	67%	42%	45%
64.5%	63%	20%	73%	70%	71%	90%
72.2%	93%	64%	78%	91%	50%	57%
88.0%	90%	89%	84%	88%	92%	85%
76.0%	83%	85%	59%	85%	67%	77%
77.3%	82%	63%	92%	85%	58%	84%
78.2%	70%	93%	64%	86%	63%	93%
85.8%	91%	92%	79%	82%	76%	95%
76.7%	67%	73%	63%	89%	92%	76%
80.2%	66%	85%	86%	86%	73%	85%
89.8%	89%	86%	94%	89%	93%	88%
74.0%	93%	60%	74%	73%	78%	66%
80.5%	88%	75%	86%	77%	79%	78%
85.3%	82%	89%	85%	89%	82%	85%
75.8%	88%	69%	88%	86%	66%	58%
88.7%	87%	95%	95%	93%	76%	86%
66.7%	79%	59%	77%	66%	65%	54%