MiniMax M2.5 vs Qwen3.5-27B
Updated October 21, 2026. 40 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick MiniMax M2.5 for coding: it scores 59.4 on the Vibe Coding Index against 22.6 for Qwen3.5-27B.
Pick Qwen3.5-27B when the context window is larger, 262K against 205K tokens, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 40
- MiniMax M2.5 only
- 27
- Qwen3.5-27B only
- 13
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
MiniMax M2.5
MiniMax M2.5 scores 59.4 against 22.6.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Qwen3.5-27B
Qwen3.5-27B leads, 22.9 against 22.8.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only MiniMax M2.5 has a GPQA Diamond result, 82.1%.
Directional only
Math
AIME
No call
Only MiniMax M2.5 has a AIME result, 88.8%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M2.5 has a MMLU Pro result, 80.1%.
Directional only
Web design
Design Arena: websites
No call
Only MiniMax M2.5 has a Design Arena: websites result, 1222.
Directional only
Long documents
Listed context window
Qwen3.5-27B
Qwen3.5-27B takes 262K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
MiniMax M2.5 $0.0007, Qwen3.5-27B $0.0014 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.5 has the number, $0.62.
Directional only
At a glance
- Coding index
- MiniMax M2.5 59.4 from 2 benchmarks, Qwen3.5-27B 22.6 from 1 benchmark.
- Widest category
- Knowledge, 9.0 points apart on average over 4 shared benchmarks.
- Widest single gap
- LMArena Text: Japanese: MiniMax M2.5 1171 against Qwen3.5-27B 1346, 29.1 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $0.95 against Qwen3.5-27B $2.16 per million output tokens, 2.3x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, Qwen3.5-27B 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 M2.5 | Bars | Qwen3.5-27B | Ties |
|---|---|---|---|---|
| Coding | 5 | 2 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 1 | 1 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 19 | ||
| All shared boards | 6 | 34 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index52
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| SWE-bench Verified | 75.8% | Not measured | Only MiniMax M2.5 measured |
| SWE-bench Multilingual | 68.3% | Not measured | Only MiniMax M2.5 measured |
| LMArena WebDev | 1386 | 1358 | MiniMax M2.5 |
| LiveCodeBench (Vals AI) | 79.2% | Not measured | Only MiniMax M2.5 measured |
| SWE-bench Verified (Vals AI) | 74.2% | Not measured | Only MiniMax M2.5 measured |
| Vibe Code Bench (Vals AI) | 14.8% | Not measured | Only MiniMax M2.5 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | 32.6% | MiniMax M2.5 |
| Terminal-Bench | 42.7% | Not measured | Only MiniMax M2.5 measured |
| WeirdML | Not measured | 39.5% | Only Qwen3.5-27B measured |
| ALE-Bench | 618.2 | 349.4 | MiniMax M2.5 |
| LMArena Text: coding | 1380 | 1427 | Qwen3.5-27B |
| LMArena Text: software and IT | 1383 | 1431 | Qwen3.5-27B |
| LMArena WebDev: React | 1374 | 1346 | MiniMax M2.5 |
| LMArena WebDev: HTML | 1414 | 1386 | MiniMax M2.5 |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 22.9 | Qwen3.5-27B |
| Epoch Capabilities Index | 146.6 | Not measured | Only MiniMax M2.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 95.3% | 93.9% | MiniMax M2.5 |
| Vending-Bench 2 | -$23 | $202 | Qwen3.5-27B |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | Not measured | Only MiniMax M2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 84.8% | 85.8% | Qwen3.5-27B |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | 23.9% | Qwen3.5-27B |
| ARC-AGI | 63.7% | Not measured | Only MiniMax M2.5 measured |
| ARC-AGI-2 | 4.9% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: hard prompts | 1372 | 1415 | Qwen3.5-27B |
| LMArena Text: expert | 1378 | 1427 | Qwen3.5-27B |
| LMArena Text: hard prompts in English | 1384 | 1429 | Qwen3.5-27B |
| LMArena Vision: diagrams | Not measured | 1249 | Only Qwen3.5-27B measured |
| LMArena Vision: homework | Not measured | 1256 | Only Qwen3.5-27B measured |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only MiniMax M2.5 measured |
| ProofBench | 4.0% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: math | 1378 | 1429 | Qwen3.5-27B |
| LMArena Text: mathematical work | 1378 | 1429 | Qwen3.5-27B |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| MMLU Pro | 80.1% | Not measured | Only MiniMax M2.5 measured |
| LegalBench (Vals AI) | 80.0% | Not measured | Only MiniMax M2.5 measured |
| CaseLaw (Vals AI) | 53.5% | Not measured | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | 59.6% | Not measured | Only MiniMax M2.5 measured |
