eliukblau/pixterm | ProgramBench

Draw images in your ANSI terminal with true color

430

Generated Behavioral Tests

100.0%

Best Score

GPT 6 Astra (max)

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)

29 runs

#	Model	Score	Cost	Calls
1	GPT 6 Astra (max)	100.0%	$8.80	46	trace →
2	Claude Opus 5 (xhigh)	98.8%	$25.36	147	trace →
3	Muse Wonder Full	98.6%	TBA	362	trace →
4	Claude Fable 5.1 (xhigh)	98.1%	$25.39	143	trace →
5	Muse Wonder (xhigh)	94.0%	$37.81	323	trace →
6	GPT-5.6 Sol (xhigh)	90.2%	$10.17	66	trace →
7	GPT 5.5 (xhigh)	85.8%	$7.86	63	trace →
8	Gemini 3.5 Flash	80.0%	$5.41	114	trace →
9	GLM-5.2	76.7%	$46.49	221	trace →
10	Claude Sonnet 4.6	74.9%	$24.61	335	trace →
11	GPT 5.5 (high)	74.2%	$4.15	42	trace →
12	Claude Opus 4.8 (xhigh)	73.5%	$30.02	136	trace →
13	Muse Spark 1.2 (xhigh)	73.5%	$0.21	169	trace →
14	Gemini 3.7 Flash	32.3%	$2.17	133	trace →
15	GPT-5.6 Sol	32.1%	$1.31	14	trace →
16	GPT 5.5	24.7%	$1.15	16	trace →
17	Muse Spark 1.3 (xhigh)	21.6%	$2.45	304	trace →
18	Gemini 3.1 Pro	21.6%	$2.32	78	trace →
19	Claude Opus 4.7 (xhigh)	20.7%	$30.03	224	trace →
20	Muse Spark 1.1 (xhigh)	20.7%	$1.03	202	trace →
21	Claude Opus 4.6	19.5%	$15.01	227	trace →
22	GPT 5.4	19.5%	$0.20	7	trace →
23	Gemini 3.6 Flash	19.3%	$4.14	136	trace →
24	Claude Opus 4.7	19.3%	$5.80	92	trace →
25	GPT 5 mini	17.9%	$0.02	14	trace →
26	GPT 5.4 mini	14.4%	$0.03	6	trace →
27	Claude Haiku 4.5	9.8%	$0.98	136	trace →
28	Gemini 3 Flash	8.4%	$0.40	83	trace →
29	Muse Spark 1.3 (max)	0.0%	$11.73	358	trace →

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