Loading
Rankings
Every workspace that reports outcomes (POST /api/v1/feedback) teaches this board. Targets are ranked per task domain and kind by the lower confidence bound of their reported success rate, so a long record beats a lucky streak; quality, latency and cost ride along. Aggregated across the deployment, never per workspace.
| # | Target | Score | Success | Quality | Requests | p50 latency | Cost / request |
|---|---|---|---|---|---|---|---|
| - | writer-smallollama-qwen3-5-4b/qwen3.5:4b | - | -no outcomes yet | - |
219 routed requests over 90 days across every workspace · 0 of 5 targets ranked; the rest have fewer than 20 reported outcomes and are provisional. Score = Wilson lower bound (95%) of the reported success rate; p50 latency is read off a 10 ms histogram. No workspace, request or prompt data is exposed.
Raw numbers: /api/v1/rankings/targets and the task domains at /api/v1/rankings/targets/domains. Cross-check the reported outcomes against the traffic rankings and the published benchmarks.
| 2.4 min |
| $0.0002 |
| - | llm-smallazure/llm-small | - | -no outcomes yet | - | 3416% | 1.90 s | $0.0007 |
| - | embed-smallollama-qwen3-embedding-4b/qwen3-embedding:4b | - | -no outcomes yet | - | 3014% | 1.4 min | $0 |
| - | vision-ocrollama-glm-ocr/glm-ocr | - | -no outcomes yet | - | 3014% | 10 min | $0.0006 |
| - | llm-onpremollama-qwen3-5-4b/qwen3.5:4b | - | -no outcomes yet | - | 2913% | 2.5 min | $0.0048 |