MiniMax M2.5 vs Inkling Small
MiniMax M2.5 leads Inkling Small on coding, 37.2 to 27.3 on the Vibe Coding Index, at about the same output price ($1.20 vs $1.20 per million). Updated October 22, 2026; 47 benchmarks have a result for both.
MiniMax M2.5 or Inkling Small: which to pick
Pick MiniMax M2.5 for coding: it scores 37.2 on the Vibe Coding Index against 27.3 for Inkling Small, though on 3 benchmarks against 4.
Pick Inkling Small for a lower cost per solved task ($0.16 against $0.62) and a larger context window (524K against 205K tokens).
- Shared results
- 47
- MiniMax M2.5 only
- 21
- Inkling Small only
- 37
- Like-for-like categories
- 6 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
MiniMax M2.5
MiniMax M2.5 scores 37.2 against 27.3.
3 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
Inkling Small
Inkling Small leads, 25.7 against 22.8.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Inkling Small has a AA Agentic Index result, 23.5.
Directional only
Reasoning
GPQA Diamond
Inkling Small
Inkling Small leads, 83.6% 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
Inkling Small
Inkling Small leads, 85.6% against 80.1%.
Same board, both measured
Web design
Design Arena: websites
No call
Only MiniMax M2.5 has a Design Arena: websites result, 1222.
Directional only
General
Vals Index
No call
Only Inkling Small has a Vals Index result, 27.6%.
Directional only
Long documents
Listed context window
Inkling Small
Inkling Small takes 524K tokens against 205K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
MiniMax M2.5
MiniMax M2.5 $0.0009, Inkling Small $0.0010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Inkling Small
MiniMax M2.5 $0.62, Inkling Small $0.16.
Published attempt cost and pass rate
At a glance
- Coding index
- MiniMax M2.5 37.2 from 3 benchmarks, Inkling Small 27.3 from 4 benchmarks.
- Widest category
- Reasoning, 12.7 points apart on average over 8 shared benchmarks.
- Widest single gap
- LMArena Text: Japanese: MiniMax M2.5 1171 against Inkling Small 1401, 38.3 points apart on a 0 to 100 scale.
- Output price
- Both cost $1.20 per million output tokens.
- Context window
- MiniMax M2.5 takes 205K tokens, Inkling Small 524K.
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 | Inkling Small | Ties |
|---|---|---|---|---|
| Coding | 1 | 7 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 8 | ||
| Math | 0 | 3 | ||
| Knowledge | 0 | 8 | ||
| General | 0 | 18 | ||
| All shared boards | 1 | 46 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index17
| Benchmark | MiniMax M2.5 | Inkling Small | 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 | 1409 | Inkling Small |
| AA Coding Index | Not measured | 52.9 | Only Inkling Small measured |
| LiveCodeBench (Vals AI) | 79.2% | 85.9% | Inkling Small |
| SWE-bench Verified (Vals AI) | 74.2% | 82.2% | Inkling Small |
| Terminal-Bench 4 (Vals AI) | Not measured | 0.0% | Only Inkling Small measured |
| Vibe Code Bench (Vals AI) | 14.8% | 19.1% | Inkling Small |
| Code migration (Vals AI) | Not measured | 13.7% | Only Inkling Small measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only Inkling Small measured |
| IOI (Vals AI) | Not measured | 9.3% | Only Inkling Small measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 55.1% | Only Inkling Small measured |
| SkillsBench (Vals AI) | Not measured | 33.6% | Only Inkling Small measured |
| CyberBench (Vals AI) | Not measured | 64.1% | Only Inkling Small measured |
| SciCode | Not measured | 49.7% | Only Inkling Small measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | Not measured | Only MiniMax M2.5 measured |
| 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 | 1450 | Inkling Small |
| LMArena Text: software and IT | 1383 | 1447 | Inkling Small |
| LMArena WebDev: React | 1374 | 1399 | Inkling Small |
