rs/jplot | ProgramBench

iTerm2 expvar/JSON monitoring tool

583

Generated Behavioral Tests

99.1%

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	99.1%	TBA	372	trace →
2	Claude Opus 5.5 (xhigh)	98.8%	$30.41	350	trace →
3	GPT 6 Astra (max)	98.6%	$8.80	44	trace →
4	Muse Wonder (xhigh)	98.5%	$24.69	284	trace →
5	Claude Fable 5.1 (xhigh)	96.9%	$46.78	235	trace →
6	Muse Spark 1.3 (max)	96.6%	$2.96	220	trace →
7	Claude Opus 4.8 (xhigh)	94.7%	$25.17	129	trace →
8	GPT 5.5 (high)	91.3%	$3.76	43	trace →
9	Claude Opus 4.6	89.0%	$8.17	139	trace →
10	GPT 5.5 (xhigh)	86.6%	$3.95	38	trace →
11	GPT-5.6 Sol (xhigh)	85.6%	$2.66	27	trace →
12	Claude Opus 4.7 (xhigh)	83.4%	$4.86	95	trace →
13	Muse Spark 1.1 (xhigh)	83.2%	$0.57	119	trace →
14	Claude Opus 4.7	82.5%	$2.34	85	trace →
15	Muse Spark 1.2 (xhigh)	82.3%	$7.40	288	trace →
16	GLM-5.2	78.4%	$18.98	177	trace →
17	Gemini 3.7 Flash	77.4%	$1.56	135	trace →
18	GPT 5.5	69.0%	$1.90	28	trace →
19	Gemini 3.6 Flash	64.8%	$6.60	153	trace →
20	Muse Spark 1.3 (xhigh)	57.8%	$1.18	198	trace →
21	Claude Opus 5 (xhigh)	50.8%	$50.73	235	trace →
22	Claude Sonnet 4.6	47.7%	$31.83	344	trace →
23	Gemini 3 Flash	45.1%	$0.15	35	trace →
24	Gemini 3.5 Flash	44.9%	$3.88	80	trace →
25	GPT 5.4	43.2%	$0.12	11	trace →
26	Claude Haiku 4.5	41.9%	$0.18	67	trace →
27	GPT 5.4 mini	35.0%	$0.02	10	trace →
28	GPT 5 mini	16.3%	$0.02	16	trace →
29	Gemini 3.1 Pro	13.7%	$1.63	67	trace →
30	GPT-5.6 Sol	2.6%	$0.41	11	trace →

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