dandavison/delta | ProgramBench

A syntax-highlighting pager for git, diff, grep, rg --json, and blame output

949

Generated Behavioral Tests

80.3%

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)

30 runs

#	Model	Score	Cost	Calls
1	GPT 6 Astra (max)	80.3%	$19.52	89	trace →
2	Muse Wonder Full	79.3%	TBA	509	trace →
3	Claude Fable 5.1 (xhigh)	76.2%	$89.32	333	trace →
4	Claude Opus 5.5 (xhigh)	70.9%	$10.37	111	trace →
5	Claude Opus 5 (xhigh)	66.5%	$92.02	371	trace →
6	GPT-5.6 Sol (xhigh)	47.7%	$10.19	41	trace →
7	GPT 5.5 (xhigh)	39.0%	$10.75	65	trace →
8	Claude Sonnet 4.6	37.3%	$34.08	470	trace →
9	Muse Spark 1.3 (xhigh)	36.9%	$1.43	167	trace →
10	GLM-5.2	36.8%	$31.00	275	trace →
11	Claude Opus 4.8 (xhigh)	35.8%	$14.66	131	trace →
12	Muse Spark 1.2 (xhigh)	34.1%	$0.68	142	trace →
13	GPT 5.5 (high)	31.8%	$6.94	57	trace →
14	GPT 5.5	30.1%	$0.96	14	trace →
15	GPT-5.6 Sol	29.4%	$0.93	10	trace →
16	Claude Opus 4.7 (xhigh)	28.1%	$1.19	48	trace →
17	Claude Opus 4.7	23.1%	$0.35	22	trace →
18	Gemini 3 Flash	21.3%	$0.20	52	trace →
19	GPT 5 mini	20.8%	$0.03	14	trace →
20	GPT 5.4	17.8%	$0.23	7	trace →
21	Claude Haiku 4.5	10.1%	$1.28	166	trace →
22	Gemini 3.6 Flash	9.6%	$3.73	129	trace →
23	Muse Wonder (xhigh)	7.6%	$40.51	345	trace →
24	GPT 5.4 mini	5.4%	$0.05	8	trace →
25	Muse Spark 1.1 (xhigh)	0.8%	$0.39	186	trace →
26	Claude Opus 4.6	0.8%	$8.32	236	trace →
27	Muse Spark 1.3 (max)	0.7%	$12.41	370	trace →
28	Gemini 3.7 Flash	0.7%	$3.80	141	trace →
29	Gemini 3.5 Flash	0.7%	$1.85	79	trace →
30	Gemini 3.1 Pro	0.0%	$1.70	120	trace →

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