MiniMax M3 vs Inkling 2 Small
Inkling 2 Small leads MiniMax M3 on coding, 48.9 to 33.6 on the Vibe Coding Index, and Inkling 2 Small costs 1.2x less per output token ($1.00 vs $1.20 per million). Updated November 14, 2026; 38 benchmarks have a result for both.
MiniMax M3 or Inkling 2 Small: which to pick
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 33.6 for MiniMax M3, though on 3 benchmarks against 5.
Pick MiniMax M3 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 38
- MiniMax M3 only
- 80
- Inkling 2 Small only
- 13
- 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
Inkling 2 Small
Inkling 2 Small scores 48.9 against 33.6.
5 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
Inkling 2 Small
Inkling 2 Small leads, 30.6 against 18.9.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only MiniMax M3 has a AA Agentic Index result, 29.5.
Directional only
Reasoning
GPQA Diamond
No call
Only MiniMax M3 has a GPQA Diamond result, 92.7%.
Directional only
Knowledge
MMLU Pro
No call
Only MiniMax M3 has a MMLU Pro result, 84.2%.
Directional only
Web design
Design Arena: websites
No call
Only MiniMax M3 has a Design Arena: websites result, 1249.
Directional only
General
Vals Index
No call
Only Inkling 2 Small has a Vals Index result, 56.1%.
Directional only
Long documents
Listed context window
No call
Both take 1.05M tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Inkling 2 Small
MiniMax M3 $0.0009, Inkling 2 Small $0.0008 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only MiniMax M3 has the number, $0.56.
Directional only
At a glance
- Coding index
- MiniMax M3 33.6 from 5 benchmarks, Inkling 2 Small 48.9 from 3 benchmarks.
- Widest category
- Agentic work, 14.7 points apart on average over 3 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): MiniMax M3 47.6% against Inkling 2 Small 81.5%, 34.0 points apart on a 0 to 100 scale.
- Output price
- MiniMax M3 $1.20 against Inkling 2 Small $1.00 per million output tokens, 1.2x apart.
- Context window
- Both take 1.05M tokens.
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 M3 | Bars | Inkling 2 Small | Ties |
|---|---|---|---|---|
| Coding | 2 | 10 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 3 | ||
| Reasoning | 2 | 4 | ||
| Knowledge | 2 | 1 | ||
| General | 10 | 3 | ||
| All shared boards | 16 | 22 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index210
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| LMArena WebDev | 1484 | 1647 | Inkling 2 Small |
| AA Coding Index | 58.6 | Not measured | Only MiniMax M3 measured |
| LiveCodeBench (Vals AI) | 82.2% | Not measured | Only MiniMax M3 measured |
| SWE-bench Verified (Vals AI) | 75.0% | Not measured | Only MiniMax M3 measured |
| Terminal-Bench 4 (Vals AI) | 1.0% | 12.6% | Inkling 2 Small |
| Vibe Code Bench (Vals AI) | 47.6% | 81.5% | Inkling 2 Small |
| Code migration (Vals AI) | 19.9% | Not measured | Only MiniMax M3 measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only Inkling 2 Small measured |
| Terminal-Bench 2.1 (Vals AI) | 53.6% | Not measured | Only MiniMax M3 measured |
| SWE-bench Multimodal (Vals AI) | 33.3% | 43.1% | Inkling 2 Small |
| Vibe Code Bench 1-100 (Vals AI) | 9.2% | Not measured | Only MiniMax M3 measured |
| SkillsBench (Vals AI) | 51.5% | Not measured | Only MiniMax M3 measured |
| CyberBench (Vals AI) | 65.0% | 72.7% | Inkling 2 Small |
| SciCode | 47.1% | 52.3% | Inkling 2 Small |
