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

AI Safety & Robustness

Best Models (Coverage)

1.Claude Haiku 4.5
81.9%
2.GPT 4.1 Mini
80.8%
3.Gemini 2.5 Flash
76.6%
4.Gemma 3 12b It
76.0%
5.GPT 4.1 Nano
68.4%

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 81.9%	3rd 76.6%	4th 76.0%	2nd 80.8%	5th 68.4%	6th 65.2%
71.8%	74%	88%	56%	69%	65%	79%
63.8%	63%	67%	52%	67%	65%	69%
78.8%	79%	72%	86%	85%	77%	74%
74.7%	90%	71%	71%	86%	80%	50%
55.8%	65%	61%	46%	57%	65%	41%
81.3%	91%	67%	94%	88%	86%	62%
69.2%	90%	69%	60%	66%	69%	61%
78.3%	87%	74%	83%	84%	83%	59%
83.7%	89%	85%	85%	95%	85%	63%
86.2%	89%	97%	87%	67%	93%	84%
79.7%	90%	88%	81%	81%	88%	50%
67.2%	95%	76%	82%	84%	13%	53%
84.8%	90%	87%	82%	87%	81%	82%
69.8%	89%	61%	91%	69%	36%	73%
64.0%	64%	47%	53%	66%	75%	79%
78.2%	80%	91%	76%	86%	71%	65%
87.7%	86%	91%	85%	89%	84%	91%
62.7%	89%	80%	67%	75%	25%	40%
79.3%	83%	82%	88%	82%	66%	75%
48.2%	43%	59%	55%	44%	44%	44%
57.2%	77%	77%	54%	71%	29%	35%
86.2%	92%	81%	91%	91%	72%	90%
79.3%	90%	63%	92%	87%	87%	57%
52.0%	65%	54%	58%	46%	54%	35%
77.8%	81%	83%	79%	86%	84%	54%
91.3%	94%	90%	94%	85%	94%	91%
74.8%	87%	89%	71%	88%	84%	30%
77.3%	89%	83%	90%	90%	51%	61%
81.3%	86%	84%	83%	87%	65%	83%
75.5%	85%	78%	71%	86%	78%	55%
77.5%	92%	56%	89%	92%	88%	48%
73.5%	81%	83%	58%	87%	84%	48%
86.3%	85%	96%	89%	88%	78%	82%
65.2%	68%	78%	67%	70%	60%	48%
79.2%	85%	85%	77%	75%	82%	71%
81.5%	90%	88%	88%	85%	86%	52%
78.5%	91%	90%	67%	94%	81%	48%
85.5%	85%	83%	87%	86%	84%	88%
69.7%	91%	58%	88%	82%	51%	48%
79.7%	68%	79%	78%	85%	87%	81%
76.2%	86%	61%	75%	95%	67%	73%
83.2%	93%	69%	88%	84%	72%	93%
77.7%	71%	72%	87%	76%	85%	75%
62.0%	61%	58%	76%	60%	64%	53%
74.8%	85%	88%	75%	78%	68%	55%
75.5%	82%	89%	76%	95%	55%	56%
77.0%	81%	78%	82%	77%	87%	57%
84.2%	95%	95%	81%	98%	81%	55%
86.7%	95%	81%	87%	88%	79%	90%
71.3%	83%	84%	88%	86%	22%	65%
76.2%	88%	91%	92%	90%	21%	75%
56.2%	69%	29%	61%	63%	56%	59%
73.7%	81%	70%	67%	81%	75%	68%
61.0%	66%	70%	59%	60%	61%	50%
76.2%	91%	87%	79%	78%	79%	43%
69.2%	90%	73%	83%	85%	19%	65%
51.8%	47%	66%	45%	49%	54%	50%
74.8%	88%	92%	73%	87%	36%	73%
68.3%	65%	94%	63%	73%	54%	61%
66.8%	81%	65%	69%	73%	61%	52%
88.0%	86%	88%	82%	96%	86%	90%
72.2%	80%	79%	61%	64%	74%	75%
82.8%	87%	82%	94%	77%	72%	85%
76.7%	94%	60%	77%	88%	91%	50%
84.0%	86%	95%	93%	89%	89%	52%
91.5%	95%	94%	88%	90%	91%	91%
75.8%	85%	83%	80%	86%	43%	78%
74.3%	87%	78%	81%	81%	52%	67%
79.3%	83%	78%	83%	77%	74%	81%
91.3%	93%	84%	90%	93%	94%	94%
64.3%	71%	62%	65%	69%	72%	47%
74.7%	87%	42%	79%	92%	85%	63%
86.5%	94%	72%	87%	93%	90%	83%
64.7%	67%	83%	72%	57%	55%	54%
65.8%	79%	54%	61%	81%	80%	40%
76.7%	77%	63%	82%	86%	81%	71%
76.8%	85%	85%	81%	75%	76%	59%
70.7%	87%	73%	76%	86%	51%	51%
75.8%	86%	64%	82%	83%	86%	54%
70.3%	83%	86%	76%	72%	66%	39%
89.0%	95%	92%	79%	95%	80%	93%
73.5%	98%	86%	79%	93%	14%	71%
75.3%	83%	65%	80%	85%	67%	72%
88.5%	94%	94%	89%	98%	72%	84%
81.3%	87%	88%	81%	80%	79%	73%
74.5%	86%	59%	76%	84%	87%	55%
56.0%	65%	67%	67%	69%	29%	39%
67.8%	74%	72%	60%	77%	69%	55%
49.8%	58%	79%	50%	68%	13%	31%
83.3%	83%	88%	77%	96%	82%	74%
84.8%	71%	91%	89%	87%	83%	88%
51.3%	57%	66%	38%	63%	58%	26%
74.5%	83%	52%	84%	80%	64%	84%
69.3%	87%	88%	78%	88%	18%	57%
55.5%	63%	63%	57%	56%	51%	43%
81.0%	87%	86%	70%	82%	89%	72%
75.7%	81%	55%	74%	92%	79%	73%
78.7%	78%	48%	91%	86%	83%	86%
74.7%	73%	86%	58%	87%	63%	81%
61.7%	75%	71%	52%	82%	61%	29%
71.7%	69%	69%	78%	64%	65%	85%
71.2%	93%	73%	72%	95%	37%	57%
90.3%	91%	84%	94%	91%	92%	90%
81.0%	83%	94%	67%	85%	83%	74%
77.5%	96%	85%	88%	90%	24%	82%
73.7%	67%	68%	67%	92%	68%	80%
79.2%	88%	64%	78%	85%	72%	88%
69.3%	65%	97%	47%	74%	57%	76%
73.7%	69%	81%	83%	74%	60%	75%
85.7%	90%	85%	91%	83%	80%	85%
76.8%	90%	83%	64%	78%	87%	59%
86.8%	92%	75%	93%	84%	95%	82%
89.8%	86%	95%	90%	90%	93%	85%
74.7%	91%	60%	75%	84%	90%	48%
91.2%	82%	95%	96%	99%	85%	90%
60.0%	68%	72%	54%	61%	70%	35%