MiniMax M2.7 vs Qwen2.5 72B Instruct
MiniMax M2.7 leads Qwen2.5 72B Instruct on the Artificial Analysis Intelligence Index, 22.8 to 7.7, and Qwen2.5 72B Instruct costs 3.0x less per output token ($0.40 vs $1.20 per million). Updated October 22, 2026; 35 benchmarks have a result for both.
MiniMax M2.7 or Qwen2.5 72B Instruct: which to pick
Only MiniMax M2.7 has a coding score, 36.2 on the Vibe Coding Index; Qwen2.5 72B Instruct has none, so the two cannot be ranked on coding.
Pick Qwen2.5 72B Instruct for output tokens 3.0x cheaper ($0.40 vs $1.20 per million).
- Shared results
- 35
- MiniMax M2.7 only
- 39
- Qwen2.5 72B Instruct only
- 18
- 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 M2.7 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
MiniMax M2.7
MiniMax M2.7 leads, 22.8 against 7.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only MiniMax M2.7 has a AA Agentic Index result, 15.3.
Directional only
Reasoning
GPQA Diamond
No call
Only MiniMax M2.7 has a GPQA Diamond result, 86.6%.
Directional only
Math
AIME
No call
Only MiniMax M2.7 has a AIME result, 91.0%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M2.7 has a MMLU Pro result, 80.4%.
Directional only
Web design
Design Arena: websites
No call
Only MiniMax M2.7 has a Design Arena: websites result, 1242.
Directional only
Long documents
Listed context window
MiniMax M2.7
MiniMax M2.7 takes 205K tokens against 33K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Qwen2.5 72B Instruct
MiniMax M2.7 $0.0009, Qwen2.5 72B Instruct $0.0006 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M2.7 has the number, $0.64.
Directional only
At a glance
- Coding index
- MiniMax M2.7 36.2 from 3 benchmarks, Qwen2.5 72B Instruct not benchmarked.
- Widest category
- Agentic work, 50.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: MiniMax M2.7 84.8% against Qwen2.5 72B Instruct 34.5%, 50.3 points apart on a 0 to 100 scale.
- Output price
- MiniMax M2.7 $1.20 against Qwen2.5 72B Instruct $0.40 per million output tokens, 3.0x apart.
- Context window
- MiniMax M2.7 takes 205K tokens, Qwen2.5 72B Instruct 33K.
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 M2.7 | Bars | Qwen2.5 72B Instruct | Ties |
|---|---|---|---|---|
| Coding | 4 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 5 | 0 | ||
| Math | 2 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 17 | 0 | ||
| All shared boards | 35 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index40
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| LMArena WebDev | 1399 | Not measured | Only MiniMax M2.7 measured |
| AA Coding Index | 52.6 | Not measured | Only MiniMax M2.7 measured |
| LiveCodeBench (Vals AI) | 79.9% | Not measured | Only MiniMax M2.7 measured |
| SWE-bench Verified (Vals AI) | 73.8% | Not measured | Only MiniMax M2.7 measured |
| Vibe Code Bench (Vals AI) | 11.9% | Not measured | Only MiniMax M2.7 measured |
| Code migration (Vals AI) | 8.7% | Not measured | Only MiniMax M2.7 measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only MiniMax M2.7 measured |
| Terminal-Bench 2.1 (Vals AI) | 48.7% | Not measured | Only MiniMax M2.7 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 27.6% | Only Qwen2.5 72B Instruct measured |
| SciCode | 50.1% | Not measured | Only MiniMax M2.7 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 39.4% | 4.5% | MiniMax M2.7 |
| Terminal-Bench | 45.1% | Not measured | Only MiniMax M2.7 measured |
| WeirdML | 37.0% | 16.0% | MiniMax M2.7 |
| ALE-Bench | 599.3 | Not measured | Only MiniMax M2.7 measured |
| LMArena Text: coding | 1454 | 1292 | MiniMax M2.7 |
| LMArena Text: software and IT | 1446 | 1292 | MiniMax M2.7 |
| LMArena WebDev: React | 1388 | Not measured | Only MiniMax M2.7 measured |
| LMArena WebDev: HTML | 1401 | Not measured | Only MiniMax M2.7 measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 7.7 | MiniMax M2.7 |
| Epoch Capabilities Index | 145.8 | 129.0 | MiniMax M2.7 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AA Agentic Index | 15.3 | Not measured | Only MiniMax M2.7 measured |
| Finance Agent (Vals AI) | 27.9% | Not measured | Only MiniMax M2.7 measured |
| Tax Agent Bench (Vals AI) | 6.9% | Not measured | Only MiniMax M2.7 measured |
| Legal Research Bench (Vals AI) | 10.6% | Not measured | Only MiniMax M2.7 measured |
| Excel Modeling Benchmark (Vals AI) | 28.4% | Not measured | Only MiniMax M2.7 measured |
| τ²-Bench Telecom | 84.8% | 34.5% | MiniMax M2.7 |
| METR time horizons | Not measured | 35.8% | Only Qwen2.5 72B Instruct measured |
| BALROG | Not measured | 16.2% | Only Qwen2.5 72B Instruct measured |
| TheAgentCompany | Not measured | 5.7% | Only Qwen2.5 72B Instruct measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| GPQA Diamond | 86.6% | Not measured | Only MiniMax M2.7 measured |
| GPQA Diamond (Artificial Analysis run) | 87.4% | 49.1% | MiniMax M2.7 |
| Humanity's Last Exam (Artificial Analysis run) | 29.6% | 3.6% | MiniMax M2.7 |
| GPQA Diamond (Epoch AI run) | Not measured | 49.1% | Only Qwen2.5 72B Instruct measured |
| BIG-Bench Hard | Not measured | 79.8% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: hard prompts | 1422 | 1271 | MiniMax M2.7 |
| LMArena Text: expert | 1443 | 1245 | MiniMax M2.7 |
| LMArena Text: hard prompts in English | 1441 | 1279 | MiniMax M2.7 |
| Neither model has a result on the other 15 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| AIME | 91.0% | Not measured | Only MiniMax M2.7 measured |
| AA Math Index | Not measured | 14.0 | Only Qwen2.5 72B Instruct measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 14.0% | Only Qwen2.5 72B Instruct measured |
| OTIS Mock AIME | Not measured | 8.1% | Only Qwen2.5 72B Instruct measured |
| ProofBench | 3.0% | Not measured | Only MiniMax M2.7 measured |
| MATH level 5 | Not measured | 63.2% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: math | 1421 | 1283 | MiniMax M2.7 |
| LMArena Text: mathematical work | 1437 | 1290 | MiniMax M2.7 |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| MMLU Pro | 80.4% | Not measured | Only MiniMax M2.7 measured |
| LegalBench (Vals AI) | 84.0% | Not measured | Only MiniMax M2.7 measured |
| CaseLaw (Vals AI) | 60.9% | Not measured | Only MiniMax M2.7 measured |
| CorpFin (Vals AI) | 61.2% | Not measured | Only MiniMax M2.7 measured |
| TaxEval (Vals AI) | 66.6% | Not measured | Only MiniMax M2.7 measured |
| MedCode (Vals AI) | 34.4% | Not measured | Only MiniMax M2.7 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 72.0% | Only Qwen2.5 72B Instruct measured |
| MMLU | Not measured | 85.3% | Only Qwen2.5 72B Instruct measured |
| AI2 Reasoning Challenge | Not measured | 94.5% | Only Qwen2.5 72B Instruct measured |
| LMArena Text: science | 1416 | 1275 | MiniMax M2.7 |
| LMArena Text: medicine and healthcare | 1409 | 1258 | MiniMax M2.7 |
| LMArena Text: legal and government | 1403 | 1288 | MiniMax M2.7 |
| LMArena Text: business and finance | 1407 | 1253 | MiniMax M2.7 |
| Neither model has a result on the other 7 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| Design Arena: websites | 1242 | Not measured | Only MiniMax M2.7 measured |
| Design Arena: UI components | 1207 | Not measured | Only MiniMax M2.7 measured |
| Design Arena: game dev | 1209 | Not measured | Only MiniMax M2.7 measured |
| Design Arena: data viz | 1233 | Not measured | Only MiniMax M2.7 measured |
| Design Arena: 3D | 1194 | Not measured | Only MiniMax M2.7 measured |
