ibara Lab benchmarkshttps://ibara.app/docs/benchmarks/runsMeasured results and corrections for computer and browser use.Permanent Ubuntu peer and reader calibration journal: revision 1https://ibara.app/docs/benchmarks/runs/frame-peer-calibration-20261011/r1https://ibara.app/docs/benchmarks/runs/frame-peer-calibration-20261011/r1Sun, 11 Oct 2026 05:59:22 +0000Diagnostic run · 86 attempts recorded. Measured 2026-10-11. benchmark.Ubuntu common native confirmation: revision 1https://ibara.app/docs/benchmarks/runs/common-native-20261011-ubuntu/r1https://ibara.app/docs/benchmarks/runs/common-native-20261011-ubuntu/r1Sun, 11 Oct 2026 05:59:20 +0000Diagnostic run · 60 attempts recorded. Measured 2026-10-11. benchmark.Omarchy common native confirmation: revision 1https://ibara.app/docs/benchmarks/runs/common-native-20261011-omarchy/r1https://ibara.app/docs/benchmarks/runs/common-native-20261011-omarchy/r1Sun, 11 Oct 2026 05:59:19 +0000Diagnostic run · 60 attempts recorded. Measured 2026-10-11. benchmark.Ubuntu interrupted common native diagnostic: revision 1https://ibara.app/docs/benchmarks/runs/common-native-interrupted-20261011-ubuntu/r1https://ibara.app/docs/benchmarks/runs/common-native-interrupted-20261011-ubuntu/r1Sun, 11 Oct 2026 05:59:17 +0000Diagnostic run · 40 attempts recorded. Measured 2026-10-11. benchmark.Omarchy interrupted common native diagnostic: revision 1https://ibara.app/docs/benchmarks/runs/common-native-interrupted-20261011-omarchy/r1https://ibara.app/docs/benchmarks/runs/common-native-interrupted-20261011-omarchy/r1Sun, 11 Oct 2026 05:59:16 +0000Diagnostic run · 41 attempts recorded. Measured 2026-10-11. benchmark.Ubuntu native benchmark confirmation: revision 1https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-ubuntu/r1https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-ubuntu/r1Sun, 11 Oct 2026 01:30:34 +0000Diagnostic run · 96 attempts recorded. Measured 2026-10-11. benchmark.Omarchy native benchmark confirmation: revision 1https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-omarchy/r1https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-omarchy/r1Sun, 11 Oct 2026 01:30:33 +0000Diagnostic run · 96 attempts recorded. Measured 2026-10-10. benchmark.Native interaction benchmark, round 4: revision 2https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-round04/r2https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-round04/r2Sun, 11 Oct 2026 01:30:32 +0000Diagnostic run · 60 attempts recorded. Measured 2026-10-10. benchmark.Native interaction benchmark, round 4: revision 1https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-round04/r1https://ibara.app/docs/benchmarks/runs/native-interaction-20261010-round04/r1Sat, 10 Oct 2026 22:56:33 +0000Diagnostic run · 60 attempts recorded. Measured 2026-10-10. benchmark.Six workflows with Sonnet 5.5 and GPT-6.1 Sol at medium effort: revision 1https://ibara.app/docs/benchmarks/runs/2026-10-08-medium-model-pair/r1https://ibara.app/docs/benchmarks/runs/2026-10-08-medium-model-pair/r1Fri, 09 Oct 2026 02:36:41 +0000Diagnostic run · 12 attempts recorded. Measured 2026-10-09. benchmark.Six-task computer-use baseline with GPT-6.1 Sol: revision 1https://ibara.app/docs/benchmarks/runs/2026-10-08-sol61-short-baseline/r1https://ibara.app/docs/benchmarks/runs/2026-10-08-sol61-short-baseline/r1Fri, 09 Oct 2026 02:11:43 +0000Diagnostic run · 6 attempts recorded. Measured 2026-10-09. benchmark.Incumbent computer-use diagnostic campaign: revision 1https://ibara.app/docs/benchmarks/runs/2026-10-08-incumbent-lifecycle-baseline/r1https://ibara.app/docs/benchmarks/runs/2026-10-08-incumbent-lifecycle-baseline/r1Fri, 09 Oct 2026 01:31:37 +0000Incomplete benchmark · 65 attempts recorded. Measured 2026-10-08. benchmark.Computer and browser use: diagnostic pilot: revision 3https://ibara.app/docs/benchmarks/runs/2026-10-07-incumbent-baseline/r3https://ibara.app/docs/benchmarks/runs/2026-10-07-incumbent-baseline/r3Thu, 08 Oct 2026 09:41:43 +0000Diagnostic run · 22 attempts recorded. Measured 2026-10-08. benchmark.Computer and browser use: diagnostic pilot: revision 2https://ibara.app/docs/benchmarks/runs/2026-10-07-incumbent-baseline/r2https://ibara.app/docs/benchmarks/runs/2026-10-07-incumbent-baseline/r2Thu, 08 Oct 2026 09:10:27 +0000Diagnostic run · 22 attempts recorded. Measured 2026-10-08. benchmark.Computer and browser use: incumbent diagnostic baseline: revision 1https://ibara.app/docs/benchmarks/runs/2026-10-07-incumbent-baseline/r1https://ibara.app/docs/benchmarks/runs/2026-10-07-incumbent-baseline/r1Thu, 08 Oct 2026 05:32:39 +00007/22 passed (31.8%). Measured 2026-10-08. benchmark.Computer and browser use: ibara 0.1.0-17: revision 1https://ibara.app/docs/benchmarks/runs/2026-09-29-release-benchmark/r1https://ibara.app/docs/benchmarks/runs/2026-09-29-release-benchmark/r1Thu, 08 Oct 2026 02:23:45 +0000132/157 passed (84.1%). Measured 2026-09-29. historical.