Corrected replay + historical run · 2026-09-12

One hundred searches.
Every miss counted.

The original responses stay frozen. The current Fast-to-Standard consistency rule is replayed over them, so the corrected metrics are traceable without inventing a new benchmark run.

finished 20:57:42Z22 factual78 navigation24 source scopes26 hosts500 first attempts
80.01Standard replay quality
79.37Fast frozen-run quality
91%Standard replay Hit@10 · Fast 88%
0manual score changes

Corrected fixed-mode replay

The frozen Fast prefix is preserved, unique frozen Standard results are appended to ten, and the original scoring formula is applied unchanged. No provider was called again.

Orbita modeQualityHit@1Hit@5Hit@10MRRnDCG@10Status
Standard80.0165%88%91%0.73630.7789deterministic replay
Fast79.3765%88%88%0.73170.7686unchanged frozen result

Boundary. These are corrected rank metrics from stored responses, not a new live run. Latency was not replayed and remains historical until the next frozen benchmark.

Historical leaderboard

The original values are retained rather than rewritten after the product correction. Composite rank is diagnostic here—not a promise that Fast is the stronger mode.

Provider / modeQualityHit@1Hit@5Hit@10Hit@10 95% CIMRRnDCG@10p50p95Errors
Orbita Fast79.3765%88%88%80.19–93.00%0.73170.7686836 ms*5,672 ms*0
Orbita Standard76.0661%81%88%80.19–93.00%0.69900.74275,394 ms*16,746 ms*0
Exa Fast68.2362%67%67%57.31–75.44%0.64000.6476624 ms970 ms0
Linkup Standard52.9238%52%61%51.20–69.98%0.44980.48771,327 ms2,312 ms0
Tavily Basic35.9718%37%40%30.94–49.80%0.25740.29232,065 ms4,402 ms0

Mode consistency. This run exposed a regression where a broader fixed mode could reorder a strong Fast result downward. That behavior has been corrected; fresh rank and latency numbers require a new frozen run. External and Orbita timings here are not directly comparable.

By query stratum

The factual subset is harder and smaller. The navigation subset asks for an official page by title, so it should not be read as open-ended research quality.

Provider / modeFactual qualityFactual Hit@10Navigation qualityNavigation Hit@10
Orbita Fast75.8277.27%80.3791.03%
Orbita Standard75.0081.82%76.3689.74%
Exa Fast59.4559.09%70.7069.23%
Linkup Standard24.4136.36%60.9767.95%
Tavily Basic33.5536.36%36.6541.03%

Method

Every target URL was fixed and confirmed before execution. The corpus size, storage layout and internal index statistics are intentionally not public.

Quality formula

Hit@1 25% + Hit@5 20% + Hit@10 15% + MRR 20% + nDCG@10 10% + successful delivery 10%.

Exact modes

Orbita Fast 20→5; Orbita Standard 100→10; Exa Fast; Tavily Basic; Linkup Standard. No failed request was retried.

What this does not prove

These limits stay beside the result so a benchmark cannot quietly become a larger marketing claim.