Side by side

See the difference.

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

Scroll to compare models →

Comparison of multilingual-e5-large-instruct, Pixelcut Looping Video, Step-5-Preview
3 modelsintfloatmultilingual-e5-large-instructRemove ×pixelcutPixelcut Looping VideoRemove ×stepfun-aiStep-5-PreviewRemove ×
What’s differentThe Multilingual-E5 models, initialized from XLM-RoBERTa, support up to 512 tokens per input — any longer text will be silently truncated. To ensure optimal performance, always prefix inputs with “query:”…Turns one product photo into a loop that ends on its starting frame, with a locked camera and subtle motion or a full spin.600B total and 27B active parameters; accepts images and video, with FP8 and BF16 weights for deployment.
DateApr 17, 2025ListedSep 29, 2026ListedSep 18, 2026Released
Listed rateSee provider quotesSee provider quotes$1.00 in / $2.70 out/ 1M tokensDeepInfra · all routes ↗
Provider endpoints0 endpoints →0 endpoints →6 endpoints →
AA Intelligence ↗4.3.2Not reportedNot reported43.73 ↗Effort not specifiedIndependent result
AA-Briefcase ↗1.1Not reportedNot reported1,424.32 ↗Effort not specifiedIndependent result
GDPval-AA ↗2.1Not reportedNot reported1,586.63 ↗Effort not specifiedIndependent result
AutomationBench-AA ↗AA Index 4.3.2 collectionNot reportedNot reported50.96% ↗Effort not specifiedIndependent result
Terminal-Bench 4.0 · AA ↗Not reportedNot reported33.33% ↗Effort not specifiedHarness unreportedIndependent result
SciCode ↗AA Index 4.3.2 collectionNot reportedNot reported58.91% ↗AA · Under reviewEffort not specifiedIndependent result
Humanity’s Last Exam ↗AA Index 4.3.2 collectionNot reportedNot reported46.48% ↗Effort not specifiedIndependent result
GDP.pdf ↗AA Index 4.3.2 collectionNot reportedNot reported14.8% ↗Effort not specifiedIndependent result
CritPt ↗AA Index 4.3.2 collectionNot reportedNot reported20.86% ↗AA · Under reviewEffort not specifiedIndependent result
AA-Omniscience ↗AA Index 4.3.2 collectionNot reportedNot reported16.38 ↗Effort not specifiedIndependent result
AA-LCR ↗1.1Not reportedNot reported88.33% ↗Effort not specifiedIndependent result
LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported62.01% ↗Effort: max · single run · equal mean of 7 suitesIndependent result
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported76.9% ↗Effort: max · single runIndependent result
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported72.8% ↗Effort: max · single runIndependent result
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported24% ↗Effort: max · single runIndependent result
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported85.6% ↗Effort: max · single runIndependent result
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported27.5% ↗Effort: max · single runIndependent result
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported63.5% ↗Effort: max · single runIndependent result
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported83.8% ↗Effort: max · single runIndependent result
Context window512—1M
Max output——64K
Parameters———
Tool callingNot reportedNot reportedSupported
Structured outputNot reportedNot reportedSupported
Image inputNot reportedNot reportedSupported
Video inputNot reportedNot reportedSupported
ReasoningNot reportedNot reportedSupported
Prompt cachingNot reportedNot reportedSupported
Open weightsNot reportedNot reportedSupported

Add another model

Search all models →