MiniMax M2.5 vs Qwen3 32B
MiniMax M2.5 leads Qwen3 32B on the Artificial Analysis Intelligence Index, 22.8 to 7.3, and Qwen3 32B costs 3.0x less per output token ($0.40 vs $1.20 per million). Updated October 22, 2026; 32 benchmarks have a result for both.
MiniMax M2.5 or Qwen3 32B: which to pick
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Qwen3 32B has none, so the two cannot be ranked on coding.
Pick Qwen3 32B for output tokens 3.0x cheaper ($0.40 vs $1.20 per million) and work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.
- Shared results
- 32
- MiniMax M2.5 only
- 39
- Qwen3 32B only
- 13
- Like-for-like categories
- 7 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 MiniMax M2.5 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M2.5
MiniMax M2.5 leads, 22.8 against 7.3.
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
MiniMax M2.5
MiniMax M2.5 takes 205K tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen3 32B
MiniMax M2.5 $0.0009, Qwen3 32B $0.0003 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 37.2 from 3 benchmarks, Qwen3 32B not benchmarked.
- Widest category
- Agentic work, 65.5 points apart on average over 1 shared benchmark.
- Widest single gap
- Long context reasoning (AA-LCR): MiniMax M2.5 73.3% against Qwen3 32B 0.0%, 73.3 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $1.20 against Qwen3 32B $0.40 per million output tokens, 3.0x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, Qwen3 32B 131K.
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 32B | Ties |
|---|---|---|---|---|
| Coding | 3 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 6 | 0 | ||
| Math | 0 | 2 | ||
| Knowledge | 2 | 2 | ||
| General | 14 | 0 | ||
| All shared boards | 28 | 4 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index30
| Benchmark | MiniMax M2.5 | Qwen3 32B | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 40.0% | Only Qwen3 32B measured |
| 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 | Not measured | Only MiniMax M2.5 measured |
| 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 |
| LiveCodeBench (Artificial Analysis run) | Not measured | 54.6% | Only Qwen3 32B measured |
| SciCode | Not measured | 36.0% | Only Qwen3 32B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | 3.0% | MiniMax M2.5 |
| Terminal-Bench | 42.7% | Not measured | Only MiniMax M2.5 measured |
| ALE-Bench | 618.2 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: coding | 1380 | 1357 | MiniMax M2.5 |
| LMArena Text: software and IT | 1383 | 1366 | MiniMax M2.5 |
| LMArena WebDev: React | 1374 | Not measured | Only MiniMax M2.5 measured |
| LMArena WebDev: HTML | 1414 | Not measured | Only MiniMax M2.5 measured |
| SWE Atlas: Codebase QnA | 10.3% | Not measured | Only MiniMax M2.5 measured |
| SWE Atlas: Refactoring | 19.5% | Not measured | Only MiniMax M2.5 measured |
| SWE Atlas: Test Writing | 18.6% | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | MiniMax M2.5 | Qwen3 32B | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 7.3 | MiniMax M2.5 |
| Epoch Capabilities Index | 146.6 | 138.4 | MiniMax M2.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | MiniMax M2.5 | Qwen3 32B | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 95.3% | 29.8% | MiniMax M2.5 |
| Vending-Bench 2 | -$23 | Not measured | Only MiniMax M2.5 measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 48.7% | Only Qwen3 32B measured |
| BrowseComp-Plus | Not measured | 10.7% | Only Qwen3 32B measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | MiniMax M2.5 | Qwen3 32B | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | Not measured | Only MiniMax M2.5 measured |
| GPQA Diamond (Artificial Analysis run) | 84.8% | 66.8% | MiniMax M2.5 |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | 7.4% | MiniMax M2.5 |
| GPQA Diamond (Epoch AI run) | Not measured | 65.7% | Only Qwen3 32B measured |
| 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 | 1334 | MiniMax M2.5 |
| LMArena Text: expert | 1378 | 1362 | MiniMax M2.5 |
| LMArena Text: hard prompts in English | 1384 | 1350 | MiniMax M2.5 |
| Kagi LLM Benchmark | 55.2% | 48.7% | MiniMax M2.5 |
| Neither model has a result on the other 13 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Qwen3 32B | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only MiniMax M2.5 measured |
