quinn-rs/quinn | ProgramBench

Async-friendly QUIC implementation in Rust

522

Generated Behavioral Tests

99.6%

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)

29 runs

#	Model	Score	Cost	Calls
1	Claude Opus 5.5 (xhigh)	99.6%	$33.13	283	trace →
2	Muse Wonder Full	99.0%	TBA	363	trace →
3	Claude Fable 5.1 (xhigh)	98.5%	$26.80	193	trace →
4	GPT 6 Astra (max)	96.6%	$13.25	59	trace →
5	Muse Spark 1.3 (max)	96.6%	$2.67	194	trace →
6	Muse Wonder (xhigh)	95.8%	$35.42	327	trace →
7	Muse Spark 1.3 (xhigh)	94.6%	$1.60	259	trace →
8	GPT-5.6 Sol (xhigh)	88.1%	$3.81	24	trace →
9	GLM-5.2	86.5%	$7.99	133	trace →
10	GPT 5.5 (xhigh)	84.5%	$3.83	40	trace →
11	Claude Opus 4.8 (xhigh)	82.2%	$9.21	86	trace →
12	Muse Spark 1.1 (xhigh)	80.1%	$0.48	163	trace →
13	Muse Spark 1.2 (xhigh)	78.5%	$1.03	138	trace →
14	GPT 5.5 (high)	73.0%	$3.09	34	trace →
15	GPT-5.6 Sol	70.3%	$0.75	13	trace →
16	Gemini 3.6 Flash	69.7%	$3.08	94	trace →
17	Claude Opus 4.7 (xhigh)	63.4%	$5.00	117	trace →
18	GPT 5.5	62.3%	$1.31	18	trace →
19	Claude Opus 4.6	61.9%	$7.44	147	trace →
20	Claude Sonnet 4.6	57.5%	$16.65	375	trace →
21	Gemini 3.1 Pro	56.5%	$1.99	88	trace →
22	Claude Opus 4.7	53.8%	$2.27	54	trace →
23	GPT 5.4	46.9%	$0.31	10	trace →
24	Gemini 3 Flash	26.2%	$0.32	88	trace →
25	Claude Haiku 4.5	26.1%	$0.51	92	trace →
26	GPT 5.4 mini	20.9%	$0.04	9	trace →
27	GPT 5 mini	19.3%	$0.02	9	trace →
28	Gemini 3.7 Flash	0.0%	$0.72	77	trace →
29	Gemini 3.5 Flash	0.0%	$4.36	93	trace →

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