GLM 4.6 vs MiniMax M2.1
MiniMax M2.1 leads GLM 4.6 on the Artificial Analysis Intelligence Index, 20.9 to 18.5, and MiniMax M2.1 costs 1.8x less per output token ($1.20 vs $2.20 per million). Updated October 22, 2026; 29 benchmarks have a result for both.
GLM 4.6 or MiniMax M2.1: which to pick
Only GLM 4.6 has a coding score, 8.8 on the Vibe Coding Index; MiniMax M2.1 has none, so the two cannot be ranked on coding.
Pick MiniMax M2.1 for output tokens 1.8x cheaper ($1.20 vs $2.20 per million) and work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 29
- GLM 4.6 only
- 40
- MiniMax M2.1 only
- 5
- Like-for-like categories
- 8 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Only GLM 4.6 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M2.1
MiniMax M2.1 leads, 20.9 against 18.5.
Same board, both measured
Reasoning
GPQA Diamond
MiniMax M2.1
MiniMax M2.1 leads, 78.5% against 74.5%.
Same board, both measured
Math
AIME
GLM 4.6
GLM 4.6 leads, 92.7% against 77.9%.
Same board, both measured
Knowledge
MMLU Pro
MiniMax M2.1
MiniMax M2.1 leads, 87.0% against 82.2%.
Same board, both measured
Web design
Design Arena: websites
MiniMax M2.1
MiniMax M2.1 leads, 1201 against 1174.
Same board, both measured
Long documents
Listed context window
No call
Both take 205K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.1
GLM 4.6 $0.0017, MiniMax M2.1 $0.0009 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.1 has the number, $0.59.
Directional only
At a glance
- Coding index
- GLM 4.6 8.8 from 2 benchmarks, MiniMax M2.1 not benchmarked.
- Widest category
- General, 20.1 points apart on average over 2 shared benchmarks.
- Widest single gap
- IFBench: GLM 4.6 43.4% against MiniMax M2.1 69.9%, 26.5 points apart on a 0 to 100 scale.
- Output price
- GLM 4.6 $2.20 against MiniMax M2.1 $1.20 per million output tokens, 1.8x apart.
- Context window
- Both take 205K tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GLM 4.6 | Bars | MiniMax M2.1 | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | 1 tie | |
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 3 | ||
| Math | 4 | 0 | ||
| Knowledge | 2 | 4 | ||
| Web design | 1 | 6 | ||
| General | 0 | 2 | ||
| All shared boards | 7 | 21 | 1 tie |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| SWE-bench Verified | 68.2% | Not measured | Only GLM 4.6 measured |
| LMArena WebDev | 1341 | Not measured | Only GLM 4.6 measured |
| AA Coding Index | 45.8 | Not measured | Only GLM 4.6 measured |
| LiveCodeBench (Vals AI) | 81.0% | 81.8% | MiniMax M2.1 |
| SWE-bench Verified (Vals AI) | Not measured | 74.8% | Only MiniMax M2.1 measured |
| Vibe Code Bench (Vals AI) | 3.1% | Not measured | Only GLM 4.6 measured |
| LiveCodeBench (Artificial Analysis run) | 69.5% | 81.0% | MiniMax M2.1 |
| Terminal-Bench Hard (Artificial Analysis run) | 28.8% | 28.8% | Tie |
| Terminal-Bench | 24.5% | 36.6% | MiniMax M2.1 |
| ALE-Bench | 340.8 | 623.8 | MiniMax M2.1 |
| LMArena Text: coding | 1449 | Not measured | Only GLM 4.6 measured |
| LMArena Text: software and IT | 1455 | Not measured | Only GLM 4.6 measured |
| LMArena WebDev: HTML | 1350 | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| AA Intelligence Index | 18.5 | 20.9 | MiniMax M2.1 |
| Neither model has a result on the other 1 board here | |||
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| Design Arena: agents building full-stack apps | 1029 | Not measured | Only GLM 4.6 measured |
| Design Arena: agents building mobile apps | 1096 | Not measured | Only GLM 4.6 measured |
| Design Arena: agents building Android apps | 1084 | Not measured | Only GLM 4.6 measured |
| Design Arena: agents building Godot games | 1180 | Not measured | Only GLM 4.6 measured |
| τ²-Bench Telecom | 76.9% | 85.4% | MiniMax M2.1 |
| Berkeley Function Calling Leaderboard (BFCL) | 72.4% | Not measured | Only GLM 4.6 measured |
| BrowseComp-Plus | 48.2% | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| GPQA Diamond | 74.5% | 78.5% | MiniMax M2.1 |
| GPQA Diamond (Artificial Analysis run) | 78.0% | 83.0% | MiniMax M2.1 |
| Humanity's Last Exam (Artificial Analysis run) | 14.5% | 23.2% | MiniMax M2.1 |
| LMArena Text: hard prompts | 1440 | Not measured | Only GLM 4.6 measured |
| LMArena Text: expert | 1432 | Not measured | Only GLM 4.6 measured |
| LMArena Text: hard prompts in English | 1445 | Not measured | Only GLM 4.6 measured |
| Kagi LLM Benchmark | 45.7% | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| AIME | 92.7% | 77.9% | GLM 4.6 |
| MATH 500 (Vals AI) | Not measured | 89.0% | Only MiniMax M2.1 measured |
| MGSM (Vals AI) | 89.8% | 87.8% | GLM 4.6 |
| AA Math Index | 86.0 | 82.7 | GLM 4.6 |
