antonmedv/fx | ProgramBench

Terminal JSON viewer & processor

2,044

Generated Behavioral Tests

99.2%

Best Score

Muse Wonder Full

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	Muse Wonder Full	99.2%	TBA	558	trace →
2	GPT 6 Astra (max)	98.0%	$11.26	59	trace →
3	Muse Wonder (xhigh)	98.0%	$74.58	495	trace →
4	Claude Opus 5.5 (xhigh)	97.9%	$73.09	489	trace →
5	Claude Fable 5.1 (xhigh)	97.4%	$52.18	270	trace →
6	Claude Opus 5 (xhigh)	93.8%	$54.53	295	trace →
7	Muse Spark 1.3 (max)	88.5%	$14.05	592	trace →
8	Gemini 3.7 Flash	84.1%	$1.50	137	trace →
9	GPT-5.6 Sol (xhigh)	79.9%	$5.77	36	trace →
10	Claude Opus 4.8 (xhigh)	78.2%	$26.72	182	trace →
11	Claude Opus 4.6	75.7%	$20.74	396	trace →
12	GPT 5.5 (high)	74.5%	$3.29	50	trace →
13	GLM-5.2	72.9%	$19.15	220	trace →
14	Gemini 3.6 Flash	70.6%	$4.66	176	trace →
15	GPT-5.6 Sol	69.4%	$1.61	22	trace →
16	Muse Spark 1.1 (xhigh)	65.9%	$0.25	136	trace →
17	Gemini 3.5 Flash	62.5%	$6.59	271	trace →
18	Muse Spark 1.2 (xhigh)	60.6%	$0.11	110	trace →
19	GPT 5.5	56.6%	$1.21	24	trace →
20	Claude Opus 4.7	49.4%	$5.93	145	trace →
21	GPT 5.4	49.3%	$0.20	10	trace →
22	Claude Opus 4.7 (xhigh)	47.1%	$7.48	135	trace →
23	GPT 5.5 (xhigh)	43.3%	$7.63	71	trace →
24	Gemini 3.1 Pro	42.2%	$1.37	127	trace →
25	GPT 5.4 mini	40.4%	$0.03	7	trace →
26	Claude Haiku 4.5	17.6%	$0.73	133	trace →
27	Muse Spark 1.3 (xhigh)	17.4%	$1.31	210	trace →
28	Gemini 3 Flash	16.1%	$0.19	85	trace →
29	GPT 5 mini	11.6%	$0.01	11	trace →
30	Claude Sonnet 4.6	4.3%	$25.98	621	trace →

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