Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of NVIDIA: Switchyard, Hi3D 3D Part Splitter, Anthropic: Claude Sonnet 5.5
3 modelsnvidiaNVIDIA: SwitchyardRemove ×hitem3dHi3D 3D Part SplitterRemove ×anthropicAnthropic: Claude Sonnet 5.5Remove ×
What’s differentSwitchyard is an open-source model router that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most popular...Split a 3D model into parts with Hi3D.Tuned for quick iteration on scoped fixes and documents; Anthropic favors Opus 5.5 for open-ended work needing sustained judgment.
DateSep 21, 2026ListedJul 31, 2026ListedSep 28, 2026Released
Listed rateSee provider quotes$0.40/ generationfal · all routes ↗$2.00 in / $10.00 out/ 1M tokensAmazon Bedrock · via OpenRouter · all routes ↗amazon-bedrock
Provider endpoints1 endpoint →1 endpoint →11 endpoints →
AA Intelligence ↗4.3.2Not reportedNot reported56 ↗Effort: max · Max, Default FallbackIndependent result
AA-Briefcase ↗1.1Not reportedNot reported1,817.26 ↗Effort: max · Max, Default FallbackIndependent result
GDPval-AA ↗2.1Not reportedNot reported1,837.82 ↗Effort: max · Max, Default FallbackIndependent result
AutomationBench-AA ↗AA Index 4.3.2 collectionNot reportedNot reported71.77% ↗Effort: max · Max, Default FallbackIndependent result
Terminal-Bench 4.0 · AA ↗Not reportedNot reported63.64% ↗Effort: max · Max, Default FallbackHarness unreportedIndependent result
SciCode ↗AA Index 4.3.2 collectionNot reportedNot reported61% ↗AA · Under reviewEffort: max · Max, Default FallbackIndependent result
Humanity’s Last Exam ↗AA Index 4.3.2 collectionNot reportedNot reported54.96% ↗Effort: max · Max, Default FallbackIndependent result
GDP.pdf ↗AA Index 4.3.2 collectionNot reportedNot reported25.8% ↗Effort: max · Max, Default FallbackIndependent result
CritPt ↗AA Index 4.3.2 collectionNot reportedNot reported31.43% ↗AA · Under reviewEffort: max · Max, Default FallbackIndependent result
AA-Omniscience ↗AA Index 4.3.2 collectionNot reportedNot reported32.3 ↗Effort: max · Max, Default FallbackIndependent result
AA-LCR ↗1.1Not reportedNot reported82.67% ↗Effort: max · Max, Default FallbackIndependent result
LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported82.46% ↗Effort: max · single run · equal mean of 7 suitesIndependent result
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported85% ↗Effort: max · single runIndependent result
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported83.6% ↗Effort: max · single runIndependent result
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported84% ↗Effort: max · single runIndependent result
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported94.7% ↗Effort: max · single runIndependent result
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported78.8% ↗Effort: max · single runIndependent result
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported59.5% ↗Effort: max · single runIndependent result
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported91.6% ↗Effort: max · single runIndependent result
Context window1M—1M
Max output——128K
Parameters———
Tool callingNot reportedNot reportedSupported
Structured outputNot reportedNot reportedSupported
Image inputNot reportedNot reportedSupported
ReasoningNot reportedNot reportedSupported
Prompt cachingNot reportedNot reportedSupported

Add another model

Search all models →