Benchmarks

Measured against Claude Opus 5 on Anthropic first-party. Each task is a real omp session working in a pristine git workspace from a written spec; hidden tests are copied in only after the agent exits, so they cannot be read or edited. Every task is verified to fail an untouched workspace and to pass a reference solution. Both arms are metered from omp's own event stream under an identical tool surface. The router arm routes freely — nothing pinned.

Data generated 2026-08-29 · baseline claude-opus-5

Core suite — 10 coding tasks × 3 trials

auto-model-routerClaude Opus 5
Tasks solved30 / 3030 / 30
Total cost$0.63$16.61
Cost per solved task$0.0209$0.5538
Turns to finish278303
Tool calls265337
Wall clock2 057 s3 185 s
Median time to first token5 776 ms1 490 ms

Both engines solved everything, so this measures cost at equal correctness. 26.5× cheaper — in fewer turns, fewer tool calls, and 19 minutes less wall clock. The one regression is time to first token: a routed turn pays for classification and dispatch before anything streams.

Difficulty ladder — 7 rungs, run twice

auto-model-routerClaude Opus 5
Run 15 / 7 · $0.305 / 7 · $6.25
Run 25 / 7 · $0.466 / 7 · $6.60

A second suite of deliberately escalating difficulty, ending in npm semver range semantics and a minimal diff with a specified tie-break. At the top of the ladder the engines separate.

What it routed to

ModelTurnsInput priceRole
z-ai/glm-5.3-flash389 (84%)$0.07 / MTokdefault
google/gemini-3.7-flash56 (12%)$0.75 / MTokescalation target
x-ai/grok-4.618 (4%)$2.00 / MTokescalation target

Across 464 routed turns in all five runs. Tier escalation converts to a costlier model roughly one-for-one; the escalation target is chosen live from trust and latency history, so it differs between runs on the same catalog.

Real-world — a week on the live ledger

auto-model-routerClaude Opus 5 (single-model)
Spend over the week$61.69$921.20
Per turn$0.0089$0.133
Extrapolated / month$263$3 932

6 918 billed turns across 299 conversations, 7 days, 410:1 input-to-output, 68% cache hit — the identical token stream repriced against a single Opus 5 model with its own cache namespace. ≈15× cheaper, ~93% saved: a four-figure monthly bill becomes a three-figure one.

Live ledger snapshot

No live ledger snapshot is bundled with this build. Maintainers regenerate one with bun tools/export-benchmarks.ts against a real install before a release.

Scope & honesty

These are small, self-contained tasks of one to three files. On the core suite both engines solved everything, so it measures cost at equal correctness rather than capability; the ladder is where capability separates. The cost multiple varied between 14× and 32× across runs depending on which task the baseline stalled on — treat "well over an order of magnitude" as the claim, not a specific figure. Full harness, tasks, and raw per-turn data are in docs/routing-benchmark-findings.md.