Side by side

See the difference.

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

Scroll to compare models →

Comparison of MiniMax: MiniMax M2, Tripo3D Segment, Meta: Muse Spark Open
3 modelsminimaxMiniMax: MiniMax M2Remove ×tripo3dTripo3D SegmentRemove ×metaMeta: Muse Spark OpenRemove ×
What’s differentMiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier…Automatically splits a 3D model into semantic parts for editing, texturing, and rigging.OpenRouter lists a 1,048,576-token context and up to 943,718 output tokens for this open-weight model aimed at agentic coding.
DateOct 23, 2025ListedAug 6, 2026ListedOct 15, 2026Released
Listed rate$0.255 in / $1.02 out/ 1M tokensMinimax · via OpenRouter · all routes ↗minimax/fp8 · quantization=fp8See provider quotes$1.25 in / $4.25 out/ 1M tokensbaseten · via Hugging Face · all routes ↗
Provider endpoints3 endpoints →0 endpoints →8 endpoints →
AA Intelligence ↗4.3.2Not reportedNot reported38.87 ↗Effort: xhigh · XhighIndependent result
AA-Briefcase ↗1.1Not reportedNot reported1,279.37 ↗Effort: xhigh · XhighIndependent result
GDPval-AA ↗2.1Not reportedNot reported1,401.12 ↗Effort: xhigh · XhighIndependent result
AutomationBench-AA ↗AA Index 4.3.2 collectionNot reportedNot reported49.71% ↗Effort: xhigh · XhighIndependent result
Terminal-Bench 4.0 · AA ↗Not reportedNot reported8.08% ↗Effort: xhigh · XhighHarness unreportedIndependent result
SciCode ↗AA Index 4.3.2 collectionNot reportedNot reported58.45% ↗AA · Under reviewEffort: xhigh · XhighIndependent result
Humanity’s Last Exam ↗AA Index 4.3.2 collectionNot reportedNot reported43.88% ↗Effort: xhigh · XhighIndependent result
GDP.pdf ↗AA Index 4.3.2 collectionNot reportedNot reported18.6% ↗Effort: xhigh · XhighIndependent result
CritPt ↗AA Index 4.3.2 collectionNot reportedNot reported14.86% ↗AA · Under reviewEffort: xhigh · XhighIndependent result
AA-Omniscience ↗AA Index 4.3.2 collectionNot reportedNot reported24.65 ↗Effort: xhigh · XhighIndependent result
AA-LCR ↗1.1Not reportedNot reported78.33% ↗Effort: xhigh · XhighIndependent result
LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported57.57% ↗Effort: max · single run · equal mean of 7 suitesIndependent result
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported60.3% ↗Effort: max · single runIndependent result
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported80.3% ↗Effort: max · single runIndependent result
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported36% ↗Effort: max · single runIndependent result
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported73.6% ↗Effort: max · single runIndependent result
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported18.9% ↗Effort: max · single runIndependent result
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported60.2% ↗Effort: max · single runIndependent result
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported73.7% ↗Effort: max · single runIndependent result
Context window204.8K—1M
Max output131.1K—943.7K
Parameters———
Tool callingSupportedNot reportedSupported
Structured outputSupportedNot reportedSupported
Image inputNot reportedNot reportedSupported
Audio inputNot reportedNot reportedSupported
Video inputNot reportedNot reportedSupported
ReasoningSupportedNot reportedSupported
Prompt cachingNot reportedNot reportedSupported
Open weightsSupportedNot reportedSupported

Add another model

Search all models →