Skip to content

Add claude-opus-5 to available model options - #752

Merged
Sun Haoran (haoranpb) merged 6 commits into
mainfrom
add-claude-opus-5-model
Aug 6, 2026
Merged

Add claude-opus-5 to available model options#752
Sun Haoran (haoranpb) merged 6 commits into
mainfrom
add-claude-opus-5-model

Conversation

@Groenbech96

Copy link
Copy Markdown
Collaborator

Adds claude-opus-5 as a selectable model.

Changes

  • .github/workflows/copilot-evaluation.yml - model choice
  • .github/workflows/claude-evaluation.yml - model choice
  • .github/workflows/contamination-file-path-identification.yml - model choice
  • src/bcbench/cli_options.py - added to CopilotModel and ClaudeCodeModel literals

Note: workflow dropdown options only take effect once merged to the default branch.

Adds claude-opus-5 as a selectable model in the Copilot, Claude Code, and contamination evaluation workflows, and to the CopilotModel/ClaudeCodeModel literals.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot AI balanced review requested due to automatic review settings July 27, 2026 08:00

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds Claude Opus 5 as an evaluation model.

Changes:

  • Adds model choices to three workflows.
  • Extends Copilot and Claude Code CLI model types.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 3 comments.

File Description
src/bcbench/cli_options.py Adds CLI model literals.
.github/workflows/copilot-evaluation.yml Adds Copilot workflow choice.
.github/workflows/claude-evaluation.yml Adds Claude workflow choice.
.github/workflows/contamination-file-path-identification.yml Adds contamination workflow choice.

Comment thread .github/workflows/copilot-evaluation.yml
Comment thread .github/workflows/contamination-file-path-identification.yml
Comment thread .github/workflows/claude-evaluation.yml
Claude Code added the claude-opus-5 model in 2.1.219; the pinned 2.1.160 does not know the alias.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings July 27, 2026 09:05

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated no new comments.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings July 27, 2026 09:10

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated no new comments.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings July 27, 2026 09:28

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated no new comments.

Copilot AI review requested due to automatic review settings July 29, 2026 08:26

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 5 out of 5 changed files in this pull request and generated no new comments.

Comment thread src/bcbench/cli_options.py Outdated
Comment thread .github/workflows/claude-evaluation.yml Outdated
Comment thread .github/workflows/copilot-evaluation.yml Outdated
@haoranpb

Copy link
Copy Markdown
Collaborator

The turn count metrics is also broken in the latest copilot cli, but we will address that in a seperate PR, probably leveraging the --output-format=json

Copilot AI review requested due to automatic review settings August 6, 2026 11:53

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated no new comments.

Suppressed comments (1)

src/bcbench/cli_options.py:32

  • The PR description says this change only adds claude-opus-5, but this block replaces the entire Copilot model set, and the same PR also changes the default model to gpt-5.6-luna in three commands/workflows and upgrades both evaluation CLIs. That is a materially broader behavior change than the stated scope. Either preserve the existing choices/defaults and append claude-opus-5, or update the title and description to explicitly document the model-set migration, default change, and CLI upgrades.
        "claude-sonnet-5",
        "claude-opus-5",
        "gpt-5.6-sol",
        "gpt-5.6-terra",
        "gpt-5.6-luna",

@haoranpb
Sun Haoran (haoranpb) merged commit 4f3f41a into main Aug 6, 2026
15 checks passed
@haoranpb
Sun Haoran (haoranpb) deleted the add-claude-opus-5-model branch August 6, 2026 12:19
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants