MiniMax M2.5 vs Qwen3.7 Max
Qwen3.7 Max leads MiniMax M2.5 on coding, 54.1 to 37.2 on the Vibe Coding Index, and MiniMax M2.5 costs 3.7x less per output token ($1.20 vs $4.425 per million). Updated October 22, 2026; 28 benchmarks have a result for both.
MiniMax M2.5 or Qwen3.7 Max: which to pick
Pick Qwen3.7 Max for coding: it scores 54.1 on the Vibe Coding Index against 37.2 for MiniMax M2.5.
Pick MiniMax M2.5 for output tokens 3.7x cheaper ($1.20 vs $4.425 per million) and a lower cost per solved task ($0.62 against $4.69).
- Shared results
- 28
- MiniMax M2.5 only
- 43
- Qwen3.7 Max only
- 32
- 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
Qwen3.7 Max
Qwen3.7 Max scores 54.1 against 37.2.
3 benchmarks behind each score
Intelligence
AA Intelligence Index
Qwen3.7 Max
Qwen3.7 Max leads, 29.5 against 22.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Qwen3.7 Max has a AA Agentic Index result, 22.5.
Directional only
Reasoning
GPQA Diamond
Qwen3.7 Max
Qwen3.7 Max leads, 90.2% against 82.1%.
Same board, both measured
Math
AIME
No call
Only MiniMax M2.5 has a AIME result, 88.8%.
Directional only
Knowledge
MMLU Pro
Qwen3.7 Max
Qwen3.7 Max leads, 89.3% against 80.1%.
Same board, both measured
Web design
Design Arena: websites
Qwen3.7 Max
Qwen3.7 Max leads, 1274 against 1222.
Same board, both measured
Long documents
Listed context window
Qwen3.7 Max
Qwen3.7 Max takes 1M tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
MiniMax M2.5 $0.0009, Qwen3.7 Max $0.0037 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
MiniMax M2.5
MiniMax M2.5 $0.62, Qwen3.7 Max $4.69.
Published attempt cost and pass rate
At a glance
- Coding index
- MiniMax M2.5 37.2 from 3 benchmarks, Qwen3.7 Max 54.1 from 3 benchmarks.
- Widest category
- Math, 22.0 points apart on average over 1 shared benchmark.
- Widest single gap
- Vibe Code Bench (Vals AI): MiniMax M2.5 14.8% against Qwen3.7 Max 47.7%, 32.8 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.5 $1.20 against Qwen3.7 Max $4.425 per million output tokens, 3.7x apart.
- Context window
- MiniMax M2.5 takes 205K tokens, Qwen3.7 Max 1M.
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 | Qwen3.7 Max | Ties |
|---|---|---|---|---|
| Coding | 1 | 7 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 1 | ||
| Knowledge | 0 | 4 | ||
| Web design | 0 | 7 | ||
| General | 0 | 2 | ||
| All shared boards | 2 | 26 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index17
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | 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 | 1515 | Qwen3.7 Max |
| AA Coding Index | Not measured | 66.0 | Only Qwen3.7 Max measured |
| LiveCodeBench (Vals AI) | 79.2% | 87.1% | Qwen3.7 Max |
| SWE-bench Verified (Vals AI) | 74.2% | 68.8% | MiniMax M2.5 |
| Vibe Code Bench (Vals AI) | 14.8% | 47.7% | Qwen3.7 Max |
| Code migration (Vals AI) | Not measured | 13.1% | Only Qwen3.7 Max measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 61.0% | Only Qwen3.7 Max measured |
| SciCode | Not measured | 49.5% | Only Qwen3.7 Max measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | 50.8% | Qwen3.7 Max |
| Terminal-Bench | 42.7% | Not measured | Only MiniMax M2.5 measured |
| ALE-Bench | 618.2 | 1189.4 | Qwen3.7 Max |
| LMArena Text: coding | 1380 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: software and IT | 1383 | Not measured | Only MiniMax M2.5 measured |
| LMArena WebDev: React | 1374 | 1514 | Qwen3.7 Max |
| LMArena WebDev: HTML | 1414 | 1512 | Qwen3.7 Max |
| 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 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 29.5 | Qwen3.7 Max |
| Epoch Capabilities Index | 146.6 | 154.0 | Qwen3.7 Max |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 22.5 | Only Qwen3.7 Max measured |
| Design Arena: agents building web apps | Not measured | 1208 | Only Qwen3.7 Max measured |
| Design Arena: agents building full-stack apps | Not measured | 1191 | Only Qwen3.7 Max measured |
| Design Arena: agents building mobile apps | Not measured | 1154 | Only Qwen3.7 Max measured |
| Design Arena: agents building Android apps | Not measured | 1159 | Only Qwen3.7 Max measured |
| Design Arena: agents building Godot games | Not measured | 1187 | Only Qwen3.7 Max measured |
| Design Arena: agents building games | Not measured | 1161 | Only Qwen3.7 Max measured |
| Design Arena: HTML slides | Not measured | 1108 | Only Qwen3.7 Max measured |
| Design Arena: PowerPoint slides | Not measured | 1172 | Only Qwen3.7 Max measured |
| Finance Agent (Vals AI) | Not measured | 47.8% | Only Qwen3.7 Max measured |
| Tax Agent Bench (Vals AI) | Not measured | 15.8% | Only Qwen3.7 Max measured |
| Legal Research Bench (Vals AI) | Not measured | 25.5% | Only Qwen3.7 Max measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 57.0% | Only Qwen3.7 Max measured |
| τ²-Bench Telecom | 95.3% | 94.7% | MiniMax M2.5 |
| Vending-Bench 2 | -$23 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 27 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | 90.2% | Qwen3.7 Max |
| GPQA Diamond (Artificial Analysis run) | 84.8% | 92.3% | Qwen3.7 Max |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | 40.5% | Qwen3.7 Max |
| GPQA Diamond (Epoch AI run) | Not measured | 90.9% | Only Qwen3.7 Max measured |
| ARC-AGI | 63.7% | Not measured | Only MiniMax M2.5 measured |
| ARC-AGI-2 | 4.9% | Not measured | Only MiniMax M2.5 measured |