| Terminal-Bench Hard (Artificial Analysis run) | 42.4% | Not measured | Only MiniMax M3 measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 2.0% | 13.1% | Inkling 2 Small |
| FrontierCode 2.0 | 21.9% | 25.4% | Inkling 2 Small |
| FrontierCode | 14.7% | Not measured | Only MiniMax M3 measured |
| ALE-Bench | 640.0 | Not measured | Only MiniMax M3 measured |
| LMArena Text: coding | 1468 | 1455 | MiniMax M3 |
| LMArena Text: software and IT | 1463 | 1443 | MiniMax M3 |
| LMArena WebDev: React | 1479 | 1660 | Inkling 2 Small |
| LMArena WebDev: HTML | 1460 | 1661 | Inkling 2 Small |
| LMArena WebDev: from an image | 1473 | Not measured | Only MiniMax M3 measured |
| SWE-Bench Pro V2 | Not measured | 97.7% | Only Inkling 2 Small measured |
| GameBench 2 | 29.0 | Not measured | Only MiniMax M3 measured |
| Terminal-Bench 4.0 | 7.3% | Not measured | Only MiniMax M3 measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Intelligence Index | 18.9 | 30.6 | Inkling 2 Small |
| Epoch Capabilities Index | 147.7 | Not measured | Only MiniMax M3 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| AA Agentic Index | 29.5 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building web apps | 1186 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building full-stack apps | 1175 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building mobile apps | 1169 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building Android apps | 1156 | Not measured | Only MiniMax M3 measured |
| Design Arena: agents building games | 1110 | Not measured | Only MiniMax M3 measured |
| Design Arena: HTML slides | 1076 | Not measured | Only MiniMax M3 measured |
| Design Arena: PowerPoint slides | 1171 | Not measured | Only MiniMax M3 measured |
| Design Arena: spreadsheets | 1159 | Not measured | Only MiniMax M3 measured |
| SREBench (Vals AI) | Not measured | 1.9% | Only Inkling 2 Small measured |
| Finance Agent (Vals AI) | 48.3% | Not measured | Only MiniMax M3 measured |
| Tax Agent Bench (Vals AI) | 20.6% | 38.9% | Inkling 2 Small |
| Legal Research Bench (Vals AI) | 29.8% | 46.6% | Inkling 2 Small |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 21.7% | Only Inkling 2 Small measured |
| Excel Modeling Benchmark (Vals AI) | 47.8% | Not measured | Only MiniMax M3 measured |
| BioMysteryBench (Vals AI) | Not measured | 70.0% | Only Inkling 2 Small measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 2.9% | Only Inkling 2 Small measured |
| Vals Science Index | Not measured | 32.7% | Only Inkling 2 Small measured |
| τ²-Bench Telecom | 88.9% | Not measured | Only MiniMax M3 measured |
| APEX-Agents | 37.7% | 46.8% | Inkling 2 Small |
| OSWorld 2.0 | 4.6% | Not measured | Only MiniMax M3 measured |
| Vending-Bench 2 | $2,158 | Not measured | Only MiniMax M3 measured |
| MCP Atlas | Not measured | 85.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 21 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| GPQA Diamond | 92.7% | Not measured | Only MiniMax M3 measured |
| MysteryMechanism (Vals AI) | Not measured | 25.2% | Only Inkling 2 Small measured |
| MMMU Pro (Vals AI) | 81.2% | Not measured | Only MiniMax M3 measured |
| GPQA Diamond (Artificial Analysis run) | 92.9% | Not measured | Only MiniMax M3 measured |
| Humanity's Last Exam (Artificial Analysis run) | 39.0% | 44.1% | Inkling 2 Small |
| HLE-Diamond (Artificial Analysis run) | 16.0% | 28.7% | Inkling 2 Small |
| CritPt v2, hard subset (Artificial Analysis run) | 28.0% | 35.0% | Inkling 2 Small |
| GPQA Diamond (Epoch AI run) | 90.9% | Not measured | Only MiniMax M3 measured |
