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

Social interaction

AI Safety & Robustness

General Knowledge

Best Models (Coverage)

1.Claude Haiku 4.5
81.5%
2.GPT 4.1 Mini
80.6%
3.Gemini 2.5 Flash
77.9%
4.GPT 4.1 Nano
70.2%
5.GPT 4o Mini
65.0%

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 81.5%	3rd 77.9%	- -	2nd 80.6%	4th 70.2%	5th 65.0%
74.8%	74%	90%		66%	65%	79%
69.4%	64%	67%		73%	77%	66%
80.4%	79%	85%		88%	76%	74%
72.4%	90%	60%		86%	76%	50%
56.0%	66%	65%		51%	54%	44%
78.6%	91%	66%		88%	92%	56%
72.8%	90%	76%		69%	68%	61%
79.8%	87%	77%		87%	85%	63%
80.4%	85%	80%		91%	77%	69%
79.4%	76%	60%		81%	96%	84%
80.2%	90%	88%		85%	88%	50%
71.2%	95%	82%		93%	25%	61%
87.0%	91%	87%		87%	85%	85%
70.0%	89%	74%		66%	45%	76%
68.6%	63%	57%		72%	72%	79%
77.6%	77%	91%		80%	66%	74%
88.4%	86%	93%		87%	80%	96%
61.2%	92%	78%		83%	25%	28%
78.2%	83%	85%		82%	65%	76%
46.2%	43%	59%		44%	44%	41%
57.6%	75%	78%		71%	29%	35%
87.2%	93%	86%		93%	74%	90%
79.6%	90%	91%		84%	76%	57%
50.0%	65%	54%		44%	54%	33%
78.4%	84%	80%		85%	89%	54%
90.4%	94%	85%		85%	94%	94%
80.6%	90%	88%		89%	87%	49%
72.4%	89%	72%		89%	55%	57%
81.6%	86%	85%		87%	65%	85%
73.8%	85%	72%		78%	79%	55%
76.2%	91%	57%		90%	89%	54%
73.2%	81%	85%		75%	70%	55%
84.8%	85%	93%		86%	78%	82%
67.0%	68%	90%		72%	59%	46%
80.4%	85%	86%		85%	87%	59%
74.4%	90%	88%		82%	60%	52%
79.4%	91%	83%		83%	84%	56%
86.2%	84%	89%		86%	84%	88%
69.2%	91%	74%		82%	51%	48%
73.6%	68%	78%		82%	62%	78%
83.8%	82%	91%		97%	76%	73%
83.6%	93%	77%		84%	82%	82%
77.0%	73%	77%		83%	77%	75%
62.8%	61%	54%		60%	86%	53%
78.4%	88%	87%		78%	78%	61%
77.6%	82%	89%		93%	68%	56%
74.0%	81%	74%		77%	81%	57%
85.8%	95%	95%		85%	99%	55%
85.4%	95%	80%		89%	73%	90%
68.8%	83%	87%		87%	22%	65%
78.6%	88%	87%		88%	55%	75%
55.6%	69%	29%		65%	56%	59%
76.8%	85%	76%		81%	82%	60%
61.0%	66%	70%		57%	61%	51%
72.0%	89%	85%		70%	79%	37%
78.8%	90%	69%		91%	83%	61%
54.4%	46%	67%		56%	53%	50%
74.2%	88%	92%		82%	36%	73%
66.6%	65%	93%		73%	49%	53%
66.8%	75%	66%		71%	70%	52%
85.4%	86%	88%		95%	79%	79%
77.2%	80%	81%		72%	77%	76%
83.4%	87%	91%		78%	80%	81%
80.6%	94%	79%		88%	92%	50%
71.6%	92%	61%		83%	70%	52%
86.4%	95%	74%		93%	82%	88%
82.6%	85%	86%		84%	80%	78%
71.6%	87%	74%		85%	52%	60%
79.2%	80%	75%		80%	81%	80%
92.6%	93%	89%		97%	90%	94%
63.0%	71%	65%		64%	70%	45%
77.2%	88%	67%		88%	80%	63%
87.0%	93%	73%		96%	90%	83%
61.6%	59%	83%		56%	55%	55%
64.6%	78%	50%		81%	74%	40%
74.8%	77%	58%		86%	82%	71%
73.8%	85%	76%		69%	73%	66%
78.6%	87%	81%		86%	88%	51%
76.4%	86%	74%		82%	86%	54%
69.2%	83%	87%		66%	75%	35%
92.4%	95%	93%		91%	88%	95%
80.8%	98%	92%		93%	50%	71%
73.4%	83%	62%		80%	71%	71%
85.6%	94%	84%		95%	72%	83%
76.0%	78%	87%		80%	73%	62%
78.2%	86%	84%		87%	86%	48%
54.2%	65%	66%		68%	32%	40%
69.6%	74%	71%		77%	69%	57%
46.6%	55%	72%		68%	12%	26%
84.4%	83%	84%		97%	82%	76%
84.4%	71%	91%		86%	83%	91%
55.2%	57%	63%		71%	58%	27%
75.2%	83%	52%		80%	77%	84%
67.2%	87%	81%		86%	20%	62%
55.6%	64%	65%		49%	57%	43%
79.8%	84%	87%		82%	83%	63%
76.6%	81%	64%		88%	73%	77%
79.6%	78%	60%		86%	88%	86%
80.2%	73%	94%		90%	63%	81%
63.6%	76%	75%		80%	58%	29%
73.4%	68%	68%		73%	73%	85%
69.8%	93%	77%		84%	38%	57%
92.0%	90%	95%		92%	93%	90%
82.6%	83%	93%		90%	71%	76%
73.8%	93%	83%		88%	20%	85%
73.6%	67%	68%		91%	64%	78%
86.2%	91%	91%		86%	72%	91%
66.4%	62%	80%		73%	60%	57%
74.2%	69%	83%		74%	60%	85%
87.2%	90%	88%		88%	84%	86%
80.4%	90%	89%		78%	86%	59%
85.0%	92%	75%		84%	92%	82%
90.2%	85%	95%		92%	93%	86%
75.6%	92%	60%		87%	91%	48%
87.4%	82%	96%		99%	67%	93%
61.0%	70%	72%		58%	70%	35%