runs

One row per attempt, including invalidated ones. Sort any column, filter by model, level, mode or answer.

every run

the answer column shows what the model actually reported, normalised to lowercase letters. an invalidated run left its working directory and is excluded from every aggregate on this site, as is one that died on plan quota — that is a fact about the subscription, not the model.

✓ 0 invalidated

model	lvl	mode	trial	outcome	answer	chars	frames	spatial	time	shell	imgs	diffed	hit wall
fable-5	L1	blind	1	— timed out	—	0	0	0	1800s	42	41	—	30m
fable-5	L1	blind	2	~ quota	—	0	0	0	626s	16	8	—	—
fable-5	L1	blind	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L1	blind	3	~ quota	—	0	0	0	3s	0	0	—	—
fable-5	L1	blind	3	~ quota	—	0	0	0	5s	0	0	—	—
fable-5	L1	hinted	1	~ quota	—	0	0	0	555s	16	8	yes	—
fable-5	L1	hinted	1	— timed out	—	0	0	0	1800s	32	62	yes	—
fable-5	L1	hinted	2	~ quota	—	0	0	0	874s	24	23	—	—
fable-5	L1	hinted	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L1	hinted	2	~ quota	—	0	0	0	448s	16	6	yes	—
fable-5	L1	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L1	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	blind	1	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	blind	1	— timed out	—	0	0	0	1800s	53	38	yes	30m
fable-5	L2	blind	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	blind	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	blind	2	~ quota	—	0	0	0	483s	21	6	—	—
fable-5	L2	blind	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	blind	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	hinted	1	~ quota	—	0	0	0	639s	12	38	—	—
fable-5	L2	hinted	1	— timed out	—	0	0	0	1800s	29	35	yes	30m
fable-5	L2	hinted	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	hinted	2	~ quota	—	0	0	0	445s	10	21	yes	—
fable-5	L2	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L2	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	blind	1	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	blind	1	— timed out	—	0	0	0	1800s	41	29	—	—
fable-5	L3	blind	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	blind	2	~ quota	—	0	0	0	469s	16	5	—	—
fable-5	L3	blind	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	blind	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	hinted	1	— timed out	—	0	0	0	903s	25	22	yes	—
fable-5	L3	hinted	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	hinted	2	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
fable-5	L3	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
gpt-5.6/high	L1	blind	1	✓ solved	theolovesobsidian	17	2	2	817s	21	0	yes	—
gpt-5.6/high	L1	blind	2	✗ missed	obsidian	0	0	0	930s	37	0	—	—
gpt-5.6/high	L1	blind	3	✓ solved	theolovesobsidian	17	0	0	954s	20	0	—	—
gpt-5.6/high	L1	hinted	1	~ partial	snowflakeobsidian	8	8	8	6400s	217	0	yes	30m
gpt-5.6/high	L1	hinted	2	— timed out	—	0	0	0	1800s	39	0	—	30m
gpt-5.6/high	L1	hinted	3	— timed out	—	0	0	0	1800s	25	0	yes	30m
gpt-5.6/high	L2	blind	1	— timed out	—	0	0	0	1800s	42	0	—	30m
gpt-5.6/high	L2	blind	2	✗ missed	selfavoidance	0	0	0	2522s	42	0	yes	—
gpt-5.6/high	L2	blind	3	— timed out	—	0	0	0	1800s	23	0	yes	30m
gpt-5.6/high	L2	hinted	1	— timed out	—	0	0	0	1800s	42	0	—	30m
gpt-5.6/high	L2	hinted	2	— timed out	—	0	0	0	1800s	57	0	yes	30m
gpt-5.6/high	L2	hinted	3	— timed out	—	0	0	0	1800s	37	0	yes	30m
gpt-5.6/high	L3	blind	1	— timed out	—	0	0	0	1800s	50	0	—	30m
gpt-5.6/high	L3	blind	2	— timed out	—	0	0	0	1800s	44	0	yes	30m
