Release v0.1

Native division

Native workloads differ: rows are not a head-to-head comparison.

Each system runs its own model and shape, shown side by side with the normalised metrics of RFC-0004. Rows are in alphabetical order by system, workload and profile. This page is sorted by profile, as requested by following that column's link; alphabetical order. There is no combined score and no highlighted value.

Native division rows
System	Claim card summary	Workload	Profile	rate_whole_wall	rate_prove.steady	cost_per_1k_tokens_whole_wall	proof_bytes_per_token	verify_seconds_per_token	overhead_vs_serving_whole_wall
flashprove	relation: The output token is the top choice of the integer model whose weights were committed under the given commitment ID, on the given 1,024-token window. security.notion: knowledge_soundness coverage: prefill, request residual: proves the integer model, which differs from the 16-bit model's top token at some positions	fp-maverick-w1024-b1	prover-h100	1.891 token/s scope whole_wallgrade derivedtier reportedmock mean 1.891, sd 0.005308, min 1.886, max 1.896, n 3, n_failed 0 source: mock derivation record	17.43 token/s scope prove.steadygrade derivedtier reportedmock mean 17.43, sd 0.08201, min 17.35, max 17.51, n 3, n_failed 0 source: mock derivation record	0.6301 USD/1k_token scope whole_wallgrade derivedtier reportedmock mean 0.6301, sd 0.001770, min 0.6285, max 0.6320, n 3, n_failed 0 source: mock derivation record	18,340 B/token grade derivedtier reportedmock mean 18,340, sd 5.859, min 18,340, max 18,350, n 3, n_failed 0 source: mock derivation record	0.003047 s/token scope verifygrade derivedtier reportedmock mean 0.003047, sd 1.953e-5, min 0.003027, max 0.003066, n 3, n_failed 0 source: mock derivation record	null (not_applicable) ratio scope whole_wallgrade derivedtier reportedmock source: mock derivation record
flashprove	relation: The output token is the top choice of the integer model whose weights were committed under the given commitment ID, on the given 1,024-token window. security.notion: knowledge_soundness coverage: prefill, request residual: proves the integer model, which differs from the 16-bit model's top token at some positions	fp-maverick-w1024-b24	prover-h100	34.17 token/s scope whole_wallgrade derivedtier reproducedmock mean 34.17, sd 0.05753, min 34.11, max 34.23, n 3, n_failed 0 source: mock derivation record	110.7 token/s scope prove.steadygrade derivedtier reproducedmock mean 110.7, sd 0.8317, min 109.8, max 111.5, n 3, n_failed 0 source: mock derivation record	0.03487 USD/1k_token scope whole_wallgrade derivedtier reproducedmock mean 0.03487, sd 5.873e-5, min 0.03482, max 0.03493, n 3, n_failed 0 source: mock derivation record	18,340 B/token grade derivedtier reproducedmock mean 18,340, sd 4.905, min 18,330, max 18,340, n 3, n_failed 0 source: mock derivation record	0.003047 s/token scope verifygrade derivedtier reproducedmock mean 0.003047, sd 2.930e-5, min 0.003018, max 0.003076, n 3, n_failed 0 source: mock derivation record	null (not_measurable_on_profile) ratio scope whole_wallgrade derivedtier reproducedmock source: mock derivation record
ref-recompute	Reference row: runs the model without proving, no proof claim (RFC-0015).	sash-l31-8b-c4096	prover-h100	469.0 token/s scope whole_wallgrade derivedtier reportedmock mean 469.0, sd 5.289, min 464.0, max 474.6, n 3, n_failed 0 source: mock derivation record	not reported	0.002541 USD/1k_token scope whole_wallgrade derivedtier reportedmock mean 0.002541, sd 2.860e-5, min 0.002511, max 0.002568, n 3, n_failed 0 source: mock derivation record	not reported	not reported	not reported
ref-serve	Reference row: runs the model without proving, no proof claim (RFC-0015).	fp-maverick-w1024-b24	prover-h100	null (not_measurable_on_profile) token/s scope whole_wallgrade derivedtier reportedmock source: mock derivation record	not reported	not reported	not reported	not reported	not reported
ref-serve	Reference row: runs the model without proving, no proof claim (RFC-0015).	sash-l31-8b-c4096	prover-h100	1,347 token/s scope whole_wallgrade derivedtier reportedmock mean 1,347, sd 11.82, min 1,336, max 1,359, n 3, n_failed 0 source: mock derivation record	not reported	0.0008844 USD/1k_token scope whole_wallgrade derivedtier reportedmock mean 0.0008844, sd 7.758e-6, min 0.0008767, max 0.0008922, n 3, n_failed 0 source: mock derivation record	not reported	not reported	not reported
sash	relation: not stated security.notion: not stated coverage: both, segment_grid residual: not stated	sash-l31-8b-c1024	prover-h100	0.7873 token/s scope whole_wallgrade derivedtier reportedmock mean 0.7873, sd 0.007639, min 0.7798, max 0.7951, n 3, n_failed 0 source: mock derivation record	null (not_observable) token/s scope prove.steadygrade derivedtier reportedmock source: mock derivation record	1.514 USD/1k_token scope whole_wallgrade derivedtier reportedmock mean 1.514, sd 0.01468, min 1.499, max 1.528, n 3, n_failed 0 source: mock derivation record	4,476,000 B/token grade derivedtier reportedmock mean 4,476,000, sd 0, min 4,476,000, max 4,476,000, n 3, n_failed 0 source: mock derivation record	0.02773 s/token scope verifygrade derivedtier reportedmock mean 0.02773, sd 0.0003228, min 0.02739, max 0.02803, n 3, n_failed 0 source: mock derivation record	null (not_applicable) ratio scope whole_wallgrade derivedtier reportedmock source: mock derivation record
sash	relation: not stated security.notion: not stated coverage: both, segment_grid residual: not stated	sash-l31-8b-c4096	prover-h100	0.8411 token/s scope whole_wallgrade derivedtier peer-reviewedmock mean 0.8411, sd 0.009368, min 0.8309, max 0.8493, n 3, n_failed 1 source: mock derivation record	null (not_observable) token/s scope prove.steadygrade derivedtier peer-reviewedmock source: mock derivation record	1.417 USD/1k_token scope whole_wallgrade derivedtier peer-reviewedmock mean 1.417, sd 0.01584, min 1.403, max 1.434, n 3, n_failed 1 source: mock derivation record	4,297,000 B/token grade derivedtier peer-reviewedmock mean 4,297,000, sd 0, min 4,297,000, max 4,297,000, n 3, n_failed 1 source: mock derivation record	0.02632 s/token scope verifygrade derivedtier peer-reviewedmock mean 0.02632, sd 0.0003049, min 0.02600, max 0.02661, n 3, n_failed 1 source: mock derivation record	1,602 ratio scope whole_wallgrade derivedtier peer-reviewedmock source: mock derivation record