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

Factual Accuracy & Hallucination

Mathematics & Statistics

Social interaction

General Knowledge

Best Models (Coverage)

1.Claude Haiku 4.5
81.2%
2.GPT 4.1 Mini
79.6%
3.Gemini 2.5 Flash
69.6%
4.GPT 4o Mini
68.2%
5.GPT 4.1 Nano
62.3%

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 81.2%	3rd 69.6%	- -	2nd 79.6%	5th 62.3%	4th 68.2%
70.0%	83%	77%		86%	26%	78%
72.0%	61%	68%		65%	93%	73%
76.0%	77%	81%		75%	73%	74%
66.8%	82%	54%		76%	59%	63%
57.2%	68%	66%		54%	51%	47%
76.4%	92%	79%		90%	53%	68%
69.2%	85%	80%		63%	63%	55%
81.2%	85%	76%		86%	82%	77%
78.8%	82%	76%		91%	82%	63%
59.0%	60%	24%		79%	60%	72%
83.0%	94%	75%		92%	87%	67%
64.8%	87%	73%		66%	32%	66%
87.6%	90%	85%		90%	83%	90%
88.4%	95%	88%		86%	89%	84%
53.4%	58%	25%		70%	39%	75%
77.0%	84%	82%		91%	71%	57%
89.8%	91%	83%		91%	94%	90%
55.0%	88%	40%		86%	22%	39%
68.2%	76%	82%		84%	18%	81%
68.0%	65%	84%		69%	59%	63%
53.8%	74%	40%		73%	34%	48%
82.6%	83%	81%		94%	75%	80%
74.2%	95%	92%		88%	36%	60%
54.2%	72%	66%		44%	56%	33%
70.2%	80%	86%		60%	78%	47%
88.0%	90%	86%		92%	86%	86%
69.4%	93%	73%		90%	23%	68%
78.0%	93%	77%		89%	65%	66%
68.4%	86%	63%		82%	27%	84%
64.4%	83%	50%		80%	54%	55%
69.2%	89%	59%		91%	49%	58%
77.6%	92%	66%		79%	82%	69%
84.6%	98%	66%		93%	78%	88%
57.2%	52%	72%		61%	68%	33%
73.2%	86%	61%		82%	76%	61%
84.4%	85%	91%		89%	90%	67%
72.8%	82%	68%		91%	69%	54%
81.0%	82%	79%		78%	86%	80%
86.0%	91%	95%		92%	92%	60%
73.0%	67%	82%		88%	50%	78%
75.4%	88%	56%		92%	82%	59%
79.6%	89%	75%		88%	74%	72%
89.0%	90%	92%		90%	87%	86%
53.0%	56%	54%		57%	43%	55%
65.6%	84%	61%		70%	54%	59%
77.0%	91%	92%		95%	52%	55%
68.4%	77%	62%		76%	69%	58%
81.6%	87%	98%		99%	62%	62%
80.0%	94%	71%		83%	69%	83%
65.6%	81%	86%		69%	11%	81%
73.2%	84%	84%		92%	22%	84%
55.4%	73%	26%		69%	52%	57%
71.6%	81%	76%		81%	58%	62%
56.0%	50%	64%		38%	91%	37%
75.6%	91%	88%		82%	69%	48%
70.2%	90%	59%		93%	35%	74%
52.0%	44%	74%		53%	43%	46%
85.0%	94%	86%		90%	65%	90%
63.2%	60%	87%		63%	63%	43%
57.8%	75%	53%		61%	56%	44%
74.6%	84%	37%		75%	89%	88%
59.2%	83%	49%		66%	28%	70%
83.0%	83%	82%		90%	80%	80%
74.8%	94%	67%		88%	68%	57%
78.6%	83%	90%		70%	93%	57%
83.2%	92%	69%		94%	71%	90%
81.2%	95%	88%		91%	44%	88%
71.0%	85%	64%		76%	61%	69%
83.8%	88%	80%		81%	87%	83%
90.0%	88%	94%		88%	90%	90%
63.6%	69%	60%		68%	73%	48%
73.6%	76%	68%		79%	75%	70%
75.0%	79%	38%		82%	96%	80%
59.8%	68%	76%		56%	43%	56%
64.6%	79%	59%		87%	49%	49%
72.2%	65%	61%		76%	87%	72%
67.2%	79%	42%		74%	76%	65%
58.0%	89%	40%		83%	17%	61%
78.8%	94%	43%		88%	90%
73.0%	85%	81%		75%	64%	60%
88.8%	91%	94%		93%	88%	78%
73.0%	84%	79%		97%	14%	91%
68.8%	79%	43%		76%	73%	73%
80.4%	82%	88%		83%	70%	79%
66.6%	92%	82%		78%	19%	62%
69.4%	92%	43%		86%	57%	69%
50.0%	70%	65%		58%	20%	37%
54.8%	74%	42%		65%	39%	54%
48.4%	53%	82%		61%	17%	29%
79.2%	90%	83%		85%	68%	70%
84.4%	82%	72%		91%	92%	85%
61.8%	67%	70%		76%	59%	37%
74.0%	88%	38%		65%	88%	91%
70.8%	88%	64%		79%	58%	65%
47.0%	63%	46%		50%	30%	46%
84.0%	92%	85%		89%	82%	72%
59.2%	72%	56%		80%	15%	73%
71.0%	77%	38%		79%	76%	85%
82.6%	84%	64%		93%	80%	92%
54.8%	74%	48%		69%	34%	49%
58.4%	63%	20%		70%	69%	70%
73.6%	95%	64%		93%	57%	59%
90.4%	89%	95%		85%	93%	90%
74.0%	82%	91%		80%	40%	77%
75.0%	82%	63%		85%	60%	85%
79.4%	64%	95%		91%	63%	84%
83.8%	97%	67%		86%	75%	94%
82.2%	71%	79%		82%	91%	88%
80.4%	63%	87%		86%	81%	85%
87.4%	89%	87%		89%	88%	84%
74.0%	93%	62%		72%	77%	66%
80.4%	88%	77%		77%	82%	78%
85.2%	79%	90%		90%	82%	85%
72.0%	88%	67%		88%	46%	71%
83.5%	87%	96%			65%	86%
61.2%	79%	68%		77%	28%	54%