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%3Aequally Concerned And Excited C5 - Run 24fa9eb...

Global Dialogues GD4 - Equally concerned and excited (5 context Qs)

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

TAGS:

Instruction Following & Prompt Adherence

Reasoning

Mathematics & Statistics

General Knowledge

Social interaction

AI Safety & Robustness

Economic Disruption & Reskilling Advice

Mental Health & Crisis Support

Best Models (Coverage)

1.Claude Haiku 4.5
82.0%
2.GPT 4.1 Mini
80.4%
3.Gemini 2.5 Flash
77.7%
4.Gemma 3 12b It
75.9%
5.GPT 4.1 Nano
67.0%

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 82.0%	3rd 77.7%	4th 75.9%	2nd 80.4%	5th 67.0%	6th 65.2%
71.0%	74%	87%	56%	63%	65%	81%
67.2%	63%	69%	52%	76%	77%	66%
78.5%	68%	85%	84%	88%	76%	70%
75.2%	90%	65%	73%	87%	86%	50%
57.0%	67%	64%	46%	58%	65%	42%
80.7%	91%	69%	94%	84%	90%	56%
70.5%	90%	74%	63%	67%	68%	61%
80.7%	88%	77%	80%	84%	88%	67%
81.2%	89%	80%	77%	95%	77%	69%
84.7%	78%	97%	87%	67%	95%	84%
79.5%	90%	89%	78%	87%	83%	50%
69.7%	95%	77%	82%	79%	26%	59%
82.7%	90%	86%	80%	87%	85%	68%
68.2%	89%	68%	74%	69%	36%	73%
59.3%	62%	46%	58%	72%	39%	79%
75.3%	78%	89%	74%	86%	51%	74%
87.2%	86%	88%	85%	84%	84%	96%
63.3%	92%	77%	68%	84%	25%	34%
72.8%	83%	85%	88%	88%	18%	75%
48.2%	43%	59%	55%	44%	44%	44%
54.0%	77%	78%	54%	71%	15%	29%
84.3%	92%	80%	91%	91%	72%	80%
72.8%	90%	64%	92%	87%	51%	53%
50.3%	65%	54%	58%	44%	50%	31%
77.8%	82%	82%	79%	84%	86%	54%
92.0%	93%	90%	94%	93%	93%	89%
70.8%	90%	88%	81%	89%	28%	49%
78.0%	89%	79%	95%	90%	49%	66%
81.2%	86%	86%	84%	87%	65%	79%
75.2%	85%	74%	71%	86%	80%	55%
77.5%	92%	72%	89%	92%	68%	52%
71.7%	80%	82%	58%	73%	67%	70%
88.0%	85%	95%	89%	88%	89%	82%
67.7%	63%	91%	67%	72%	54%	59%
76.8%	85%	76%	77%	75%	83%	65%
81.5%	90%	88%	87%	88%	87%	49%
76.2%	89%	85%	69%	86%	80%	48%
86.0%	86%	88%	90%	86%	78%	88%
77.2%	91%	61%	88%	89%	86%	48%
74.7%	68%	77%	79%	82%	62%	80%
82.3%	86%	92%	75%	97%	71%	73%
86.2%	93%	78%	90%	88%	82%	86%
78.0%	71%	72%	89%	76%	85%	75%
66.2%	61%	57%	76%	65%	85%	53%
69.3%	88%	87%	76%	74%	28%	63%
76.5%	82%	86%	76%	98%	59%	58%
75.0%	81%	74%	71%	77%	81%	66%
81.7%	95%	99%	81%	85%	75%	55%
85.8%	95%	80%	87%	89%	74%	90%
72.5%	80%	87%	88%	89%	24%	67%
76.2%	89%	94%	91%	88%	21%	74%
55.5%	68%	29%	59%	67%	47%	63%
69.7%	85%	75%	67%	78%	53%	60%
62.3%	68%	70%	59%	56%	67%	54%
73.7%	88%	86%	79%	70%	76%	43%
69.0%	90%	70%	83%	91%	19%	61%
51.8%	46%	66%	45%	50%	54%	50%
75.5%	87%	91%	72%	84%	46%	73%
67.8%	65%	94%	63%	68%	56%	61%
66.5%	77%	67%	69%	70%	64%	52%
86.8%	86%	89%	82%	90%	84%	90%
73.0%	80%	82%	63%	69%	73%	71%
83.2%	87%	86%	94%	88%	72%	72%
76.3%	94%	59%	77%	86%	92%	50%
81.0%	85%	77%	91%	85%	90%	58%
88.7%	95%	89%	88%	91%	81%	88%
81.8%	85%	82%	80%	86%	80%	78%
76.5%	87%	81%	80%	89%	60%	62%
81.0%	83%	78%	89%	76%	80%	80%
91.2%	93%	86%	90%	94%	90%	94%
65.5%	71%	73%	65%	67%	72%	45%
77.0%	87%	65%	82%	85%	80%	63%
87.2%	94%	66%	94%	93%	90%	86%
66.7%	66%	84%	68%	59%	64%	59%
68.2%	77%	79%	62%	79%	76%	36%
77.7%	77%	70%	82%	84%	82%	71%
73.7%	85%	76%	81%	66%	75%	59%
73.7%	87%	80%	76%	86%	62%	51%
75.5%	86%	66%	82%	84%	81%	54%
70.7%	83%	87%	76%	66%	77%	35%
89.0%	95%	92%	79%	95%	80%	93%
80.0%	98%	90%	79%	94%	48%	71%
74.3%	83%	65%	80%	80%	67%	71%
85.8%	94%	73%	89%	98%	71%	90%
81.5%	93%	87%	81%	87%	79%	62%
72.2%	86%	56%	76%	85%	82%	48%
55.7%	65%	67%	67%	67%	27%	41%
68.0%	80%	78%	60%	81%	69%	40%
53.8%	70%	83%	50%	61%	33%	26%
82.0%	93%	88%	77%	86%	72%	76%
86.3%	76%	91%	89%	92%	82%	88%
50.7%	57%	66%	38%	60%	60%	23%
76.2%	88%	52%	87%	74%	64%	92%
69.7%	87%	82%	82%	87%	20%	60%
54.7%	64%	55%	57%	45%	57%	50%
79.3%	84%	86%	68%	82%	84%	72%
76.5%	81%	60%	74%	91%	76%	77%
79.7%	78%	48%	86%	88%	92%	86%
75.8%	73%	92%	55%	90%	64%	81%
61.5%	75%	71%	52%	82%	60%	29%
71.0%	73%	53%	70%	73%	72%	85%
66.5%	93%	73%	70%	95%	35%	33%
91.2%	91%	87%	94%	90%	93%	92%
78.2%	83%	91%	66%	81%	77%	71%
76.8%	89%	88%	90%	92%	19%	83%
70.3%	67%	82%	67%	73%	53%	80%
85.3%	91%	91%	76%	84%	72%	98%
63.5%	65%	81%	47%	67%	56%	65%
74.5%	69%	82%	81%	74%	60%	81%
89.2%	89%	89%	91%	92%	88%	86%
81.2%	90%	89%	64%	82%	90%	72%
85.5%	91%	72%	96%	84%	88%	82%
91.0%	87%	95%	89%	92%	93%	90%
75.8%	91%	67%	74%	85%	90%	48%
88.3%	82%	93%	92%	95%	78%	90%
59.2%	70%	63%	64%	58%	70%	30%