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

Efficiency & Succinctness

Social interaction

AI Safety & Robustness

Psychology

Economics & Finance

Best Models (Coverage)

1.Claude Haiku 4.5
79.3%
2.GPT 4.1 Mini
77.1%
3.Gemini 2.5 Flash
75.3%
4.GPT 4o Mini
70.2%
5.GPT 4.1 Nano
56.8%

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 79.3%	3rd 75.3%	- -	2nd 77.1%	5th 56.8%	4th 70.2%
51.6%	66%	65%		51%	28%	48%
72.6%	66%	73%		77%	58%	89%
78.4%	85%	82%		78%	79%	68%
67.4%	81%	75%		76%	37%	68%
85.8%	86%	94%		90%	78%	81%
65.2%	77%	74%		70%	75%	30%
71.0%	89%	77%		66%	63%	60%
79.4%	90%	78%		85%	77%	67%
62.2%	70%	42%		84%	82%	33%
63.6%	77%	82%		93%	20%	46%
73.8%	74%	79%		77%	63%	76%
75.4%	94%	89%		93%	10%	91%
73.6%	90%	81%		81%	35%	81%
45.6%	72%	51%		45%	24%	36%
49.6%	56%	34%		55%	56%	47%
85.2%	92%	81%		86%	72%	95%
84.6%	87%	87%		77%	85%	87%
68.6%	87%	76%		85%	11%	84%
72.0%	87%	86%		86%	17%	84%
59.4%	49%	76%		59%	59%	54%
67.0%	78%	78%		84%	14%	81%
81.6%	93%	79%		80%	76%	80%
65.8%	76%	63%		78%	59%	53%
62.0%	63%	74%		56%	58%	59%
61.8%	82%	49%		65%	73%	40%
80.6%	81%	78%		83%	86%	75%
73.2%	86%	90%		91%	13%	86%
68.2%	86%	72%		76%	33%	74%
77.4%	85%	84%		71%	83%	64%
72.2%	88%	84%		71%	46%	72%
78.4%	89%	78%		86%	72%	67%
77.4%	84%	75%		86%	61%	81%
64.2%	74%	62%		68%	82%	35%
72.8%	75%	76%		75%	65%	73%
62.0%	80%	10%		78%	65%	77%
75.8%	87%	70%		83%	68%	71%
78.0%	87%	80%		79%	67%	77%
80.4%	74%	87%		83%	80%	78%
75.6%	81%	69%		82%	70%	76%
66.2%	63%	74%		71%	45%	78%
76.6%	94%	69%		75%	67%	78%
70.2%	86%	67%		74%	65%	59%
55.6%	61%	53%		57%	55%	52%
75.6%	73%	66%		67%	81%	91%
73.0%	91%	76%		88%	28%	82%
73.2%	75%	70%		81%	65%	75%
79.8%	81%	63%		88%	88%	79%
91.2%	98%	93%		90%	87%	88%
82.0%	93%	83%		81%	78%	75%
67.6%	90%	82%		74%	18%	74%
67.4%	83%	67%		70%	45%	72%
47.0%	54%	81%		40%	32%	28%
50.6%	80%	64%		46%	34%	29%
75.0%	66%	86%		73%	76%	74%
79.4%	84%	77%		89%	64%	83%
60.8%	73%	89%		60%	28%	54%
59.8%	39%	63%		54%	54%	89%
72.4%	83%	82%		83%	35%	79%
77.0%	80%	86%		82%	55%	82%
76.6%	83%	94%		94%	27%	85%
60.2%	76%	32%		80%	85%	28%
73.0%	84%	77%		72%	62%	70%
83.0%	87%	89%		93%	90%	56%
72.0%	71%	74%		76%	63%	76%
70.0%	78%	76%		81%	68%	47%
68.4%	69%	92%		61%	63%	57%
57.8%	71%	83%		50%	37%	48%
62.6%	79%	67%		76%	36%	55%
71.0%	73%	69%		72%	70%	71%
80.6%	95%	88%		92%	59%	69%
79.2%	84%	95%		91%	47%	79%
62.6%	62%	66%		68%	78%	39%
85.4%	90%	84%		79%	92%	82%
53.6%	47%	61%		52%	48%	60%
80.0%	79%	86%		90%	58%	87%
84.4%	83%	84%		92%	76%	87%
72.2%	89%	72%		80%	35%	85%
67.8%	94%	73%		69%	49%	54%
75.6%	76%	82%		77%	70%	73%
79.2%	83%	80%		88%	58%	87%
80.2%	90%	92%		74%	61%	84%
84.6%	88%	88%		92%	67%	88%
72.6%	85%	86%		62%	78%	52%
82.4%	88%	83%		86%	81%	74%
69.8%	73%	69%		86%	56%	65%
76.8%	77%	81%		82%	65%	79%
78.4%	83%	79%		81%	70%	79%
73.6%	81%	89%		89%	20%	89%
88.0%	90%	96%		81%	87%	86%
83.0%	94%	93%		97%	45%	86%
58.4%	66%	53%		60%	60%	53%
72.8%	79%	86%		85%	36%	78%
69.8%	83%	46%		64%	70%	86%
79.4%	80%	89%		83%	61%	84%
66.0%	75%	80%		78%	23%	74%
63.0%	76%	70%		86%	11%	72%
74.2%	91%	85%		86%	27%	82%
79.6%	83%	56%		87%	83%	89%
79.4%	78%	80%		84%	68%	87%
67.6%	80%	82%		82%	14%	80%
56.6%	62%	46%		65%	58%	52%
63.8%	88%	63%		79%	15%	74%
86.8%	84%	86%		88%	89%	87%
73.0%	71%	73%		78%	76%	67%
67.4%	73%	79%		80%	26%	79%
74.2%	92%	72%		75%	68%	64%
54.4%	81%	38%		57%	73%	23%
72.4%	60%	87%		75%	56%	84%
73.2%	72%	76%		76%	60%	82%
65.0%	72%	57%		68%	81%	47%
78.4%	88%	70%		82%	76%	76%
86.2%	91%	92%		91%	90%	67%
76.4%	69%	88%		77%	85%	63%
67.2%	78%	81%		82%	22%	73%
76.6%	69%	98%		84%	45%	87%
75.8%	85%	92%		92%	20%	90%