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, ByteDance Seed: Seedream 5.0 Pro, Google: Gemini 4 Argon
3 modelsByteDanceSeed-2.0-codeRemove ×bytedance-seedByteDance Seed: Seedream 5.0 ProRemove ×googleGoogle: Gemini 4 ArgonRemove ×
What’s differentA coding model optimized for real-world development environments, with reliable tool use in common IDEs such as Claude Code. It delivers strong front-end performance and supports Skills.Choose standard or fast prompt enhancement; accepts extreme aspect ratios up to 16:1 within a 2K-square pixel budget.Long decode can use the unified 1M-token budget for output; reads video, audio and PDFs, with implicit-only caching.
DateApr 29, 2026ListedJul 8, 2026ReleasedSep 30, 2026Released
Listed rate$0.50 in / $3.00 out/ 1M tokensDeepInfra · all routes ↗$0.0675/ imagefal · all routes ↗Area ≤ 1536x1536 pixels$1.00 in / $5.00 out/ 1M tokensGoogle AI Studio · via OpenRouter · all routes ↗google-ai-studio/flex · tier=flex
Provider endpoints1 endpoint →2 endpoints →8 endpoints →
AA Intelligence ↗4.3.2Not reportedNot reported52.56 ↗Effort: high · HighIndependent result
AA-Briefcase ↗1.1Not reportedNot reported1,486.44 ↗Effort: high · HighIndependent result
GDPval-AA ↗2.1Not reportedNot reported1,623.99 ↗Effort: high · HighIndependent result
AutomationBench-AA ↗AA Index 4.3.2 collectionNot reportedNot reported77.51% ↗Effort: high · HighIndependent result
Terminal-Bench 4.0 · AA ↗Not reportedNot reported57.07% ↗Effort: high · HighHarness unreportedIndependent result
SciCode ↗AA Index 4.3.2 collectionNot reportedNot reported61.81% ↗AA · Under reviewEffort: high · HighIndependent result
Humanity’s Last Exam ↗AA Index 4.3.2 collectionNot reportedNot reported57.09% ↗Effort: high · HighIndependent result
GDP.pdf ↗AA Index 4.3.2 collectionNot reportedNot reported21.8% ↗Effort: high · HighIndependent result
CritPt ↗AA Index 4.3.2 collectionNot reportedNot reported27.14% ↗AA · Under reviewEffort: high · HighIndependent result
AA-Omniscience ↗AA Index 4.3.2 collectionNot reportedNot reported42.35 ↗Effort: high · HighIndependent result
AA-LCR ↗1.1Not reportedNot reported79.67% ↗Effort: high · HighIndependent result
LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported84.1% ↗Effort: high · single run · equal mean of 7 suitesIndependent result
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported73.7% ↗Effort: high · single runIndependent result
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported83.1% ↗Effort: high · single runIndependent result
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported92% ↗Effort: high · single runIndependent result
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported89.7% ↗Effort: high · single runIndependent result
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported69.9% ↗Effort: high · single runIndependent result
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported85.2% ↗Effort: high · single runIndependent result
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported95.1% ↗Effort: high · single runIndependent result
AA Image ↗2.1Not reported1,100.01 ↗Text-to-image · all categoriesIndependent result95% CI 1,089.01–1,111.01 · n=11,391Not reported
Context window256K—1M
Max output——65.5K
Parameters———
Tool callingNot reportedNot reportedSupported
Structured outputNot reportedNot reportedSupported
Image inputNot reportedSupportedSupported
Audio inputNot reportedNot reportedSupported
Video inputNot reportedNot reportedSupported
ReasoningNot reportedNot reportedSupported
Prompt cachingNot reportedNot reportedSupported

Add another model

Search all models →