gpt-5.6/high	L3	blind	3	— timed out	—	0	0	0	1800s	32	0	yes	30m
gpt-5.6/high	L3	hinted	1	— timed out	—	0	0	0	1800s	50	0	yes	30m
gpt-5.6/high	L3	hinted	2	— timed out	—	0	0	0	1800s	26	0	yes	30m
gpt-5.6/high	L3	hinted	3	— timed out	—	0	0	0	1800s	34	0	—	30m
gpt-5.6/med	L1	blind	1	~ partial	tooseasoned	1	0	0	668s	22	0	yes	—
gpt-5.6/med	L1	blind	2	~ partial	silentvideos	2	0	0	618s	20	0	yes	—
gpt-5.6/med	L1	blind	3	✗ missed	obsidian	0	0	0	576s	20	0	—	—
gpt-5.6/med	L1	hinted	1	~ partial	snowflakeobsidian	8	2	0	901s	22	0	yes	—
gpt-5.6/med	L1	hinted	2	✓ solved	theolovesobsidian	17	5	5	1751s	56	0	yes	—
gpt-5.6/med	L1	hinted	3	— timed out	—	0	0	0	1800s	54	0	—	30m
gpt-5.6/med	L2	blind	1	✗ missed	beyean	0	0	0	1457s	28	0	—	—
gpt-5.6/med	L2	blind	2	~ partial	casino	1	0	0	1193s	46	0	yes	—
gpt-5.6/med	L2	blind	3	— timed out	—	0	0	0	1800s	40	0	yes	30m
gpt-5.6/med	L2	hinted	1	— timed out	—	0	0	0	1800s	26	0	—	30m
gpt-5.6/med	L2	hinted	2	~ quota	—	0	0	0	2s	0	0	—	—
gpt-5.6/med	L2	hinted	2	— timed out	—	0	0	0	1800s	31	0	yes	30m
gpt-5.6/med	L2	hinted	3	— timed out	—	0	0	0	1800s	37	0	—	30m
gpt-5.6/med	L3	blind	1	✗ missed	zenith	0	0	0	1375s	26	0	yes	—
gpt-5.6/med	L3	blind	2	— timed out	—	0	0	0	1800s	39	0	yes	30m
gpt-5.6/med	L3	blind	3	— timed out	—	0	0	0	1800s	42	0	—	30m
gpt-5.6/med	L3	hinted	1	~ partial	internationalized	1	0	0	3149s	141	0	yes	30m
gpt-5.6/med	L3	hinted	2	— timed out	—	0	0	0	1800s	37	0	yes	30m
gpt-5.6/med	L3	hinted	3	— timed out	—	0	0	0	1800s	30	0	—	30m
opus-5	L1	blind	1	✓ solved	theolovesobsidian	17	17	17	1291s	43	17	—	—
opus-5	L1	blind	2	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L1	blind	2	— timed out	—	0	0	0	1800s	57	21	yes	30m
opus-5	L1	blind	3	✓ solved	theolovesobsidian	17	17	17	668s	31	20	—	—
opus-5	L1	hinted	1	~ quota	—	0	0	0	569s	19	7	—	—
opus-5	L1	hinted	1	— timed out	—	0	0	0	1800s	61	19	yes	30m
opus-5	L1	hinted	2	~ quota	—	0	0	0	986s	31	20	—	—
opus-5	L1	hinted	2	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L1	hinted	2	— timed out	—	0	0	0	1800s	40	24	—	30m
opus-5	L1	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L1	hinted	3	— timed out	—	0	0	0	1800s	31	11	—	30m
opus-5	L2	blind	1	— timed out	—	0	0	0	1800s	53	19	yes	30m
opus-5	L2	blind	2	~ quota	—	0	0	0	3s	0	0	—	—
opus-5	L2	blind	2	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L2	blind	2	— timed out	—	0	0	0	1800s	50	17	—	30m
opus-5	L2	blind	3	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L2	blind	3	— timed out	—	0	0	0	1800s	66	18	yes	30m
opus-5	L2	hinted	1	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L2	hinted	1	— timed out	—	0	0	0	1800s	46	26	—	30m
opus-5	L2	hinted	2	~ quota	—	0	0	0	520s	17	9	—	—
opus-5	L2	hinted	2	— timed out	—	0	0	0	1800s	48	35	—	30m
opus-5	L2	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L2	hinted	3	— timed out	—	0	0	0	1800s	44	13	—	30m
opus-5	L3	blind	1	~ quota	—	0	0	0	536s	28	7	yes	—
opus-5	L3	blind	1	— timed out	—	0	0	0	1800s	52	15	—	30m
opus-5	L3	blind	2	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L3	blind	2	— timed out	—	0	0	0	1800s	38	15	—	30m
opus-5	L3	blind	3	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L3	blind	3	— timed out	—	0	0	0	1800s	47	38	—	30m
opus-5	L3	hinted	1	— timed out	—	0	0	0	1800s	56	33	yes	30m
opus-5	L3	hinted	2	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L3	hinted	2	— timed out	—	0	0	0	1800s	34	44	—	30m
opus-5	L3	hinted	3	~ quota	—	0	0	0	2s	0	0	—	—
opus-5	L3	hinted	3	— timed out	—	0	0	0	1800s	63	64	yes	30m