| ARC-AGI | Not measured | 96.5% | Only Inkling 2 Small measured |
| ARC-AGI-2 | Not measured | 81.7% | Only Inkling 2 Small measured |
| SimpleBench | 45.8% | Not measured | Only MiniMax M3 measured |
| Chess puzzles | 17.0% | Not measured | Only MiniMax M3 measured |
| Mystery game puzzles | 8.0% | Not measured | Only MiniMax M3 measured |
| LMArena Text: hard prompts | 1442 | 1421 | MiniMax M3 |
| LMArena Text: expert | 1460 | 1478 | Inkling 2 Small |
| LMArena Text: hard prompts in English | 1452 | 1424 | MiniMax M3 |
| LMArena Vision: diagrams | 1266 | Not measured | Only MiniMax M3 measured |
| LMArena Vision: homework | 1266 | Not measured | Only MiniMax M3 measured |
| Neither model has a result on the other 8 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| OTIS Mock AIME | 71.1% | Not measured | Only MiniMax M3 measured |
| ProofBench | 18.0% | Not measured | Only MiniMax M3 measured |
| LMArena Text: math | 1423 | Not measured | Only MiniMax M3 measured |
| LMArena Text: mathematical work | 1443 | Not measured | Only MiniMax M3 measured |
| MathArena | Not measured | 42.4% | Only Inkling 2 Small measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| MMLU Pro | 84.2% | Not measured | Only MiniMax M3 measured |
| LegalBench (Vals AI) | 85.4% | Not measured | Only MiniMax M3 measured |
| CorpFin (Vals AI) | 68.1% | Not measured | Only MiniMax M3 measured |
| TaxEval (Vals AI) | 72.7% | Not measured | Only MiniMax M3 measured |
| MortgageTax (Vals AI) | 68.4% | Not measured | Only MiniMax M3 measured |
| MedCode (Vals AI) | 46.3% | Not measured | Only MiniMax M3 measured |
| AA-Omniscience | -5.5 | 16.1 | Inkling 2 Small |
| LMArena Text: science | 1446 | 1409 | MiniMax M3 |
| LMArena Text: medicine and healthcare | 1433 | Not measured | Only MiniMax M3 measured |
| LMArena Text: legal and government | 1430 | Not measured | Only MiniMax M3 measured |
| LMArena Text: business and finance | 1431 | 1415 | MiniMax M3 |
| Neither model has a result on the other 10 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| Design Arena: websites | 1249 | Not measured | Only MiniMax M3 measured |
| Design Arena: UI components | 1235 | Not measured | Only MiniMax M3 measured |
| Design Arena: game dev | 1200 | Not measured | Only MiniMax M3 measured |
| Design Arena: data viz | 1229 | Not measured | Only MiniMax M3 measured |
| Design Arena: 3D | 1189 | Not measured | Only MiniMax M3 measured |
| Design Arena: all code categories | 1236 | Not measured | Only MiniMax M3 measured |
| Design Arena: SVG | 1146 | Not measured | Only MiniMax M3 measured |
| Design Arena: ASCII art | 1149 | Not measured | Only MiniMax M3 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index103
| Benchmark | MiniMax M3 | Inkling 2 Small | Leader |
|---|---|---|---|
| Vals Index | Not measured | 56.1% | Only Inkling 2 Small measured |
| Public Benefits Bench (Vals AI) | 64.1% | Not measured | Only MiniMax M3 measured |
| SAGE (Vals AI) | 85.5% | 88.6% | Inkling 2 Small |
| MedScribe (Vals AI) | 87.3% | Not measured | Only MiniMax M3 measured |
| Vals Multimodal Index | 60.0% | Not measured | Only MiniMax M3 measured |
| IFBench | 82.9% | Not measured | Only MiniMax M3 measured |
| Long context reasoning (AA-LCR) | 83.0% | 83.3% | Inkling 2 Small |
| GDPval-AA | 1250 | 1630 | Inkling 2 Small |
| DTBench | 78.9% | Not measured | Only MiniMax M3 measured |
| LMCA | 33.7% | Not measured | Only MiniMax M3 measured |
