Side by side

See the difference.

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

Scroll to compare models →

Comparison of MiniMax-M3, MiniMax: MiniMax-01, OpenAI: GPT-6.1 Sol
3 modelsMiniMaxAIMiniMax-M3Remove ×minimaxMiniMax: MiniMax-01Remove ×openaiOpenAI: GPT-6.1 SolRemove ×
What’s differentMiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per inference, and can handle a…Requires Responses API for tools; offers Ultrafast inference with US or EU data residency.
DateJun 2, 2026ListedJan 15, 2025ListedSep 29, 2026Released
Listed rate$0.28 in / $1.10 out/ 1M tokensdeepinfra · via Hugging Face · all routes ↗$0.20 in / $1.10 out/ 1M tokensMinimax · via OpenRouter · all routes ↗minimax$1.00 in / $5.00 out/ 1M tokensOpenAI · via OpenRouter · all routes ↗openai/flex · tier=flex · prompt ≤ 272000 tokens
Provider endpoints7 endpoints →2 endpoints →10 endpoints →
AA Intelligence ↗4.3.2Not reportedNot reported51.83 ↗Effort: max · MaxIndependent result
AA-Briefcase ↗1.1Not reportedNot reported1,557 ↗Effort: max · MaxIndependent result
GDPval-AA ↗2.1Not reportedNot reported1,593.85 ↗Effort: max · MaxIndependent result
AutomationBench-AA ↗AA Index 4.3.2 collectionNot reportedNot reported64.87% ↗Effort: max · MaxIndependent result
Terminal-Bench 4.0 · AA ↗Not reportedNot reported56.06% ↗Effort: max · MaxHarness unreportedIndependent result
SciCode ↗AA Index 4.3.2 collectionNot reportedNot reported54.17% ↗AA · Under reviewEffort: max · MaxIndependent result
Humanity’s Last Exam ↗AA Index 4.3.2 collectionNot reportedNot reported52.92% ↗Effort: max · MaxIndependent result
GDP.pdf ↗AA Index 4.3.2 collectionNot reportedNot reported31% ↗Effort: max · MaxIndependent result
CritPt ↗AA Index 4.3.2 collectionNot reportedNot reported31.71% ↗AA · Under reviewEffort: max · MaxIndependent result
AA-Omniscience ↗AA Index 4.3.2 collectionNot reportedNot reported41.53 ↗Effort: max · MaxIndependent result
AA-LCR ↗1.1Not reportedNot reported83% ↗Effort: max · MaxIndependent result
LiveBench ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported85.41% ↗Effort: max · single run · equal mean of 7 suitesIndependent result
LiveBench Design ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported82.1% ↗Effort: max · single runIndependent result
LiveBench Research ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported83.5% ↗Effort: max · single runIndependent result
LiveBench Browser Use ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported88% ↗Effort: max · single runIndependent result
LiveBench Coding ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported96% ↗Effort: max · single runIndependent result
LiveBench Agentic ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported73% ↗Effort: max · single runIndependent result
LiveBench Data Analysis ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported82.7% ↗Effort: max · single runIndependent result
LiveBench Reasoning ↗2.0 · 2026-10-14 (dataset 2026-09-02)Not reportedNot reported92.6% ↗Effort: max · single runIndependent result
Context window1M1M1.1M
Max output—900.2K128K
Parameters———
Tool callingSupportedNot reportedSupported
Structured outputSupportedNot reportedSupported
Image inputSupportedSupportedSupported
ReasoningNot reportedNot reportedSupported
Prompt cachingNot reportedNot reportedSupported
Open weightsSupportedSupportedNot reported

Add another model

Search all models →