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: Gd5 C10 Dtef Global Dialogues Gd5 Religion%3Ajudaism C10 - Run be9a7a1...

Global Dialogues GD5 - Judaism (10 context Qs)

DTEF: Predict response distributions for Judaism. Source: Global Dialogues GD5 (https://github.com/collect-intel/global-dialogues)

TAGS:

Select Prompt:

Average key point coverage extent for each model across all prompts.

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	2nd 66.2%	5th 59.4%	- -	1st 67.9%	4th 60.2%	3rd 63.2%
63.8%	57%	60%		79%	60%	63%
52.2%	59%	51%		46%	51%	54%
76.0%	73%	75%		90%	59%	83%
100.0%	100%	100%		100%	100%	100%
78.8%	100%	79%		89%	68%	58%
69.0%	70%	70%		69%	68%	68%
74.2%	71%	69%		69%	85%	77%
45.8%	45%	48%		55%	39%	42%
47.6%	54%	61%		65%	28%	30%
67.6%	83%	59%		72%	65%	59%
60.0%	59%	63%		59%	65%	54%
53.4%	74%	16%		76%	33%	68%
72.0%	71%	84%		95%	45%	65%
100.0%	100%	100%		100%	100%	100%
57.4%	55%	45%		66%	63%	58%
68.6%	71%	53%		64%	87%	68%
73.6%	79%	70%		81%	70%	68%
38.8%	48%	35%		37%	26%	48%
61.4%	63%	61%		72%	49%	62%
66.8%	70%	67%		67%	68%	62%
57.6%	79%	39%		70%	30%	70%
56.4%	51%	48%		76%	53%	54%
85.6%	71%	89%		92%	84%	92%
41.6%	40%	47%		37%	42%	42%
77.6%	77%	94%		97%	49%	71%
63.6%	64%	63%		75%	42%	74%
36.2%	44%	27%		30%	30%	50%
43.6%	53%	0%		54%	55%	56%
90.8%	85%	95%		87%	100%	87%
72.8%	78%	80%		74%	66%	66%
59.6%	60%	60%		59%	60%	59%
71.4%	76%	64%		76%	66%	75%
65.6%	70%	42%		67%	74%	75%
80.4%	87%	51%		84%	90%	90%
67.6%	75%	66%		70%	64%	63%
33.6%	35%	27%		29%	40%	37%
69.0%	80%	49%		80%	80%	56%
44.0%	45%	56%		39%	40%	40%
59.8%	62%	49%		67%	63%	58%
80.0%	77%	78%		71%	94%	80%
70.4%	72%	70%		70%	70%	70%
39.8%	29%	51%		44%	36%	39%
57.6%	55%	65%		51%	62%	55%
55.8%	57%	51%		60%	51%	60%
62.2%	62%	62%		66%	64%	57%
46.6%	61%	45%		47%	36%	44%