kyoh86/richgo | ProgramBench

Enrich `go test` outputs with text decorations.

546

Generated Behavioral Tests

100.0%

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)	100.0%	$13.62	189	trace →
2	GPT 6 Astra (max)	99.8%	$7.76	41	trace →
3	Muse Spark 1.3 (max)	99.6%	$2.43	168	trace →
4	Claude Fable 5.1 (xhigh)	99.3%	$22.90	129	trace →
5	Muse Wonder (xhigh)	95.2%	$18.22	254	trace →
6	Claude Opus 5 (xhigh)	94.7%	$25.73	179	trace →
7	GPT-5.6 Sol (xhigh)	93.6%	$6.98	52	trace →
8	Muse Spark 1.3 (xhigh)	92.1%	$1.17	230	trace →
9	Claude Opus 4.8 (xhigh)	90.3%	$10.40	71	trace →
10	Gemini 3.7 Flash	89.0%	$1.31	117	trace →
11	Muse Spark 1.1 (xhigh)	88.8%	$0.41	180	trace →
12	GPT 5.5 (high)	88.1%	$3.00	54	trace →
13	Claude Opus 4.7 (xhigh)	87.4%	$16.10	232	trace →
14	GPT 5.5	87.2%	$1.25	20	trace →
15	GLM-5.2	86.8%	$8.61	150	trace →
16	Muse Spark 1.2 (xhigh)	86.6%	$0.70	173	trace →
17	Claude Opus 4.6	85.0%	$12.87	312	trace →
18	GPT-5.6 Sol	84.8%	$0.78	16	trace →
19	Claude Opus 4.7	83.7%	$6.01	166	trace →
20	Gemini 3.6 Flash	83.2%	$3.28	129	trace →
21	Gemini 3.5 Flash	78.8%	$4.64	193	trace →
22	Claude Sonnet 4.6	77.7%	$8.23	313	trace →
23	Muse Wonder Full	76.7%	TBA	270	trace →
24	Gemini 3 Flash	59.2%	$0.36	120	trace →
25	Gemini 3.1 Pro	56.6%	$1.48	121	trace →
26	GPT 5.4	54.4%	$0.26	10	trace →
27	GPT 5.5 (xhigh)	51.8%	$4.11	56	trace →
28	Claude Haiku 4.5	48.7%	$1.04	156	trace →
29	GPT 5.4 mini	8.2%	$0.02	8	trace →
30	GPT 5 mini	6.4%	$0.02	14	trace →

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