MiniMax · tested in Taskade Genesis
MiniMax M3 in Taskade
MiniMax M3 from MiniMax runs on every paid plan. We last tested it on Aug 25, 2026 in TSK-1, our app-building test.
- Status
- Available
- Plan
- Every paid plan
- Where to pick it
- More models or All Models
- Your own key
- Together AI
- Last test
- Context window
- 1Mtokens
- Max output
- 512Ktokens
- Released
- Where it runs
- 10services
Published scores
Benchmark scores that MiniMax and test sites published for MiniMax M3. Taskade did not re-run them. Lab-reported marks a score from MiniMax itself.
| Benchmark | Score | Source |
|---|---|---|
| SWE-Bench Verifiedresolved · Claude Code · MiniMaxLab-reported | 80.5% | MiniMaxLab-reported |
| SWE-Bench Proresolve rate · Claude Code · MiniMaxLab-reported | 59% | MiniMaxLab-reported |
| Terminal-Benchsuccess rate · v2.1 · MiniMaxLab-reported | 66% | MiniMaxLab-reported |
| OSWorld-Verifiedsuccess rate · MiniMaxLab-reported | 70.06% | MiniMaxLab-reported |
| BrowseCompaccuracy · MiniMaxLab-reported | 83.52% | MiniMaxLab-reported |
| MCP Atlassuccess rate · MiniMaxLab-reported | 74.2% | MiniMaxLab-reported |
LMArena scores
| Benchmark | Score | Source |
|---|---|---|
| Text arena±4 · 63,973 votes · Rank 96 of 416 · LMArena | 1,441 | LMArena |
| WebDev arena±6 · 19,670 votes · Rank 65 of 145 · LMArena | 1,482 | LMArena |
Scores from the LMArena leaderboard dataset (CC BY 4.0). People vote between two answers, and the votes set the score. Taskade picked the Overall category and the default setting of each model.
Scores collected by models.dev (MIT). Each source links the page that published the score.
Versions tested
Open a version to read its findings.
MiniMax M3Tested Aug 20262 findings
Not scored. Nearly half of its build actions failed, yet it reported the app as ready. We open and use every result before ranking it. A newer version can earn a fresh test.
Not scored: 47.2% of its build actions failed, and it reported the app as ready regardless of what its own record showed.
Its August build never opened, and the run ended without a closing message.
Model facts
The token limits are the most the model accepts. Taskade can run it with lower limits.
- Last updated
- Input types
- Text, Images, Video
- Output types
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- File attachments
- Yes
- Open weights
- Yes
Published specs from the model maker, via models.dev (MIT).
Run MiniMax M3 with your own key
Taskade runs it for you. You can also pick it with your own key in a custom agent.
| Key provider | Plan |
|---|---|
| Together AI | Business and up |
Where it runs
Services outside Taskade that serve MiniMax M3, from models.dev. Each link opens in a new tab. In Taskade, your own key works only through the key providers on this page.
How to choose MiniMax M3
- In the builder chat, open the model menu and choose More models. Then pick the model.
- In the agent editor, pick the model under All Models.
- If your model menu does not show the model, Taskade uses TSK-Auto instead.
Compare MiniMax
FAQ
Which Taskade plans include MiniMax M3?
MiniMax M3 runs in Taskade on every paid plan. If your model menu does not show it, Taskade uses TSK-Auto instead.
Has Taskade tested MiniMax M3?
Yes. We last tested MiniMax M3 on Aug 25, 2026 in the TSK-1 Benchmark. Not scored. Nearly half of its build actions failed, yet it reported the app as ready. We open and use every result before ranking it. A newer version can earn a fresh test.
How do I choose MiniMax M3 in Taskade?
In the builder chat, open the model menu and choose More models. Then pick MiniMax M3. In the agent editor, pick it under All Models.
Can I use my own API key for MiniMax M3?
Yes. In a custom agent, you can pick MiniMax M3 with your own key from Together AI (Business and up). Your provider bills the model use to your own account.
Who makes MiniMax M3?
MiniMax makes MiniMax M3. Taskade runs it on every paid plan, beside frontier models from other top AI labs.