AmmarAbouZor/tui-journal

Your journal app if you live in a terminal

1,402

Generated Behavioral Tests

95.3%

Best Score

Claude Opus 5.5 (xhigh)

Results by Model

Hover for details · Click a model to open it · Drag to zoom the x-axis · Shift-drag to pan · The line marks the Pareto frontier (best score per cost)

30 runs

#	Model	Score	Cost	Calls
1	Claude Opus 5.5 (xhigh)	95.3%	$52.02	471	trace →
2	Muse Wonder (xhigh)	94.7%	$55.88	457	trace →
3	Muse Wonder Full	93.1%	TBA	715	trace →
4	Muse Spark 1.3 (xhigh)	82.0%	$1.14	212	trace →
5	Claude Fable 5.1 (xhigh)	80.1%	$146.11	553	trace →
6	GPT 6 Astra (max)	75.7%	$12.87	71	trace →
7	Muse Spark 1.3 (max)	72.4%	$7.14	433	trace →
8	Claude Opus 4.8 (xhigh)	72.3%	$12.96	132	trace →
9	Claude Opus 4.7 (xhigh)	71.0%	$4.95	115	trace →
10	Claude Opus 4.7	70.8%	$4.42	107	trace →
11	GPT 5.5	70.0%	$1.26	21	trace →
12	GLM-5.2	67.0%	$28.73	322	trace →
13	GPT-5.6 Sol	62.7%	$0.87	19	trace →
14	Gemini 3.7 Flash	61.8%	$2.10	138	trace →
15	Muse Spark 1.2 (xhigh)	60.0%	$0.14	88	trace →
16	GPT 5.5 (high)	59.7%	$4.48	45	trace →
17	GPT 5.5 (xhigh)	58.8%	$6.96	63	trace →
18	GPT 5.4	58.4%	$0.29	10	trace →
19	Gemini 3.6 Flash	53.4%	$4.03	118	trace →
20	Gemini 3.5 Flash	50.8%	$4.42	161	trace →
21	Claude Haiku 4.5	44.2%	$0.65	116	trace →
22	Gemini 3.1 Pro	41.7%	$0.48	42	trace →
23	GPT 5 mini	34.5%	$0.03	20	trace →
24	GPT 5.4 mini	34.2%	$0.04	9	trace →
25	GPT-5.6 Sol (xhigh)	8.8%	$6.31	40	trace →
26	Muse Spark 1.1 (xhigh)	8.6%	$0.12	92	trace →
27	Claude Sonnet 4.6	8.6%	$35.70	579	trace →
28	Gemini 3 Flash	0.5%	$0.26	74	trace →
29	Claude Opus 5 (xhigh)	0.0%	$22.81	231	trace →
30	Claude Opus 4.6	0.0%	$3.27	239	trace →

Click a row to replay how that model rebuilt this program, or the model name to open its full run