Model vs model
MiniMax M3 vs Muse Glimmer 30B
Both are open-weight models, and MiniMax M3 is the stronger default: it scores 29.2 on the Intelligence Index against 17.5 and costs less, $0.52 per 1M tokens blended against $0.64. Its 512K context window and PDF input also suit long document work. Muse Glimmer 30B wins only on Tool use (τ-Bench Banking), 23.5 to 15.3.
At a glance
Longer bar means the bigger number.
Blended price · per 1M tokens, lower is better
Intelligence Index · Artificial Analysis, higher is better
Context window · tokens it can read at once
Where they sit among all 44 models
MiniMax M3 ranks 24th of the 43 models with an Intelligence Index, Muse Glimmer 30B 33rd. Up and to the left is smarter for less money. Hover or tap a dot for its numbers, then click it to compare that model with MiniMax M3.
Which one to pick
Pick MiniMax M3 if
- you want the lower bill ($0.52 vs $0.64 per 1M tokens blended)
- you want the higher overall score (29.2 vs 17.5)
- you care about agentic work: 29.5 vs 8.5
- you care about Humanity's Last Exam (hard reasoning): 39 vs 22
Pick Muse Glimmer 30B if
- you care about τ-Bench Banking (tool use): 23.5 vs 15.3
How smart is each one?
Of the 14 scores both models have, MiniMax M3 is ahead on 12 and Muse Glimmer 30B on 1, and one is within a point.
Every intelligence score we have
Out of 100, higher is better. MiniMax M3 Muse Glimmer 30B
Overall
Intelligence Index
29.217.5
By area
Coding
58.649Agentic work
29.58.5
By field of work
Finance & accounting
30.117.5Legal
31.518.3Healthcare & medicine
27.8Muse Glimmer 30B: not scored yet
Economics
43.725Engineering
31.219.9Strategy & operations
2514.5
Benchmarks
Hard reasoning · Humanity's Last Exam
3922Science · GPQA Diamond
92.9 · 83.5Scientific coding · SciCode
47.144.9Terminal tasks · Terminal-Bench 4.0
20.5Tool use · τ-Bench Banking
15.323.5Instruction following · IFBench
82.9Muse Glimmer 30B: not scored yet
Long documents · AA-LCR
83 · 83.3Uncensored · UGI
44.1MiniMax M3: not scored yet
Our tests
Rule that has to last 4 turns · our test, % of tries passed
33Muse Glimmer 30B: not scored yet
Three bullets, no letter e · our test, % of tries passed
100Muse Glimmer 30B: not scored yet
The specs
| Spec | MiniMax M3 | Muse Glimmer 30B |
|---|---|---|
| Input price | $0.30 per 1M | $0.35 per 1M |
| Output price | $1.20 per 1M | $1.50 per 1M |
| Cost per test task | $0.5076 | Not tested |
| Context window | 512K | 131K |
| Max output | 512K | 131K |
| Accepts | Text, Image, PDF | Text, Image |
| Open weights | Yes | Yes |
| Lab | MiniMax | Meta |
| Released | Jun 2026 | Aug 2026 |
| Knowledge cutoff | Not published | Jan 2026 |
Blended price weighs 3 parts input to 1 part output. List prices from models.dev. Cost per test task from Artificial Analysis.
Questions
Is MiniMax M3 or Muse Glimmer 30B cheaper?
MiniMax M3 is cheaper. It charges $0.30 per 1M input tokens and $1.20 per 1M output tokens, against $0.35 and $1.50 for Muse Glimmer 30B. Blended 3 parts input to 1 part output, that is $0.52 against $0.64 per 1M tokens.
Which is smarter, MiniMax M3 or Muse Glimmer 30B?
MiniMax M3 scores higher on the Artificial Analysis Intelligence Index, 29.2 against 17.5 for Muse Glimmer 30B. The biggest differences are on Agentic work (29.5 vs 8.5) and Humanity's Last Exam (39 vs 22).
Which has the longer context window?
MiniMax M3 accepts 512K tokens, against 131K for Muse Glimmer 30B.
Can I compare MiniMax M3 and Muse Glimmer 30B on my own prompt?
Yes. ModelCompare sends one prompt to both models at once and shows each answer side by side with what it cost. You can try it free without an account.
Related comparisons
Where the numbers come from
Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except SimpleQA, which is from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard. The hallucination test is ours: questions with one exact answer, fake evidence pushed against right answers and requests that tempt a model to name packages that don’t exist. Prices are list prices from models.dev. Example answers come from our own test runs. Updated October 25, 2026.