| Surface Evolver Bench | 55.0% | Not measured | Only MiniMax M3 measured |
| LMArena Text | 1428 | 1403 | MiniMax M3 |
| LMArena Text: instruction following | 1428 | 1408 | MiniMax M3 |
| LMArena Text: creative writing | 1395 | 1348 | MiniMax M3 |
| LMArena Vision | 1249 | Not measured | Only MiniMax M3 measured |
| LMArena Text: English | 1440 | 1418 | MiniMax M3 |
| LMArena Text: non-English | 1414 | 1390 | MiniMax M3 |
| LMArena Text: Chinese | 1465 | Not measured | Only MiniMax M3 measured |
| LMArena Text: German | 1429 | Not measured | Only MiniMax M3 measured |
| LMArena Text: Japanese | 1363 | Not measured | Only MiniMax M3 measured |
| LMArena Text: Korean | 1365 | Not measured | Only MiniMax M3 measured |
| LMArena Text: French | 1439 | Not measured | Only MiniMax M3 measured |
| LMArena Text: Spanish | 1424 | Not measured | Only MiniMax M3 measured |
| LMArena Text: Russian | 1422 | 1377 | MiniMax M3 |
| LMArena Text: Polish | 1417 | Not measured | Only MiniMax M3 measured |
| LMArena Text: multi-turn | 1439 | 1408 | MiniMax M3 |
| LMArena Text: longer queries | 1440 | 1403 | MiniMax M3 |
| LMArena Text: writing and language | 1411 | 1381 | MiniMax M3 |
| LMArena Text: entertainment and media | 1398 | 1359 | MiniMax M3 |
| LMArena Vision: English | 1260 | Not measured | Only MiniMax M3 measured |
| LMArena Vision: Chinese | 1310 | Not measured | Only MiniMax M3 measured |
| LMArena Vision: reading text | 1256 | Not measured | Only MiniMax M3 measured |
| LMArena Vision: humor | 1235 | Not measured | Only MiniMax M3 measured |
| LMArena Vision: recognizing things | 1196 | Not measured | Only MiniMax M3 measured |
| LMArena Vision: creative writing | 1232 | Not measured | Only MiniMax M3 measured |
| LMArena Document | 1437 | Not measured | Only MiniMax M3 measured |
| EQ-Bench 4 | 1140 | Not measured | Only MiniMax M3 measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | MiniMax M3 | Inkling 2 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
Inkling 2 Small costs less
Repository review
50K input + 3K output tokens
Inkling 2 Small costs less
Agent loop
200K input + 10K output tokens
Inkling 2 Small 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 M3 | Thinking Machines Inkling 2 Small |
|---|---|---|
| Maker | MiniMax | Thinking Machines |
| Weights | Open weights | Open weights |
| Released | May 31, 2026 | November 9, 2026 |
| Context window | 1.05M | 1.05M |
| Input $/Mtok | $0.30 | $0.30 |
| Output $/Mtok | $1.20 | $1.00 |
| Coding index | 33.6 | 48.9 |
| Independent measurements behind it | 5 | 3 |
| Cost per solved task | $0.56 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is MiniMax M3 better than Inkling 2 Small for coding?
Pick Inkling 2 Small for coding: it scores 48.9 on the Vibe Coding Index against 33.6 for MiniMax M3, though on 3 benchmarks against 5. Pick MiniMax M3 for work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, MiniMax M3 or Inkling 2 Small?
MiniMax M3 costs $0.30 per million input tokens and $1.20 per million output tokens; Inkling 2 Small costs $0.30 and $1.00. Cost per solved task is known for MiniMax M3 only.
Which has the bigger context window, MiniMax M3 or Inkling 2 Small?
Neither: both take 1.05M tokens.
How many benchmarks is the MiniMax M3 vs Inkling 2 Small comparison based on?
38 benchmarks have a result for both models as of November 14, 2026. MiniMax M3's coding index rests on 5 independent benchmarks and Inkling 2 Small's on 3. Where only one model has a result, the page says so instead of naming a winner.