| SimpleBench | Not measured | 70.4% | Only Qwen3.7 Max measured |
| Chess puzzles | Not measured | 26.0% | Only Qwen3.7 Max measured |
| Mystery game puzzles | Not measured | 32.0% | Only Qwen3.7 Max measured |
| EBR-bench | Not measured | 9.5% | Only Qwen3.7 Max measured |
| LMArena Text: hard prompts | 1372 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: expert | 1378 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: hard prompts in English | 1384 | Not measured | Only MiniMax M2.5 measured |
| Kagi LLM Benchmark | 55.2% | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 9 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only MiniMax M2.5 measured |
| OTIS Mock AIME | Not measured | 95.6% | Only Qwen3.7 Max measured |
| FrontierMath, tiers 1 to 3 | Not measured | 64.6% | Only Qwen3.7 Max measured |
| FrontierMath, tier 4 | Not measured | 34.1% | Only Qwen3.7 Max measured |
| ProofBench | 4.0% | 26.0% | Qwen3.7 Max |
| LMArena Text: math | 1378 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: mathematical work | 1378 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | Leader |
|---|---|---|---|
| MMLU Pro | 80.1% | 89.3% | Qwen3.7 Max |
| LegalBench (Vals AI) | 80.0% | 84.9% | Qwen3.7 Max |
| CaseLaw (Vals AI) | 53.5% | Not measured | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | 59.6% | 63.7% | Qwen3.7 Max |
| TaxEval (Vals AI) | 68.2% | 75.3% | Qwen3.7 Max |
| MedQA (Vals AI) | 92.5% | Not measured | Only MiniMax M2.5 measured |
| MedCode (Vals AI) | Not measured | 38.8% | Only Qwen3.7 Max measured |
| SimpleQA Verified | Not measured | 55.8% | Only Qwen3.7 Max measured |
| LMArena Text: science | 1369 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: medicine and healthcare | 1357 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: legal and government | 1366 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: business and finance | 1356 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 8 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index07
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | 1274 | Qwen3.7 Max |
| Design Arena: UI components | 1170 | 1267 | Qwen3.7 Max |
| Design Arena: game dev | 1176 | 1265 | Qwen3.7 Max |
| Design Arena: data viz | 1172 | 1276 | Qwen3.7 Max |
| Design Arena: 3D | 1170 | 1265 | Qwen3.7 Max |
| Design Arena: all code categories | 1207 | 1274 | Qwen3.7 Max |
| Design Arena: SVG | 1150 | 1216 | Qwen3.7 Max |
| Design Arena: ASCII art | Not measured | 1211 | Only Qwen3.7 Max measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | Not measured | 79.4% | Only Qwen3.7 Max measured |
| IFBench | 71.6% | 80.5% | Qwen3.7 Max |
| Long context reasoning (AA-LCR) | 73.3% | 79.0% | Qwen3.7 Max |
| DTBench | Not measured | 92.3% | Only Qwen3.7 Max measured |
| LMCA | Not measured | 44.0% | Only Qwen3.7 Max 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 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: instruction following | 1353 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: creative writing | 1331 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: English | 1380 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: non-English | 1338 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Chinese | 1393 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: German | 1361 | Not measured | Only MiniMax M2.5 measured |
| 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 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: Polish | 1334 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: multi-turn | 1364 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: longer queries | 1366 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: writing and language | 1345 | Not measured | Only MiniMax M2.5 measured |
| LMArena Text: entertainment and media | 1329 | Not measured | Only MiniMax M2.5 measured |
| EQ-Bench 4 | Not measured | 1110 | Only Qwen3.7 Max measured |
| Neither model has a result on the other 23 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | Qwen3.7 Max | 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 | Qwen3.7 Max |
|---|---|---|
| Maker | MiniMax | Qwen |
| Weights | Open weights | No public weights listed |
| Released | February 12, 2026 | May 21, 2026 |
| Context window | 205K | 1M |
| Input $/Mtok | $0.30 | $1.475 |
| Output $/Mtok | $1.20 | $4.425 |
| Coding index | 37.2 | 54.1 |
| Independent measurements behind it | 3 | 3 |
| Cost per solved task | $0.62 | $4.69 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Qwen3.7 Max for coding?
Pick Qwen3.7 Max for coding: it scores 54.1 on the Vibe Coding Index against 37.2 for MiniMax M2.5. Pick MiniMax M2.5 for output tokens 3.7x cheaper ($1.20 vs $4.425 per million) and a lower cost per solved task ($0.62 against $4.69).
Which is cheaper, MiniMax M2.5 or Qwen3.7 Max?
MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.7 Max costs $1.475 and $4.425. Per solved SWE-bench Verified task, MiniMax M2.5 costs $0.62 and Qwen3.7 Max $4.69.
Which has the bigger context window, MiniMax M2.5 or Qwen3.7 Max?
Qwen3.7 Max, with 1M tokens against 205K.
How many benchmarks is the MiniMax M2.5 vs Qwen3.7 Max comparison based on?
28 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Qwen3.7 Max's on 3. Where only one model has a result, the page says so instead of naming a winner.