will/claude-code
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(external-llm): align tier defaults with industry benchmarks

Browse Source 
- frontier: gpt-5.2 (GPT)
- mid-tier: claude-sonnet-4.5 (Claude)
- lightweight: claude-haiku-4.5 (Claude)

Prioritizes correctness over speed, aligned with MMLU/GPQA/Arena rankings.

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
OpenCode Test
2026-01-12 11:42:38 -08:00
parent f63172c4cf
commit a9eaf0114f
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
state/model-policy.json
View File

@@ -184,8 +184,8 @@
}, },
"tier_to_external_map": { "tier_to_external_map": {
"frontier": "github-copilot/gpt-5.2", "frontier": "github-copilot/gpt-5.2",
"mid-tier": "github-copilot/gpt-5-mini", "mid-tier": "github-copilot/claude-sonnet-4.5",
"lightweight": "opencode/gpt-5-nano" "lightweight": "github-copilot/claude-haiku-4.5"
}, },
"task_routing": { "task_routing": {
"reasoning": "github-copilot/gpt-5.2", "reasoning": "github-copilot/gpt-5.2",