| LMArena WebDev: HTML | 1414 | 1398 | MiniMax M2.5 |
| LMArena WebDev: from an image | Not measured | 1410 | Only Inkling Small measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | MiniMax M2.5 | Inkling Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 22.8 | 25.7 | Inkling Small |
| Epoch Capabilities Index | 146.6 | 150.3 | Inkling Small |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | MiniMax M2.5 | Inkling Small | Leader |
|---|---|---|---|
| AA Agentic Index | Not measured | 23.5 | Only Inkling Small measured |
| Finance Agent (Vals AI) | Not measured | 41.3% | Only Inkling Small measured |
| Tax Agent Bench (Vals AI) | Not measured | 15.4% | Only Inkling Small measured |
| Legal Research Bench (Vals AI) | Not measured | 25.5% | Only Inkling Small measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 2.9% | Only Inkling Small measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 31.8% | Only Inkling Small measured |
| τ²-Bench Telecom | 95.3% | Not measured | Only MiniMax M2.5 measured |
| Vending-Bench 2 | -$23 | Not measured | Only MiniMax M2.5 measured |
| Neither model has a result on the other 33 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | MiniMax M2.5 | Inkling Small | Leader |
|---|---|---|---|
| GPQA Diamond | 82.1% | 83.6% | Inkling Small |
| GPQA Diamond (Artificial Analysis run) | 84.8% | 89.5% | Inkling Small |
| Humanity's Last Exam (Artificial Analysis run) | 20.5% | 33.3% | Inkling Small |
| GPQA Diamond (Epoch AI run) | Not measured | 88.5% | Only Inkling Small measured |
| ARC-AGI | 63.7% | 84.0% | Inkling Small |
| ARC-AGI-2 | 4.9% | 40.1% | Inkling Small |
| Mystery game puzzles | Not measured | 6.0% | Only Inkling Small measured |
| LMArena Text: hard prompts | 1372 | 1423 | Inkling Small |
| LMArena Text: expert | 1378 | 1441 | Inkling Small |
| LMArena Text: hard prompts in English | 1384 | 1429 | Inkling Small |
| LMArena Vision: diagrams | Not measured | 1251 | Only Inkling Small measured |
| LMArena Vision: homework | Not measured | 1257 | Only Inkling Small 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 index03
| Benchmark | MiniMax M2.5 | Inkling Small | Leader |
|---|---|---|---|
| AIME | 88.8% | Not measured | Only MiniMax M2.5 measured |
| OTIS Mock AIME | Not measured | 90.0% | Only Inkling Small measured |
| FrontierMath, tiers 1 to 3 | Not measured | 46.3% | Only Inkling Small measured |
| FrontierMath, tier 4 | Not measured | 17.1% | Only Inkling Small measured |
| ProofBench | 4.0% | 6.0% | Inkling Small |
| LMArena Text: math | 1378 | 1459 | Inkling Small |
| LMArena Text: mathematical work | 1378 | 1441 | Inkling Small |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | MiniMax M2.5 | Inkling Small | Leader |
|---|---|---|---|
| MMLU Pro | 80.1% | 85.6% | Inkling Small |
| LegalBench (Vals AI) | 80.0% | 83.0% | Inkling Small |
| CaseLaw (Vals AI) | 53.5% | Not measured | Only MiniMax M2.5 measured |
| CorpFin (Vals AI) | 59.6% | 69.6% | Inkling Small |
| TaxEval (Vals AI) | 68.2% | 75.5% | Inkling Small |
| MortgageTax (Vals AI) | Not measured | 62.3% | Only Inkling Small measured |
| MedQA (Vals AI) | 92.5% | Not measured | Only MiniMax M2.5 measured |
| MedCode (Vals AI) | Not measured | 37.9% | Only Inkling Small measured |
| SimpleQA Verified | Not measured | 19.1% | Only Inkling Small measured |
| LMArena Text: science | 1369 | 1428 | Inkling Small |
| LMArena Text: medicine and healthcare | 1357 | 1413 | Inkling Small |
| LMArena Text: legal and government | 1366 | 1415 | Inkling Small |
| LMArena Text: business and finance | 1356 | 1413 | Inkling Small |
| Neither model has a result on the other 5 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | MiniMax M2.5 | Inkling Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1222 | Not measured | Only MiniMax M2.5 measured |
