Side by side

See the difference.

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

Scroll to compare models →

Comparison of seed-2.0-code, Google: Gemini 4 Argon, remove_background_guided
3 modelsUnknownseed-2.0-codeRemove ×googleGoogle: Gemini 4 ArgonRemove ×Briaremove_background_guidedRemove ×
What’s different262.1K context · 131.1K max output · Tool calling · Structured outputLong decode can use the unified 1M-token budget for output; reads video, audio and PDFs, with implicit-only caching.Prompt-guided background removal by Bria: tell it what to keep or what to remove and get a clean cutout with true transparency, at the original resolution with the original pixels untouched. Trained…
DateOct 16, 2026DiscoveredSep 30, 2026ReleasedOct 14, 2026Listed
Listed rate$0.50 in / $3.00 out/ 1M tokensExperiential · all routes ↗Standard · fewer than 128,001 input tokens$1.00 in / $5.00 out/ 1M tokensGoogle AI Studio · via OpenRouter · all routes ↗google-ai-studio/flex · tier=flexSee provider quotes
Provider endpoints1 endpoint →8 endpoints →0 endpoints →
AA Intelligence ↗4.3.2Not reported52.56 ↗Effort: high · HighIndependent resultNot reported
AA-Briefcase ↗1.1Not reported1,486.44 ↗Effort: high · HighIndependent resultNot reported
GDPval-AA ↗2.1Not reported1,623.99 ↗Effort: high · HighIndependent resultNot reported
AutomationBench-AA ↗AA Index 4.3.2 collectionNot reported77.51% ↗Effort: high · HighIndependent resultNot reported
Terminal-Bench 4.0 · AA ↗Not reported57.07% ↗Effort: high · HighHarness unreportedIndependent resultNot reported
SciCode ↗AA Index 4.3.2 collectionNot reported61.81% ↗AA · Under reviewEffort: high · HighIndependent resultNot reported
Humanity’s Last Exam ↗AA Index 4.3.2 collectionNot reported57.09% ↗Effort: high · HighIndependent resultNot reported
GDP.pdf ↗AA Index 4.3.2 collectionNot reported21.8% ↗Effort: high · HighIndependent resultNot reported
CritPt ↗AA Index 4.3.2 collectionNot reported27.14% ↗AA · Under reviewEffort: high · HighIndependent resultNot reported
AA-Omniscience ↗AA Index 4.3.2 collectionNot reported42.35 ↗Effort: high · HighIndependent resultNot reported
AA-LCR ↗1.1Not reported79.67% ↗Effort: high · HighIndependent resultNot reported
LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported84.1% ↗Effort: high · single run · equal mean of 7 suitesIndependent resultNot reported
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported73.7% ↗Effort: high · single runIndependent resultNot reported
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported83.1% ↗Effort: high · single runIndependent resultNot reported
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported92% ↗Effort: high · single runIndependent resultNot reported
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported89.7% ↗Effort: high · single runIndependent resultNot reported
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported69.9% ↗Effort: high · single runIndependent resultNot reported
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported85.2% ↗Effort: high · single runIndependent resultNot reported
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reported95.1% ↗Effort: high · single runIndependent resultNot reported
Context window262.1K1M—
Max output131.1K65.5K—
Parameters———
Tool callingSupportedSupportedNot reported
Structured outputSupportedSupportedNot reported
Image inputNot reportedSupportedNot reported
Audio inputNot reportedSupportedNot reported
Video inputNot reportedSupportedNot reported
ReasoningSupportedSupportedNot reported
Prompt cachingNot reportedSupportedNot reported

Add another model

Search all models →