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 Dtef Global Dialogues Gd4 AiConcern%3Amore Excited Than Concerned - Run 1e37fb8...

Global Dialogues GD4 - More excited than concerned

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

Reasoning

General Knowledge

Efficiency & Succinctness

Factual Accuracy & Hallucination

Best Models (Coverage)

1.Claude Haiku 4.5
80.5%
2.GPT 4.1 Mini
79.6%
3.Gemini 2.5 Flash
77.2%
4.GPT 4.1 Nano
75.4%
5.GPT 4o Mini
74.7%

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 80.5%	3rd 77.2%	- -	2nd 79.6%	4th 75.4%	5th 74.7%
78.6%	85%	89%		77%	60%	82%
60.4%	55%	63%		58%	75%	51%
76.0%	77%	68%		82%	74%	79%
74.6%	79%	71%		79%	76%	68%
61.0%	67%	66%		58%	56%	58%
87.6%	92%	75%		94%	91%	86%
67.0%	76%	77%		60%	60%	62%
83.6%	88%	77%		82%	88%	83%
82.8%	81%	79%		85%	88%	81%
69.6%	62%	58%		64%	93%	71%
85.8%	92%	76%		94%	84%	83%
72.2%	92%	76%		81%	56%	56%
87.0%	82%	89%		90%	87%	87%
75.4%	85%	83%		70%	70%	69%
70.4%	68%	61%		82%	66%	75%
78.8%	89%	77%		75%	82%	71%
93.0%	91%	86%		96%	93%	99%
81.4%	90%	56%		90%	90%	81%
75.2%	81%	81%		75%	64%	75%
61.0%	66%	72%		59%	55%	53%
78.0%	86%	54%		79%	94%	77%
85.4%	94%	96%		86%	65%	86%
89.4%	92%	92%		92%	86%	85%
51.4%	59%	55%		44%	57%	42%
77.6%	83%	74%		73%	80%	78%
69.4%	74%	78%		74%	60%	61%
89.6%	96%	81%		90%	94%	87%
82.6%	85%	81%		89%	84%	74%
80.2%	89%	86%		77%	70%	79%
77.2%	87%	71%		85%	71%	72%
85.2%	89%	89%		83%	90%	75%
88.8%	95%	90%		91%	86%	82%
84.6%	82%	90%		83%	79%	89%
58.0%	54%	57%		66%	75%	38%
78.6%	75%	92%		82%	69%	75%
87.8%	93%	90%		90%	85%	81%
73.0%	71%	67%		77%	81%	69%
73.8%	80%	80%		82%	60%	67%
88.2%	91%	91%		87%	89%	83%
66.0%	59%	67%		79%	60%	65%
81.6%	92%	81%		92%	82%	61%
85.0%	90%	90%		96%	59%	90%
89.6%	88%	95%		90%	84%	91%
59.6%	61%	54%		62%	59%	62%
75.6%	80%	73%		80%	77%	68%
71.8%	78%	81%		66%	67%	67%
76.4%	77%	80%		74%	75%	76%
88.2%	84%	96%		84%	98%	79%
86.2%	93%	91%		92%	71%	84%
74.8%	80%	85%		71%	69%	69%
74.4%	84%	82%		66%	65%	75%
67.2%	65%	69%		75%	63%	64%
74.0%	73%	86%		79%	53%	79%
54.6%	51%	59%		43%	78%	42%
84.2%	83%	90%		82%	89%	77%
88.0%	85%	86%		87%	91%	91%
63.2%	64%	59%		66%	69%	58%
88.8%	91%	86%		90%	90%	87%
58.6%	67%	72%		58%	55%	41%
64.4%	71%	57%		61%	67%	66%
86.6%	89%	72%		95%	90%	87%
77.4%	84%	77%		85%	66%	75%
79.0%	97%	79%		71%	72%	76%
82.0%	94%	71%		80%	82%	83%
93.2%	90%	97%		89%	92%	98%
90.8%	93%	92%		86%	89%	94%
90.6%	96%	92%		91%	85%	89%
76.4%	84%	84%		79%	63%	72%
83.8%	85%	89%		81%	87%	77%
91.2%	88%	88%		95%	90%	95%
73.0%	74%	68%		71%	75%	77%
80.8%	88%	67%		85%	85%	79%
81.8%	82%	65%		89%	88%	85%
62.4%	64%	71%		63%	56%	58%
70.8%	81%	55%		74%	79%	65%
70.0%	76%	56%		76%	72%	70%
77.0%	79%	69%		82%	76%	79%
78.0%	87%	64%		84%	77%	78%
84.6%	85%	74%		94%	85%	85%
79.4%	80%	86%		78%	83%	70%
86.2%	91%	78%		97%	88%	77%
78.8%	88%	95%		85%	56%	70%
74.8%	80%	64%		81%	75%	74%
81.4%	82%	97%		84%	65%	79%
80.6%	92%	81%		76%	74%	80%
82.2%	86%	71%		87%	86%	81%
57.6%	56%	53%		61%	59%	59%
70.2%	74%	64%		71%	74%	68%
57.4%	52%	92%		51%	52%	40%
82.4%	81%	79%		91%	84%	77%
85.2%	87%	88%		87%	80%	84%
56.8%	49%	72%		60%	45%	58%
78.4%	81%	80%		80%	71%	80%
81.4%	91%	78%		82%	80%	76%
56.8%	63%	49%		54%	58%	60%
87.4%	88%	88%		92%	84%	85%
72.6%	74%	61%		80%	76%	72%
81.4%	81%	69%		89%	82%	86%
86.2%	88%	86%		94%	83%	80%
64.0%	74%	55%		67%	61%	63%
72.6%	77%	59%		73%	76%	78%
89.8%	91%	88%		89%	90%	91%
64.4%	70%	85%		69%	43%	55%
87.0%	85%	89%		93%	87%	81%
81.2%	88%	86%		87%	65%	80%
86.6%	79%	93%		99%	64%	98%
85.8%	90%	79%		86%	81%	93%
68.4%	53%	71%		69%	76%	73%
84.4%	85%	87%		91%	80%	79%
87.8%	88%	93%		89%	87%	82%
77.4%	70%	88%		73%	76%	80%
91.2%	88%	94%		93%	88%	93%
80.4%	79%	79%		84%	81%	79%
79.0%	93%	68%		87%	71%	76%
81.8%	82%	91%		89%	76%	71%
66.4%	76%	56%		73%	72%	55%