| TaxEval (Vals AI) | 68.2% | Not measured | Only MiniMax M2.5 measured |
| MedQA (Vals AI) | 92.5% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: science | 1369 | 1437 | Qwen3.5-27B |
| LMArena Text: medicine and healthcare | 1357 | 1425 | Qwen3.5-27B |
| LMArena Text: legal and government | 1366 | 1405 | Qwen3.5-27B |
| LMArena Text: business and finance | 1356 | 1399 | Qwen3.5-27B |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: UI components | 1172 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: game dev | 1176 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: data viz | 1171 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: 3D | 1170 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: all code categories | 1207 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: SVG | 1147 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 2 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | Leader |
|---|---|---|---|
| IFBench | 71.6% | 75.6% | Qwen3.5-27B |
| Long context reasoning (AA-LCR) | 73.3% | 77.7% | Qwen3.5-27B |
| DTBench | Not measured | 82.4% | Only Qwen3.5-27B measured |
| LMCA | Not measured | 34.0% | Only Qwen3.5-27B measured |
| CL-bench | 11.4% | Not measured | Only MiniMax M2.5 measured |
| CL-bench Life | 6.3% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text | 1359 | 1409 | Qwen3.5-27B |
| LMArena Text: instruction following | 1353 | 1393 | Qwen3.5-27B |
| LMArena Text: creative writing | 1331 | 1362 | Qwen3.5-27B |
| LMArena Vision | Not measured | 1241 | Only Qwen3.5-27B measured |
| LMArena Text: English | 1380 | 1425 | Qwen3.5-27B |
| LMArena Text: non-English | 1338 | 1390 | Qwen3.5-27B |
| LMArena Text: Chinese | 1393 | 1478 | Qwen3.5-27B |
| LMArena Text: German | 1361 | 1392 | Qwen3.5-27B |
| LMArena Text: Japanese | 1171 | 1346 | Qwen3.5-27B |
| LMArena Text: Korean | 1233 | 1359 | Qwen3.5-27B |
| LMArena Text: French | 1363 | 1410 | Qwen3.5-27B |
| LMArena Text: Spanish | 1353 | 1407 | Qwen3.5-27B |
| LMArena Text: Russian | 1359 | 1390 | Qwen3.5-27B |
| LMArena Text: Polish | 1334 | 1375 | Qwen3.5-27B |
| LMArena Text: multi-turn | 1364 | 1410 | Qwen3.5-27B |
| LMArena Text: longer queries | 1366 | 1413 | Qwen3.5-27B |
| LMArena Text: writing and language | 1345 | 1380 | Qwen3.5-27B |
| LMArena Text: entertainment and media | 1329 | 1363 | Qwen3.5-27B |
| LMArena Vision: English | Not measured | 1246 | Only Qwen3.5-27B measured |
| LMArena Vision: Chinese | Not measured | 1301 | Only Qwen3.5-27B measured |
| LMArena Vision: reading text | Not measured | 1246 | Only Qwen3.5-27B measured |
| LMArena Vision: humor | Not measured | 1227 | Only Qwen3.5-27B measured |
| LMArena Vision: captioning | Not measured | 1170 | Only Qwen3.5-27B measured |
| LMArena Vision: recognizing things | Not measured | 1210 | Only Qwen3.5-27B measured |
| LMArena Vision: creative writing | Not measured | 1224 | Only Qwen3.5-27B measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | Qwen3.5-27B | 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 M2.5 costs less
Repository review
50K input + 3K output tokens
MiniMax M2.5 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.5 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 M2.5 | Qwen3.5-27B |
|---|---|---|
| Maker | MiniMax | Qwen |
| Weights | Open weights | Open weights |
| Released | February 12, 2026 | February 25, 2026 |
| Context window | 205K | 262K |
| Input $/Mtok | $0.27 | $0.27 |
| Output $/Mtok | $0.95 | $2.16 |
| Coding index | 59.4 | 22.6 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $0.62 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Qwen3.5-27B for coding?
Pick MiniMax M2.5 for coding: it scores 59.4 on the Vibe Coding Index against 22.6 for Qwen3.5-27B. Pick Qwen3.5-27B when the context window is larger, 262K against 205K tokens, or when what matters is LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, MiniMax M2.5 or Qwen3.5-27B?
MiniMax M2.5 costs $0.27 per million input tokens and $0.95 per million output tokens; Qwen3.5-27B costs $0.27 and $2.16. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, MiniMax M2.5 or Qwen3.5-27B?
Qwen3.5-27B, with 262K tokens against 205K.
How many benchmarks is the MiniMax M2.5 vs Qwen3.5-27B comparison based on?
40 benchmarks have a result for both models as of October 21, 2026. MiniMax M2.5's coding index rests on 2 independent benchmarks and Qwen3.5-27B's on 1. Where only one model has a result, the page says so instead of naming a winner.