NikolaDucak/caps-log | ProgramBench

A small TUI journaling tool. 📖

551

Generated Behavioral Tests

96.2%

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)	96.2%	$63.89	416	trace →
2	Muse Wonder Full	94.0%	TBA	554	trace →
3	GPT 6 Astra (max)	94.0%	$8.61	47	trace →
4	Muse Wonder (xhigh)	92.2%	$41.95	429	trace →
5	Claude Fable 5.1 (xhigh)	89.5%	$84.58	415	trace →
6	Muse Spark 1.3 (max)	86.2%	$8.33	384	trace →
7	Claude Opus 5 (xhigh)	79.7%	$58.77	281	trace →
8	GPT-5.6 Sol (xhigh)	79.7%	$7.42	56	trace →
9	Muse Spark 1.3 (xhigh)	78.6%	$1.40	213	trace →
10	GPT 5.5 (xhigh)	75.0%	$8.89	102	trace →
11	GLM-5.2	67.3%	$13.14	132	trace →
12	Gemini 3.7 Flash	66.4%	$1.28	115	trace →
13	GPT-5.6 Sol	65.2%	$1.13	18	trace →
14	GPT 5.5 (high)	65.0%	$5.81	53	trace →
15	Gemini 3.6 Flash	64.4%	$3.92	139	trace →
16	Claude Opus 4.8 (xhigh)	62.4%	$12.66	112	trace →
17	Gemini 3.1 Pro	61.5%	$1.70	90	trace →
18	Gemini 3.5 Flash	60.3%	$16.34	251	trace →
19	Muse Spark 1.1 (xhigh)	59.9%	$0.28	94	trace →
20	Claude Opus 4.6	56.1%	$11.12	283	trace →
21	GPT 5.5	54.8%	$0.96	17	trace →
22	Muse Spark 1.2 (xhigh)	46.3%	$1.11	157	trace →
23	Claude Opus 4.7	42.5%	$2.40	70	trace →
24	GPT 5.4	37.7%	$0.29	16	trace →
25	Claude Haiku 4.5	34.8%	$0.49	97	trace →
26	Gemini 3 Flash	18.9%	$0.36	88	trace →
27	GPT 5.4 mini	18.9%	$0.02	7	trace →
28	GPT 5 mini	18.9%	$0.01	13	trace →
29	Claude Opus 4.7 (xhigh)	10.0%	$4.96	84	trace →
30	Claude Sonnet 4.6	10.0%	$23.74	425	trace →

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