Leaderboard v1: Computer / GLM 5.3

[c-suvamsa]

Summary

• Agent / Model: DevRev Computer / GLM 5.3 (Z.ai).
• Source Harbor job URL: https://hub.harborframework.com/jobs/003cd987-31bf-4ac5-ab54-551a743c977b.
• Run: 2026-10-16; enterprise-bench/tasks/v1 via Daytona; 14 tasks × 10 attempts.
• Results: 130/140 rewards of 1.0 = 92.9% accuracy; 43,519,519 recorded input + output tokens; $85.55 SDK-reported cost.

PR checklist – leaderboard row entry

Provenance and access

• Source job is public and owned by the submitter; entry header and URL match its job ID.
• Entry has required metadata and metrics; 140 distinct trial IDs match n_trials.
• Accuracy, pass@k, and token breakdown reconcile with the recorded run; cost equals the sum of saved SDK reports.
• Agent, model, and provider are shown on the job.
• Every local trial has an ATIF trajectory and a reward/result; no failed trial was removed.
• Reviewer to confirm logged-out replay of every trajectory.

Run conditions and review

• Task content digests for all 14 tasks match enterprise-bench main. The run used an absolute local tasks/v1 path rather than a registry-pinned dataset version.
• Scored timeout multiplier is 1.0 and no CPU/memory/storage override was recorded.
• Reviewer to confirm benchmark-answer access boundaries, applied model route, and independently replay the score.

Validation

• Main-branch leaderboard validator passed locally.
• Repository validate and validate-leaderboard CI checks pass.

Notes for reviewers

The model label was supplied by the run owner after execution; saved Computer traces show the generic gateway alias, not a directly resolved provider model. Trial rewards were not changed.

[nimit2801]

Thanks for the Computer / GLM 5.3 leaderboard submission. First-touch from Nimit’s intake workflow, not an approval. Both validation checks are passing; technical review still needs to verify:

• Logged-out access to every Harbor trajectory and independent score/token/cost reconciliation.
• Evidence for the actual model/provider route, given the generic gateway alias in saved traces.
• Task provenance, timeout comparability, and benchmark-answer access boundaries.