Joseph CostaandClaude Opus 4.8
9938d46a67
A stdlib pre-router in front of Ollama with LiteLLM backend: - auto model selection by content/tools/modality, with fallbacks - OpenAI /v1, Anthropic /v1/messages, and Ollama-native /api/* endpoints - Whisper-shaped /v1/audio/transcriptions + in-chat audio - key-based fleet policies (e.g. force a client onto uncensored models) - optional Bearer auth; launchd/systemd service install - benchmark harnesses (speed, quality, agentic tool use) with sample results Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
52 lines
886 B
JSON
52 lines
886 B
JSON
{
|
|
"gemma4:26b": {
|
|
"seq": 1,
|
|
"parallel": 1,
|
|
"chain": 1,
|
|
"select": 1,
|
|
"recover": 0,
|
|
"abstain": 1,
|
|
"honesty": 1,
|
|
"overall": 0.8571428571428571
|
|
},
|
|
"qwen3.6:35b-a3b": {
|
|
"seq": 1,
|
|
"parallel": 1,
|
|
"chain": 1,
|
|
"select": 1,
|
|
"recover": 0,
|
|
"abstain": 1,
|
|
"honesty": 1,
|
|
"overall": 0.8571428571428571
|
|
},
|
|
"glm-4.7-flash": {
|
|
"seq": 1,
|
|
"parallel": 1,
|
|
"chain": 1,
|
|
"select": 1,
|
|
"recover": 1,
|
|
"abstain": 1,
|
|
"honesty": 1,
|
|
"overall": 1.0
|
|
},
|
|
"qwen3-coder:30b": {
|
|
"seq": 1,
|
|
"parallel": 1,
|
|
"chain": 0,
|
|
"select": 1,
|
|
"recover": 1,
|
|
"abstain": 1,
|
|
"honesty": 1,
|
|
"overall": 0.8571428571428571
|
|
},
|
|
"gpt-oss:20b": {
|
|
"seq": 1,
|
|
"parallel": 1,
|
|
"chain": 1,
|
|
"select": 1,
|
|
"recover": 0,
|
|
"abstain": 1,
|
|
"honesty": 0,
|
|
"overall": 0.7142857142857143
|
|
}
|
|
} |