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: Gd3 C10 Dtef Global Dialogues Gd3 AiConcern%3Amore Concerned Than Excited C10 - Run 069dcda...

Global Dialogues GD3 - More concerned than excited (10 context Qs)

DTEF: Predict response distributions for More concerned than excited. Source: Global Dialogues GD3 (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	1st 82.3%	2nd 79.4%	- -	3rd 73.6%	5th 58.2%	4th 70.9%
69.8%	92%	83%		70%	38%	66%
67.8%	81%	79%		71%	31%	77%
55.0%	55%	59%		51%	30%	80%
87.4%	75%	92%		87%	94%	89%
84.0%	94%	87%		80%	77%	82%
85.2%	94%	95%		71%	76%	90%
81.4%	84%	81%		78%	74%	90%
64.6%	86%	71%		66%	40%	60%
76.0%	84%	91%		78%	60%	67%
92.4%	94%	94%		86%	94%	94%
77.8%	90%	78%		74%	86%	61%
90.6%	93%	95%		89%	95%	81%
82.2%	73%	86%		81%	85%	86%
83.0%	92%	91%		90%	56%	86%
75.0%	91%	86%		76%	47%	75%
75.0%	86%	80%		65%	82%	62%
42.8%	75%	38%		40%	24%	37%
64.2%	76%	80%		50%	70%	45%
64.0%	60%	79%		65%	44%	72%
79.6%	85%	85%		83%	72%	73%
68.6%	81%	85%		84%	16%	77%
82.6%	89%	94%		82%	61%	87%
80.8%	82%	84%		84%	78%	76%
79.4%	84%	82%		83%	62%	86%
80.4%	90%	82%		89%	55%	86%
80.2%	81%	80%		79%	82%	79%
64.0%	84%	73%		65%	37%	61%
66.6%	88%	86%		56%	60%	43%
73.6%	82%	74%		76%	66%	70%
59.6%	79%	79%		46%	53%	41%
66.6%	76%	82%		80%	21%	74%
75.0%	100%	94%		74%	68%	39%
51.6%	49%	55%		49%	21%	84%
75.0%	74%	91%		70%	72%	68%
80.6%	86%	72%		79%	81%	85%
65.6%	87%	61%		78%	34%	68%
68.6%	88%	85%		76%	25%	69%
77.8%	79%	90%		97%	48%	75%
63.4%	80%	89%		62%	31%	55%
76.8%	88%	95%		95%	57%	49%
60.8%	92%	37%		62%	59%	54%
56.8%	49%	56%		59%	53%	67%
81.6%	89%	59%		89%	89%	82%