| AIME 2025 (Artificial Analysis run) | 86.0% | 82.7% | GLM 4.6 |
| LMArena Text: math | 1432 | Not measured | Only GLM 4.6 measured |
| LMArena Text: mathematical work | 1447 | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| MMLU Pro | 82.2% | 87.0% | MiniMax M2.1 |
| LegalBench (Vals AI) | 79.6% | 75.5% | GLM 4.6 |
| CaseLaw (Vals AI) | Not measured | 55.8% | Only MiniMax M2.1 measured |
| CorpFin (Vals AI) | 56.8% | 58.9% | MiniMax M2.1 |
| TaxEval (Vals AI) | 66.2% | 66.3% | MiniMax M2.1 |
| MedQA (Vals AI) | 92.2% | 91.2% | GLM 4.6 |
| MedCode (Vals AI) | Not measured | 34.1% | Only MiniMax M2.1 measured |
| MMLU Pro (Artificial Analysis run) | 82.9% | 87.5% | MiniMax M2.1 |
| LMArena Text: science | 1456 | Not measured | Only GLM 4.6 measured |
| LMArena Text: medicine and healthcare | 1455 | Not measured | Only GLM 4.6 measured |
| LMArena Text: legal and government | 1448 | Not measured | Only GLM 4.6 measured |
| LMArena Text: business and finance | 1416 | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 6 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index16
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| Design Arena: websites | 1174 | 1201 | MiniMax M2.1 |
| Design Arena: UI components | 1145 | 1220 | MiniMax M2.1 |
| Design Arena: game dev | 1150 | 1134 | GLM 4.6 |
| Design Arena: data viz | 1161 | 1206 | MiniMax M2.1 |
| Design Arena: 3D | 1128 | 1164 | MiniMax M2.1 |
| Design Arena: all code categories | 1165 | 1190 | MiniMax M2.1 |
| Design Arena: SVG | 1108 | 1131 | MiniMax M2.1 |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 80.8% | Only MiniMax M2.1 measured |
| IFBench | 43.4% | 69.9% | MiniMax M2.1 |
| Long context reasoning (AA-LCR) | 54.0% | 67.7% | MiniMax M2.1 |
| LMArena Text | 1440 | Not measured | Only GLM 4.6 measured |
| LMArena Text: instruction following | 1410 | Not measured | Only GLM 4.6 measured |
| LMArena Text: creative writing | 1412 | Not measured | Only GLM 4.6 measured |
| LMArena Text: English | 1449 | Not measured | Only GLM 4.6 measured |
| LMArena Text: non-English | 1426 | Not measured | Only GLM 4.6 measured |
| LMArena Text: Chinese | 1499 | Not measured | Only GLM 4.6 measured |
| LMArena Text: German | 1447 | Not measured | Only GLM 4.6 measured |
| LMArena Text: Japanese | 1393 | Not measured | Only GLM 4.6 measured |
| LMArena Text: Korean | 1400 | Not measured | Only GLM 4.6 measured |
| LMArena Text: French | 1459 | Not measured | Only GLM 4.6 measured |
| LMArena Text: Spanish | 1436 | Not measured | Only GLM 4.6 measured |
| LMArena Text: Russian | 1418 | Not measured | Only GLM 4.6 measured |
| LMArena Text: Polish | 1447 | Not measured | Only GLM 4.6 measured |
| LMArena Text: multi-turn | 1427 | Not measured | Only GLM 4.6 measured |
| LMArena Text: longer queries | 1422 | Not measured | Only GLM 4.6 measured |
| LMArena Text: writing and language | 1415 | Not measured | Only GLM 4.6 measured |
| LMArena Text: entertainment and media | 1409 | Not measured | Only GLM 4.6 measured |
| Neither model has a result on the other 26 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GLM 4.6 | MiniMax M2.1 | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
MiniMax M2.1 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.1 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.1 costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | Z.ai GLM 4.6 | MiniMax M2.1 |
|---|---|---|
| Maker | Z.ai | MiniMax |
| Weights | Open weights | Open weights |
| Released | September 30, 2025 | December 23, 2025 |
| Context window | 205K | 205K |
| Input $/Mtok | $0.60 | $0.30 |
| Output $/Mtok | $2.20 | $1.20 |
| Coding index | 8.8 | Not benchmarked |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | Not computable | $0.59 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GLM 4.6 better than MiniMax M2.1 for coding?
Only GLM 4.6 has a coding score, 8.8 on the Vibe Coding Index; MiniMax M2.1 has none, so the two cannot be ranked on coding. Pick MiniMax M2.1 for output tokens 1.8x cheaper ($1.20 vs $2.20 per million) and work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, GLM 4.6 or MiniMax M2.1?
GLM 4.6 costs $0.60 per million input tokens and $2.20 per million output tokens; MiniMax M2.1 costs $0.30 and $1.20. Cost per solved task is known for MiniMax M2.1 only.
Which has the bigger context window, GLM 4.6 or MiniMax M2.1?
Neither: both take 205K tokens.
How many benchmarks is the GLM 4.6 vs MiniMax M2.1 comparison based on?
29 benchmarks have a result for both models as of October 22, 2026. GLM 4.6's coding index rests on 2 independent benchmarks and MiniMax M2.1's on 1. Where only one model has a result, the page says so instead of naming a winner.