MiniMax M1 vs Qwen3.5-9B
Qwen3.5-9B leads MiniMax M1 on the Artificial Analysis Intelligence Index, 13.3 to 11.7, and Qwen3.5-9B costs 14.7x less per output token ($0.15 vs $2.20 per million). Updated October 22, 2026; 1 benchmarks have a result for both.
MiniMax M1 or Qwen3.5-9B: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick MiniMax M1 for a larger context window (1M against 262K tokens) and work measured by AA Intelligence Index, where it leads.
- Shared results
- 1
- MiniMax M1 only
- 28
- Qwen3.5-9B only
- 15
- Like-for-like categories
- 1 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Qwen3.5-9B
Qwen3.5-9B leads, 13.3 against 11.7.
Same board, both measured
Long documents
Listed context window
MiniMax M1
MiniMax M1 takes 1M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3.5-9B
MiniMax M1 $0.0015, Qwen3.5-9B $0.0002 per turn.
List prices
At a glance
- Coding index
- MiniMax M1 not benchmarked, Qwen3.5-9B not benchmarked.
- Widest category
- Intelligence, 1.6 points apart on average over 1 shared benchmark.
- Widest single gap
- AA Intelligence Index: MiniMax M1 11.7 against Qwen3.5-9B 13.3, 1.6 points apart on a 0 to 100 scale.
- Output price
- MiniMax M1 $2.20 against Qwen3.5-9B $0.15 per million output tokens, 14.7x apart.
- Context window
- MiniMax M1 takes 1M tokens, Qwen3.5-9B 262K.
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 | MiniMax M1 | Bars | Qwen3.5-9B | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| All shared boards | 0 | 1 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index6 boards, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| AA Coding Index | Not measured | 23.5 | Only Qwen3.5-9B measured |
| SciCode | Not measured | 29.5% | Only Qwen3.5-9B measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 24.2% | Only Qwen3.5-9B measured |
| Terminal-Bench | Not measured | 9.2% | Only Qwen3.5-9B measured |
| LMArena Text: coding | 1359 | Not measured | Only MiniMax M1 measured |
| LMArena Text: software and IT | 1359 | Not measured | Only MiniMax M1 measured |
| Neither model has a result on the other 37 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| AA Intelligence Index | 11.7 | 13.3 | Qwen3.5-9B |
| Epoch Capabilities Index | Not measured | 139.3 | Only Qwen3.5-9B measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 86.8% | Only Qwen3.5-9B measured |
| Neither model has a result on the other 41 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | Not measured | 80.6% | Only Qwen3.5-9B measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 14.9% | Only Qwen3.5-9B measured |
| GPQA Diamond (Epoch AI run) | Not measured | 79.0% | Only Qwen3.5-9B measured |
| LMArena Text: hard prompts | 1339 | Not measured | Only MiniMax M1 measured |
| LMArena Text: expert | 1317 | Not measured | Only MiniMax M1 measured |
| LMArena Text: hard prompts in English | 1353 | Not measured | Only MiniMax M1 measured |
| Neither model has a result on the other 17 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 61.7% | Only Qwen3.5-9B measured |
| LMArena Text: math | 1361 | Not measured | Only MiniMax M1 measured |
| LMArena Text: mathematical work | 1363 | Not measured | Only MiniMax M1 measured |
| MathArena | Not measured | 13.0% | Only Qwen3.5-9B measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index4 boards, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| LMArena Text: science | 1354 | Not measured | Only MiniMax M1 measured |
| LMArena Text: medicine and healthcare | 1355 | Not measured | Only MiniMax M1 measured |
| LMArena Text: legal and government | 1337 | Not measured | Only MiniMax M1 measured |
| LMArena Text: business and finance | 1319 | Not measured | Only MiniMax M1 measured |
| Neither model has a result on the other 16 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index21 boards, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | Leader |
|---|---|---|---|
| IFBench | Not measured | 66.7% | Only Qwen3.5-9B measured |
| Long context reasoning (AA-LCR) | Not measured | 70.0% | Only Qwen3.5-9B measured |
| DTBench | Not measured | 71.2% | Only Qwen3.5-9B measured |
| LMCA | Not measured | 24.5% | Only Qwen3.5-9B measured |
| LMArena Text | 1343 | Not measured | Only MiniMax M1 measured |
| LMArena Text: instruction following | 1312 | Not measured | Only MiniMax M1 measured |
| LMArena Text: creative writing | 1297 | Not measured | Only MiniMax M1 measured |
| LMArena Text: English | 1363 | Not measured | Only MiniMax M1 measured |
| LMArena Text: non-English | 1319 | Not measured | Only MiniMax M1 measured |
| LMArena Text: Chinese | 1360 | Not measured | Only MiniMax M1 measured |
| LMArena Text: German | 1350 | Not measured | Only MiniMax M1 measured |
| LMArena Text: Japanese | 1217 | Not measured | Only MiniMax M1 measured |
| LMArena Text: Korean | 1266 | Not measured | Only MiniMax M1 measured |
| LMArena Text: French | 1370 | Not measured | Only MiniMax M1 measured |
| LMArena Text: Spanish | 1353 | Not measured | Only MiniMax M1 measured |
| LMArena Text: Russian | 1329 | Not measured | Only MiniMax M1 measured |
| LMArena Text: Polish | 1329 | Not measured | Only MiniMax M1 measured |
| LMArena Text: multi-turn | 1335 | Not measured | Only MiniMax M1 measured |
| LMArena Text: longer queries | 1326 | Not measured | Only MiniMax M1 measured |
| LMArena Text: writing and language | 1311 | Not measured | Only MiniMax M1 measured |
| LMArena Text: entertainment and media | 1303 | Not measured | Only MiniMax M1 measured |
| Neither model has a result on the other 27 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M1 | Qwen3.5-9B | 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
Qwen3.5-9B costs less
Repository review
50K input + 3K output tokens
Qwen3.5-9B costs less
Agent loop
200K input + 10K output tokens
Qwen3.5-9B 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 | MiniMax M1 | Qwen3.5-9B |
|---|---|---|
| Maker | MiniMax | Qwen |
| Weights | No public weights listed | Open weights |
| Released | June 17, 2025 | March 10, 2026 |
| Context window | 1M | 262K |
| Input $/Mtok | $0.40 | $0.10 |
| Output $/Mtok | $2.20 | $0.15 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M1 better than Qwen3.5-9B for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick MiniMax M1 for a larger context window (1M against 262K tokens) and work measured by AA Intelligence Index, where it leads.
Which is cheaper, MiniMax M1 or Qwen3.5-9B?
MiniMax M1 costs $0.40 per million input tokens and $2.20 per million output tokens; Qwen3.5-9B costs $0.10 and $0.15. Cost per solved task is known for neither of them.
Which has the bigger context window, MiniMax M1 or Qwen3.5-9B?
MiniMax M1, with 1M tokens against 262K.
How many benchmarks is the MiniMax M1 vs Qwen3.5-9B comparison based on?
1 benchmarks have a result for both models as of October 22, 2026. MiniMax M1's coding index rests on 0 independent benchmarks and Qwen3.5-9B's on 0. Where only one model has a result, the page says so instead of naming a winner.