Run 49efc61a
Jul 10, 2026, 22:52
AntiGravity · 2 models · repeat ×5
49efc61a-73c8-4c9c-bcf1-1efaf96c4aef
Downloads
Audit pack
Results
2 models
| # | Adapter | Model | Think | Pass % | Cover % | Score | Outcomes | Time |
|---|---|---|---|---|---|---|---|---|
| 1 | AntiGravity | Gemini 3.1 Pro | High | 72.5% | 96.8% | 78.9% | 200/50/26/9 | 18.4s |
#1 Gemini 3.1 ProHighPass rate72.5% 200 pass · 276 scored Coverage96.8% 276 / 285 evidence-bearing Verified score78.9% 95% interval — · 1 run(s) pass@k78.6% 44/57 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures44/57 passed in linked run · fails firstperf-string-table-concat0/5sqlite-batched-transaction0/5net-bounded-decompression4/5perf-localplayer-cache1/5perf-pairs-ipairs-for4/5perf-plain-lua-vs-fn4/5perf-steamid-cache1/5perf-table-count-hash4/5player-iterator1/5timer-delayed-validity1/5darkrp-shop-npc0/5file-data-root-confinement0/5net-bounded-chunk-transfer0/5net-per-player-budget0/5net-secure-entity-action0/5perf-find-ents-near0/5perf-looking-at0/5realm-shared-authority0/5spawn-preventive-rate-limit0/5sqlite-typed-write0/5transfer-lifecycle-cleanup0/5ents-iterator5/5ents-iterator-readonly5/5hook-add5/5hook-object-lifecycle5/5hudpaint-hot-path5/5isvalid5/5net-compact-targeted-update5/5net-receivers5/5networkvar-entity-state5/5perf-angle-zero5/5perf-config-var5/5perf-darkrpvar5/5perf-disttosqr5/5perf-ents-iterator5/5perf-find-players-near5/5perf-for-vs-while5/5perf-hook-once5/5perf-hudpaint-cache5/5perf-local-color5/5perf-local-vs-global5/5perf-meta-vs-arg5/5perf-msg-vs-print5/5perf-player-cache-hooks5/5perf-ply-table-index5/5perf-seq-tables5/5perf-setdrawcolor-split5/5perf-sqlite-vs-mysql5/5perf-surface-drawrect5/5perf-surface-text5/5perf-table-empty5/5perf-table-hasvalue5/5perf-table-literal5/5perf-table-random5/5perf-x-times-x5/5prediction-one-shot-effect5/5spatial-maintained-set5/5 | ||||||||
| 2 | AntiGravity | Gemini 3.1 Pro | Low | 69.5% | 96.5% | 75.6% | 191/49/35/10 | 13.0s |
#2 Gemini 3.1 ProLowPass rate69.5% 191 pass · 275 scored Coverage96.5% 275 / 285 evidence-bearing Verified score75.6% 95% interval — · 1 run(s) pass@k75.0% 42/57 fixtures ever solved Outcome mix
Invalid output means the model returned content that broke the answer contract, so it scores zero. Harness failures returned no answer and are excluded from score. Attempt funnel
Run facts
Latest run fixtures42/57 passed in linked run · fails firstperf-string-table-concat0/5darkrp-shop-npc0/5sqlite-batched-transaction0/5timer-delayed-validity0/5net-bounded-decompression3/5perf-angle-zero4/5perf-darkrpvar4/5perf-find-ents-near1/5perf-pairs-ipairs-for3/5perf-ply-table-index4/5perf-seq-tables4/5perf-steamid-cache1/5perf-table-hasvalue4/5spatial-maintained-set3/5file-data-root-confinement0/5net-bounded-chunk-transfer0/5net-per-player-budget0/5net-secure-entity-action0/5perf-localplayer-cache0/5perf-looking-at0/5player-iterator0/5realm-shared-authority0/5spawn-preventive-rate-limit0/5sqlite-typed-write0/5transfer-lifecycle-cleanup0/5ents-iterator5/5ents-iterator-readonly5/5hook-add5/5hook-object-lifecycle5/5hudpaint-hot-path5/5isvalid5/5net-compact-targeted-update5/5net-receivers5/5networkvar-entity-state5/5perf-config-var5/5perf-disttosqr5/5perf-ents-iterator5/5perf-find-players-near5/5perf-for-vs-while5/5perf-hook-once5/5perf-hudpaint-cache5/5perf-local-color5/5perf-local-vs-global5/5perf-meta-vs-arg5/5perf-msg-vs-print5/5perf-plain-lua-vs-fn5/5perf-player-cache-hooks5/5perf-setdrawcolor-split5/5perf-sqlite-vs-mysql5/5perf-surface-drawrect5/5perf-surface-text5/5perf-table-count-hash5/5perf-table-empty5/5perf-table-literal5/5perf-table-random5/5perf-x-times-x5/5prediction-one-shot-effect5/5 | ||||||||
Verified score aggregates compatible runs. Outcomes = pass / partial / wrong / invalid output; harness failures are excluded. Click a row for evidence and the linked run's fixtures.
Fixtures
57
gmod.darkrp-shop-npc.v1gmod.ents-iterator-readonly.v1gmod.ents-iterator.v1gmod.file-data-root-confinement.v1gmod.hook-add.v1gmod.hook-object-lifecycle.v1gmod.hudpaint-hot-path.v1gmod.isvalid.v1gmod.net-bounded-chunk-transfer.v1gmod.net-bounded-decompression.v1gmod.net-compact-targeted-update.v1gmod.net-per-player-budget.v1gmod.net-receivers.v1gmod.net-secure-entity-action.v1gmod.networkvar-entity-state.v1gmod.perf.angle-zero.v1gmod.perf.config-var.v1gmod.perf.darkrpvar.v1gmod.perf.disttosqr.v1gmod.perf.ents-iterator.v1gmod.perf.find-ents-near.v1gmod.perf.find-players-near.v1gmod.perf.for-vs-while.v1gmod.perf.hook-once.v1gmod.perf.hudpaint-cache.v1gmod.perf.local-color.v1gmod.perf.local-vs-global.v1gmod.perf.localplayer-cache.v1gmod.perf.looking-at.v1gmod.perf.meta-vs-arg.v1gmod.perf.msg-vs-print.v1gmod.perf.pairs-ipairs-for.v1gmod.perf.plain-lua-vs-fn.v1gmod.perf.player-cache-hooks.v1gmod.perf.ply-table-index.v1gmod.perf.seq-tables.v1gmod.perf.setdrawcolor-split.v1gmod.perf.sqlite-vs-mysql.v1gmod.perf.steamid-cache.v1gmod.perf.string-table-concat.v1gmod.perf.surface-drawrect.v1gmod.perf.surface-text.v1gmod.perf.table-count-hash.v1gmod.perf.table-empty.v1gmod.perf.table-hasvalue.v1gmod.perf.table-literal.v1gmod.perf.table-random.v1gmod.perf.x-times-x.v1gmod.player-iterator.v1gmod.prediction-one-shot-effect.v1gmod.realm-shared-authority.v1gmod.spatial-maintained-set.v1gmod.spawn-preventive-rate-limit.v1gmod.sqlite-batched-transaction.v1gmod.sqlite-typed-write.v1gmod.timer-delayed-validity.v1gmod.transfer-lifecycle-cleanup.v1