🤖 feat: upload Terminal-Bench results to BigQuery #1737
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
ammar-agent
force-pushed
the
ci-telemetry-y83p
branch
2 times, most recently
from
9f16b47 to
1e0136e
Compare
Add CI pipeline to persist benchmark results in BigQuery for tracking performance over time. Changes: - Add scripts/upload-tbench-results.py to parse Harbor output and upload one row per trial to benchmarks.tbench_results - Add upload step to terminal-bench.yml workflow (guarded for coder/mux) Schema: run_id, task_id, github context (6 cols), run config (5 cols), results (accuracy, n_resolved, n_unresolved), per-task (passed, score, tokens), raw JSON blobs for future-proofing.
ammar-agent
force-pushed
the
ci-telemetry-y83p
branch
from
1e0136e to
90ff717
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Add CI pipeline to persist benchmark results in BigQuery for tracking performance over time.
Changes
scripts/upload-tbench-results.pyto parse Harbor output and upload one row per trial tobenchmarks.tbench_resultsterminal-bench.ymlworkflow (guarded for coder/mux repo only)Schema
Single table
mux-benchmarks.benchmarks.tbench_results:run_id,task_idgithub_run_id,github_workflow,github_sha,github_ref,github_actor,github_event_namemodel_name,thinking_level,mode,dataset,experimentsaccuracy,n_resolved,n_unresolvedpassed,score,n_input_tokens,n_output_tokensrun_result_json,task_result_json(future-proofing)ingested_atTest Plan
Generated with
mux• Model:anthropic:claude-opus-4-5• Thinking:high• Cost:$6.82