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 Concerned Than Excited C5 - Run 1b4d3c5...

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

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

TAGS:

Instruction Following & Prompt Adherence

Factual Accuracy & Hallucination

Reasoning

Social interaction

AI Safety & Robustness

Best Models (Coverage)

1.Claude Haiku 4.5
80.0%
2.GPT 4.1 Mini
76.6%
3.Gemini 2.5 Flash
75.4%
4.GPT 4o Mini
70.0%
5.GPT 4.1 Nano
58.4%

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 80.0%	3rd 75.4%	- -	2nd 76.6%	5th 58.4%	4th 70.0%
51.2%	66%	52%		57%	30%	51%
80.0%	66%	85%		84%	76%	89%
74.0%	85%	73%		78%	78%	56%
73.8%	81%	77%		70%	70%	71%
79.8%	86%	83%		91%	59%	80%
64.8%	82%	74%		76%	39%	53%
71.6%	89%	77%		66%	61%	65%
78.4%	91%	84%		78%	72%	67%
61.6%	70%	47%		67%	87%	37%
72.8%	82%	72%		85%	83%	42%
74.0%	74%	79%		78%	64%	75%
77.2%	91%	96%		88%	17%	94%
72.0%	90%	76%		75%	36%	83%
44.8%	72%	49%		41%	24%	38%
48.0%	56%	33%		60%	39%	52%
79.2%	92%	74%		82%	62%	86%
86.2%	87%	89%		82%	86%	87%
68.2%	87%	79%		87%	12%	76%
81.8%	87%	88%		83%	67%	84%
63.4%	58%	76%		59%	62%	62%
68.0%	82%	80%		82%	15%	81%
83.2%	93%	80%		83%	76%	84%
64.0%	76%	62%		74%	52%	56%
61.0%	71%	74%		63%	38%	59%
57.4%	80%	49%		69%	64%	25%
82.4%	81%	78%		83%	86%	84%
72.8%	86%	90%		91%	13%	84%
67.2%	86%	72%		70%	33%	75%
73.4%	82%	79%		71%	75%	60%
69.6%	88%	72%		74%	42%	72%
73.2%	80%	76%		83%	67%	60%
80.4%	86%	87%		87%	61%	81%
65.4%	73%	64%		64%	91%	35%
70.8%	75%	76%		76%	53%	74%
76.6%	81%	77%		81%	67%	77%
74.0%	87%	68%		85%	67%	63%
75.2%	87%	70%		79%	63%	77%
78.4%	74%	84%		84%	74%	76%
73.6%	81%	75%		84%	65%	63%
66.2%	63%	63%		76%	45%	84%
76.4%	94%	66%		77%	67%	78%
70.0%	86%	67%		73%	65%	59%
64.8%	68%	66%		57%	85%	48%
79.2%	73%	79%		83%	70%	91%
73.6%	90%	77%		90%	28%	83%
77.0%	75%	75%		83%	79%	73%
85.8%	80%	86%		90%	87%	86%
92.0%	98%	96%		90%	88%	88%
83.8%	92%	89%		81%	76%	81%
70.0%	90%	84%		74%	28%	74%
66.0%	83%	78%		80%	18%	71%
52.2%	54%	76%		35%	64%	32%
50.6%	80%	64%		46%	34%	29%
73.0%	69%	82%		69%	71%	74%
78.2%	82%	85%		89%	54%	81%
64.8%	86%	90%		66%	28%	54%
61.2%	39%	73%		51%	54%	89%
72.2%	83%	81%		79%	35%	83%
75.8%	80%	72%		80%	62%	85%
77.2%	83%	92%		94%	27%	90%
65.8%	84%	55%		80%	82%	28%
69.8%	84%	72%		67%	58%	68%
83.2%	87%	89%		89%	90%	61%
71.8%	71%	81%		77%	56%	74%
71.2%	78%	76%		79%	69%	54%
62.6%	69%	71%		52%	78%	43%
55.4%	72%	80%		48%	37%	40%
64.8%	82%	70%		72%	40%	60%
72.2%	74%	71%		75%	69%	72%
80.2%	95%	76%		95%	56%	79%
78.0%	84%	91%		87%	62%	66%
62.4%	70%	62%		62%	82%	36%
83.0%	90%	91%		67%	94%	73%
50.8%	51%	60%		54%	29%	60%
78.0%	79%	87%		88%	58%	78%
80.2%	83%	59%		88%	84%	87%
70.6%	89%	72%		80%	32%	80%
68.4%	94%	73%		71%	38%	66%
74.8%	76%	84%		77%	71%	66%
79.6%	83%	81%		88%	58%	88%
82.0%	83%	93%		81%	79%	74%
83.6%	87%	89%		85%	67%	90%
74.8%	85%	82%		72%	78%	57%
83.0%	87%	85%		79%	80%	84%
69.4%	67%	68%		86%	56%	70%
75.4%	82%	79%		79%	64%	73%
77.6%	83%	79%		81%	66%	79%
82.6%	81%	87%		89%	64%	92%
83.8%	89%	88%		81%	87%	74%
83.8%	94%	86%		93%	65%	81%
59.0%	66%	63%		57%	56%	53%
80.2%	78%	87%		78%	80%	78%
75.4%	88%	55%		77%	72%	85%
70.4%	80%	80%		83%	23%	86%
64.6%	74%	82%		81%	16%	70%
69.2%	76%	69%		87%	36%	78%
69.4%	93%	84%		74%	27%	69%
80.0%	89%	56%		85%	81%	89%
76.8%	78%	66%		84%	69%	87%
70.2%	81%	84%		81%	20%	85%
57.0%	64%	51%		63%	56%	51%
63.8%	89%	62%		79%	15%	74%
86.6%	89%	86%		80%	89%	89%
73.0%	71%	81%		75%	71%	67%
65.6%	73%	79%		75%	18%	83%
67.8%	89%	36%		77%	68%	69%
51.4%	81%	39%		57%	55%	25%
72.4%	60%	87%		73%	65%	77%
73.0%	73%	73%		77%	60%	82%
66.2%	72%	63%		68%	81%	47%
77.0%	86%	71%		85%	67%	76%
88.0%	91%	95%		96%	91%	67%
76.8%	69%	82%		78%	86%	69%
76.4%	83%	81%		81%	64%	73%
77.4%	78%	94%		83%	45%	87%
73.6%	84%	92%		93%	20%	79%