| Design Arena: UI components | 1173 | 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 index018
| Benchmark | MiniMax M2.5 | Inkling Small | Leader |
|---|---|---|---|
| Vals Index | Not measured | 27.6% | Only Inkling Small measured |
| Public Benefits Bench (Vals AI) | Not measured | 59.4% | Only Inkling Small measured |
| SAGE (Vals AI) | Not measured | 32.7% | Only Inkling Small measured |
| MedScribe (Vals AI) | Not measured | 84.1% | Only Inkling Small measured |
| Vals Multimodal Index | Not measured | 50.0% | Only Inkling Small measured |
| IFBench | 71.6% | Not measured | Only MiniMax M2.5 measured |
| Long context reasoning (AA-LCR) | 73.3% | 75.7% | Inkling Small |
| 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 | 1413 | Inkling Small |
| LMArena Text: instruction following | 1353 | 1399 | Inkling Small |
| LMArena Text: creative writing | 1331 | 1334 | Inkling Small |
| LMArena Vision | Not measured | 1237 | Only Inkling Small measured |
| LMArena Text: English | 1380 | 1421 | Inkling Small |
| LMArena Text: non-English | 1338 | 1401 | Inkling Small |
| LMArena Text: Chinese | 1393 | 1464 | Inkling Small |
| LMArena Text: German | 1361 | 1408 | Inkling Small |
| LMArena Text: Japanese | 1171 | 1401 | Inkling Small |
| LMArena Text: Korean | 1233 | 1367 | Inkling Small |
| LMArena Text: French | 1363 | 1435 | Inkling Small |
| LMArena Text: Spanish | 1353 | 1422 | Inkling Small |
| LMArena Text: Russian | 1359 | 1394 | Inkling Small |
| LMArena Text: Polish | 1334 | 1428 | Inkling Small |
| LMArena Text: multi-turn | 1364 | 1416 | Inkling Small |
| LMArena Text: longer queries | 1366 | 1402 | Inkling Small |
| LMArena Text: writing and language | 1345 | 1357 | Inkling Small |
| LMArena Text: entertainment and media | 1329 | 1352 | Inkling Small |
| LMArena Vision: English | Not measured | 1243 | Only Inkling Small measured |
| LMArena Vision: Chinese | Not measured | 1292 | Only Inkling Small measured |
| LMArena Vision: reading text | Not measured | 1243 | Only Inkling Small measured |
| LMArena Vision: humor | Not measured | 1207 | Only Inkling Small measured |
| LMArena Vision: creative writing | Not measured | 1205 | Only Inkling Small measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M2.5 | Inkling Small | 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 | Thinking Machines Inkling Small |
|---|---|---|
| Maker | MiniMax | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | February 12, 2026 | July 30, 2026 |
| Context window | 205K | 524K |
| Input $/Mtok | $0.30 | $0.45 |
| Output $/Mtok | $1.20 | $1.20 |
| Coding index | 37.2 | 27.3 |
| Independent measurements behind it | 3 | 4 |
| Cost per solved task | $0.62 | $0.16 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M2.5 better than Inkling Small for coding?
Pick MiniMax M2.5 for coding: it scores 37.2 on the Vibe Coding Index against 27.3 for Inkling Small, though on 3 benchmarks against 4. Pick Inkling Small for a lower cost per solved task ($0.16 against $0.62) and a larger context window (524K against 205K tokens).
Which is cheaper, MiniMax M2.5 or Inkling Small?
MiniMax M2.5 costs $0.30 per million input tokens and $1.20 per million output tokens; Inkling Small costs $0.45 and $1.20. Per solved SWE-bench Verified task, MiniMax M2.5 costs $0.62 and Inkling Small $0.16.
Which has the bigger context window, MiniMax M2.5 or Inkling Small?
Inkling Small, with 524K tokens against 205K.
How many benchmarks is the MiniMax M2.5 vs Inkling Small comparison based on?
47 benchmarks have a result for both models as of October 22, 2026. MiniMax M2.5's coding index rests on 3 independent benchmarks and Inkling Small's on 4. Where only one model has a result, the page says so instead of naming a winner.