| Design Arena: all code categories | 1233 | Not measured | Only MiniMax M2.7 measured |
| Design Arena: SVG | 1137 | Not measured | Only MiniMax M2.7 measured |
| Design Arena: ASCII art | 1136 | Not measured | Only MiniMax M2.7 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index170
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | Leader |
|---|---|---|---|
| MedScribe (Vals AI) | 79.9% | Not measured | Only MiniMax M2.7 measured |
| IFBench | 75.7% | 36.9% | MiniMax M2.7 |
| Long context reasoning (AA-LCR) | 78.3% | Not measured | Only MiniMax M2.7 measured |
| DTBench | Not measured | 62.9% | Only Qwen2.5 72B Instruct measured |
| LMCA | Not measured | 13.4% | Only Qwen2.5 72B Instruct measured |
| ExploitBench | 13.3% | Not measured | Only MiniMax M2.7 measured |
| HellaSwag | Not measured | 84.8% | Only Qwen2.5 72B Instruct measured |
| WinoGrande | Not measured | 82.3% | Only Qwen2.5 72B Instruct measured |
| PIQA | Not measured | 82.6% | Only Qwen2.5 72B Instruct measured |
| LMArena Text | 1405 | 1269 | MiniMax M2.7 |
| LMArena Text: instruction following | 1405 | 1254 | MiniMax M2.7 |
| LMArena Text: creative writing | 1354 | 1221 | MiniMax M2.7 |
| LMArena Text: English | 1426 | 1283 | MiniMax M2.7 |
| LMArena Text: non-English | 1382 | 1252 | MiniMax M2.7 |
| LMArena Text: Chinese | 1442 | 1273 | MiniMax M2.7 |
| LMArena Text: German | 1398 | 1234 | MiniMax M2.7 |
| LMArena Text: Japanese | 1260 | 1180 | MiniMax M2.7 |
| LMArena Text: Korean | 1314 | 1188 | MiniMax M2.7 |
| LMArena Text: French | 1424 | 1280 | MiniMax M2.7 |
| LMArena Text: Spanish | 1402 | 1255 | MiniMax M2.7 |
| LMArena Text: Russian | 1383 | 1264 | MiniMax M2.7 |
| LMArena Text: Polish | 1387 | Not measured | Only MiniMax M2.7 measured |
| LMArena Text: multi-turn | 1412 | 1272 | MiniMax M2.7 |
| LMArena Text: longer queries | 1418 | 1281 | MiniMax M2.7 |
| LMArena Text: writing and language | 1376 | 1247 | MiniMax M2.7 |
| LMArena Text: entertainment and media | 1360 | 1211 | MiniMax M2.7 |
| Neither model has a result on the other 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.7 | Qwen2.5 72B Instruct | 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
Qwen2.5 72B Instruct costs less
Repository review
50K input + 3K output tokens
MiniMax M2.7 costs less
Agent loop
200K input + 10K output tokens
MiniMax M2.7 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 M2.7 | Qwen2.5 72B Instruct |
|---|---|---|
| Maker | MiniMax | Qwen |
| Weights | Open weights | Open weights |
| Released | March 18, 2026 | September 19, 2024 |
| Context window | 205K | 33K |
| Input $/Mtok | $0.30 | $0.36 |
| Output $/Mtok | $1.20 | $0.40 |
| Coding index | 36.2 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $0.64 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.7 better than Qwen2.5 72B Instruct for coding?
Only MiniMax M2.7 has a coding score, 36.2 on the Vibe Coding Index; Qwen2.5 72B Instruct has none, so the two cannot be ranked on coding. Pick Qwen2.5 72B Instruct for output tokens 3.0x cheaper ($0.40 vs $1.20 per million).
Which is cheaper, MiniMax M2.7 or Qwen2.5 72B Instruct?
MiniMax M2.7 costs $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5 72B Instruct costs $0.36 and $0.40. Cost per solved task is known for MiniMax M2.7 only.
Which has the bigger context window, MiniMax M2.7 or Qwen2.5 72B Instruct?
MiniMax M2.7, with 205K tokens against 33K.
How many benchmarks is the MiniMax M2.7 vs Qwen2.5 72B Instruct comparison based on?
35 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.7's coding index rests on 3 independent benchmarks and Qwen2.5 72B Instruct's on 0. Where only one model has a result, the page says so instead of naming a winner.