Skip to content

🤖 bench: switch Terminal Bench GPT 5.2 to GPT 5.4 #2824

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
ibetitsmike merged 2 commits into from
Mar 6, 2026
+12 −3
Merged

🤖 bench: switch Terminal Bench GPT 5.2 to GPT 5.4 #2824

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
60bcf0b
🤖 bench: switch Terminal Bench GPT 5.2 to GPT 5.4
ibetitsmike Mar 6, 2026
c395ee1
🤖 bench: preserve historical GPT-5.2 metadata
ibetitsmike Mar 6, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/workflows/nightly-terminal-bench.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ on:
workflow_dispatch:
inputs:
models:
description: 'Models to test (comma-separated, or "all" for opus-4-6 + gpt-5.3-codex + gpt-5.2 + google/gemini-3-pro-preview + google/gemini-3-flash-preview)'
description: 'Models to test (comma-separated, or "all" for opus-4-6 + gpt-5.3-codex + gpt-5.4 + google/gemini-3-pro-preview + google/gemini-3-flash-preview)'
required: false
default: "all"
type: string
Expand Down Expand Up @@ -99,7 +99,7 @@ jobs:
INPUT_MODELS: ${{ inputs.models }}
run: |
if [ "$INPUT_MODELS" = "all" ] || [ -z "$INPUT_MODELS" ]; then
echo 'models=["anthropic/claude-opus-4-6","openai/gpt-5.3-codex","openai/gpt-5.2","google/gemini-3-pro-preview","google/gemini-3-flash-preview"]' >> "$GITHUB_OUTPUT"
echo 'models=["anthropic/claude-opus-4-6","openai/gpt-5.3-codex","openai/gpt-5.4","google/gemini-3-pro-preview","google/gemini-3-flash-preview"]' >> "$GITHUB_OUTPUT"
else
# Convert comma-separated to JSON array
models_json=$(echo "$INPUT_MODELS" | jq -R -s -c 'split(",") | map(gsub("^\\s+|\\s+$"; ""))')
Expand Down
2 changes: 1 addition & 1 deletion .github/workflows/terminal-bench.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,7 +87,7 @@ on:
required: false
type: string
model_name:
description: "Model to use (e.g., anthropic/claude-opus-4-5, openai/gpt-5.2)"
description: "Model to use (e.g., anthropic/claude-opus-4-5, openai/gpt-5.4)"
required: false
type: string
mux_run_args:
Expand Down
9 changes: 9 additions & 0 deletions benchmarks/terminal_bench/prepare_leaderboard_submission.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -102,13 +102,22 @@
"model_org_display_name": "Anthropic",
"folder_name": "Claude-Opus-4.6",
},
# Keep historical GPT-5.2 metadata alongside the new GPT-5.4 bench target
# so mixed or older artifact sets still map to the canonical leaderboard names.
"openai/gpt-5.2": {
"model_name": "gpt-5.2",
"model_provider": "openai",
"model_display_name": "GPT-5.2",
"model_org_display_name": "OpenAI",
"folder_name": "GPT-5.2",
},
"openai/gpt-5.4": {
Comment thread
ibetitsmike marked this conversation as resolved.
"model_name": "gpt-5.4",
"model_provider": "openai",
"model_display_name": "GPT-5.4",
"model_org_display_name": "OpenAI",
"folder_name": "GPT-5.4",
},
"openai/gpt-5-codex": {
"model_name": "gpt-5-codex",
"model_provider": "openai",
Expand Down
Loading