| AA Math Index | Not measured | 73.0 | Only Qwen3 32B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 73.0% | Only Qwen3 32B measured |
| OTIS Mock AIME | Not measured | 66.9% | Only Qwen3 32B measured |
| ProofBench | 4.0% | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: math | 1378 | 1399 | Qwen3 32B |
| LMArena Text: mathematical work | 1378 | 1420 | Qwen3 32B |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index22
| Benchmark | MiniMax M2.5 | Qwen3 32B | 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 |
| MMLU Pro (Artificial Analysis run) | Not measured | 79.8% | Only Qwen3 32B measured |
| LMArena Text: science | 1369 | 1372 | Qwen3 32B |
| LMArena Text: medicine and healthcare | 1357 | 1368 | Qwen3 32B |
| LMArena Text: legal and government | 1366 | 1324 | MiniMax M2.5 |
| LMArena Text: business and finance | 1356 | 1318 | MiniMax M2.5 |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | MiniMax M2.5 | Qwen3 32B | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: UI components | 1170 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: game dev | 1176 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: data viz | 1172 | 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 | 1150 | 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 index140
| Benchmark | MiniMax M2.5 | Qwen3 32B | Leader |
|---|---|---|---|
| IFBench | 71.6% | 36.3% | MiniMax M2.5 |
| Long context reasoning (AA-LCR) | 73.3% | 0.0% | MiniMax M2.5 |
| DTBench | Not measured | 67.5% | Only Qwen3 32B measured |
| LMCA | Not measured | 17.3% | Only Qwen3 32B measured |
| Fiction.LiveBench | Not measured | 74.2% | Only Qwen3 32B 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 | 1340 | MiniMax M2.5 |
| LMArena Text: instruction following | 1353 | 1305 | MiniMax M2.5 |
| LMArena Text: creative writing | 1331 | 1297 | MiniMax M2.5 |
| LMArena Text: English | 1380 | 1359 | MiniMax M2.5 |
| LMArena Text: non-English | 1338 | 1317 | MiniMax M2.5 |
| LMArena Text: Chinese | 1393 | 1357 | MiniMax M2.5 |
| LMArena Text: German | 1361 | 1341 | MiniMax M2.5 |
| LMArena Text: Japanese | 1171 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Korean | 1233 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: French | 1363 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Spanish | 1353 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Russian | 1359 | 1311 | MiniMax M2.5 |
| LMArena Text: Polish | 1334 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: multi-turn | 1364 | 1331 | MiniMax M2.5 |
| LMArena Text: longer queries | 1366 | 1327 | MiniMax M2.5 |
| LMArena Text: writing and language | 1345 | 1298 | MiniMax M2.5 |
| LMArena Text: entertainment and media | 1329 | 1279 | MiniMax M2.5 |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | Qwen3 32B | 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 32B costs less
Repository review
50K input + 3K output tokens
Qwen3 32B costs less
Agent loop
200K input + 10K output tokens
Qwen3 32B 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 32B |
|---|---|---|
| Maker | MiniMax | Qwen |
| Weights | Open weights | Open weights |
| Released | February 12, 2026 | April 28, 2025 |
| Context window | 205K | 131K |
| Input $/Mtok | $0.30 | $0.14 |
| Output $/Mtok | $1.20 | $0.40 |
| Coding index | 37.2 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $0.62 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Qwen3 32B for coding?
Only MiniMax M2.5 has a coding score, 37.2 on the Vibe Coding Index; Qwen3 32B has none, so the two cannot be ranked on coding. Pick Qwen3 32B for output tokens 3.0x cheaper ($0.40 vs $1.20 per million) and work measured by LMArena Text: math or LMArena Text: mathematical work, where it leads.
Which is cheaper, MiniMax M2.5 or Qwen3 32B?
MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen3 32B costs $0.14 and $0.40. Cost per solved task is known for MiniMax M2.5 only.
Which has the bigger context window, MiniMax M2.5 or Qwen3 32B?
MiniMax M2.5, with 205K tokens against 131K.
How many benchmarks is the MiniMax M2.5 vs Qwen3 32B comparison based on?
32 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Qwen3 32B's on 0. Where only one model has a result, the page says so instead of naming a winner.