iframe-proxy | Sunbelt Computer Software

Zstandard - Fast real-time compression algorithm

2,038

Generated Behavioral Tests

72.4%

Best Score

Gemini 3.7 Flash

Results by Model

Hover a point for details · The line marks the Pareto frontier (best score per cost) · Click a point to see model details

21 runs

#	Model	Score	Cost	Calls
1	Gemini 3.7 Flash	72.4%	$1.71	134	trace →
2	Gemini 3.6 Flash	70.8%	$3.23	144	trace →
3	Claude Sonnet 4.6	68.8%	$15.29	375	trace →
4	GPT 5.5 (xhigh)	68.6%	$5.13	64	trace →
5	GPT-5.6 Sol (xhigh)	68.3%	$7.54	53	trace →
6	GPT 5.5 (high)	62.4%	$2.54	34	trace →
7	Claude Opus 4.7 (xhigh)	61.6%	$9.84	142	trace →
8	Claude Opus 4.8 (xhigh)	60.6%	$25.52	143	trace →
9	GPT 5.5	58.4%	$1.24	22	trace →
10	Claude Opus 4.7	54.9%	$3.68	104	trace →
11	Gemini 3 Flash	50.8%	$0.21	73	trace →
12	GLM-5.2	50.4%	$21.42	229	trace →
13	Gemini 3.5 Flash	48.9%	$4.18	210	trace →
14	Gemini 3.1 Pro	44.9%	$1.11	98	trace →
15	GPT-5.6 Sol	40.7%	$0.32	8	trace →
16	GPT 5.4	35.3%	$0.21	11	trace →
17	Claude Haiku 4.5	33.9%	$0.84	129	trace →
18	GPT 5.4 mini	7.7%	$0.02	5	trace →
19	GPT 5 mini	7.0%	$0.02	7	trace →
20	Claude Opus 5 (xhigh)	0.0%	$12.66	106	trace →
21	Claude Opus 4.6	0.0%	$1.41	189	trace →

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