Model comparison
Inkling vs MiniMax-M2.1
Inkling is the stronger model overall, scoring 44.1 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 4.9× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
MiniMaxSummary
- They share 19 benchmarks with published results for both. Inkling scores higher in 7 categories and MiniMax-M2.1 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 16.6.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- MiniMax-M2.1 accepts more context: 205K tokens versus 66K.
Side by side
| Inkling | MiniMax-M2.1 | |
|---|---|---|
| Provider | Thinking Machines Lab | MiniMax |
| Noometry Index | 44.1 | 38.9 |
| Released | 2026-07-15 | 2025-12-23 |
| Weights | Open | Open |
| Context window | 66K | 205K |
| Max output | 66K | 131K |
| Input $ / M tokens | $1.87 | $0.30 |
| Output $ / M tokens | $4.68 | $1.20 |
| Results tracked | 41 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Inkling: 34.5 (#234), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena WebDev | 1413 | 1384 |
| LMArena Coding | 1464 | 1421 |
| ALE-Bench | 946 | 623.83 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
Agentic & Tool Use Inkling leads
Inkling: 29.6 (#85), MiniMax-M2.1: 27.9 (#98)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1411 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 11.2% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |
Math MiniMax-M2.1 leads
Inkling: 31.3 (#225), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1479 | 1397 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1465 | 1431 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 11.8% |
Multilingual Inkling leads
Inkling: 54.0 (#52), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1434 | 1378 |
| LMArena Chinese | 1490 | 1430 |
| LMArena French | 1458 | 1404 |
| LMArena German | 1446 | 1381 |
| LMArena Japanese | 1429 | 1287 |
| LMArena Korean | 1404 | 1298 |
| LMArena Russian | 1429 | 1387 |
| LMArena Spanish | 1448 | 1397 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1426 | 1400 |
Long Context Too close to call
Inkling: 43.8 (#86), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1434 | 1416 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Inkling | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1441 | 1392 |
| LMArena Creative Writing | 1387 | 1361 |
| LMArena Multi-Turn | 1436 | 1396 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than MiniMax-M2.1?
Inkling is the stronger model overall, scoring 44.1 to 38.9 on the Noometry Index. MiniMax-M2.1 costs 4.9× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.
Which is cheaper, Inkling or MiniMax-M2.1?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 66K.
How many benchmarks do Inkling and MiniMax-M2.1 share?
19 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and MiniMax-M2.1 has 22.