# Inkling vs MiniMax-M2.5

> Inkling is the stronger model overall, scoring 44.1 to 38.1 on the Noometry Index. MiniMax-M2.5 costs 4.9× less per token, which makes it the better buy when Inkling's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/inkling-vs-minimax-m2-5
- Last updated: 2026-10-10
- Shared benchmarks: 24

## Summary

- They share 24 benchmarks with published results for both. Inkling scores higher in 7 categories and MiniMax-M2.5 in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.6 to 17.6.
- The biggest single-benchmark swing is ARC-AGI-2: 36.5% for Inkling and 4.9% for MiniMax-M2.5.
- MiniMax-M2.5 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- MiniMax-M2.5 accepts more context: 205K tokens versus 66K.

## Snapshot

| | Inkling | MiniMax-M2.5 |
|---|---|---|
| Provider | Thinking Machines Lab | MiniMax |
| Noometry Index | 44.1 | 38.1 |
| Rank | 75 | 181 |
| Context | 66K | 205K |
| Input $/M | $1.87 | $0.30 |
| Output $/M | $4.68 | $1.20 |
| Weights | Open | Open |

## Coding

- Inkling: 34.1 (#229)
- MiniMax-M2.5: 47.9 (#53)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| LMArena WebDev | 1412 | 1386 |
| LMArena Coding | 1463 | 1380 |
| ALE-Bench | 946 | 618.17 |
| FrontierCode | 14% | — |
| SWE-bench Verified (bash only) | — | 75.8% |
| SWE-bench Multilingual | — | 68.3% |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |

## Agentic & Tool Use

- Inkling: 29.5 (#76)
- MiniMax-M2.5: 30.2 (#70)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
| Vending-Bench 2 | — | -23.16 |

## Reasoning

- Inkling: 40.6 (#48)
- MiniMax-M2.5: 17.6 (#281)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| ARC-AGI-2 | 36.5% | 4.9% |
| ARC-AGI-1 | 79.5% | 63.7% |
| LMArena Hard Prompts | 1452 | 1372 |
| Epoch Capabilities Index | 148.6 | 146.68 |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |

## Math

- Inkling: 31.2 (#198)
- MiniMax-M2.5: 25.8 (#242)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| ProofBench | 0% | 4% |
| LMArena Math | 1482 | 1378 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |

## Knowledge

- Inkling: 55.2 (#44)
- MiniMax-M2.5: 38.6 (#132)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| LMArena Expert | 1468 | 1378 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| Vectara Hallucination Rate | — | 9.1% |

## Multilingual

- Inkling: 54.2 (#49)
- MiniMax-M2.5: 47.3 (#147)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1434 | 1338 |
| LMArena Chinese | 1495 | 1392 |
| LMArena French | 1453 | 1363 |
| LMArena German | 1456 | 1361 |
| LMArena Japanese | 1428 | 1169 |
| LMArena Korean | 1401 | 1232 |
| LMArena Russian | 1430 | 1359 |
| LMArena Spanish | 1442 | 1354 |

## Instruction Following

- Inkling: 75.3 (#65)
- MiniMax-M2.5: 71.7 (#143)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1427 | 1353 |

## Long Context

- Inkling: 43.9 (#79)
- MiniMax-M2.5: 37.4 (#211)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1436 | 1367 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |

## Writing & Preference

- Inkling: 65.5 (#48)
- MiniMax-M2.5: 54.1 (#149)

| Benchmark | Inkling | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1443 | 1359 |
| LMArena Creative Writing | 1390 | 1331 |
| EQ-Bench Creative Writing | 1611 | 1361 |
| LMArena Multi-Turn | 1436 | 1364 |
| EQ-Bench 4 | 1226 | — |

## FAQ

### Is Inkling better than MiniMax-M2.5?

Inkling is the stronger model overall, scoring 44.1 to 38.1 on the Noometry Index. MiniMax-M2.5 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-M2.5?

MiniMax-M2.5 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-M2.5 better for coding?

MiniMax-M2.5 scores higher on coding benchmarks: 47.9 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

MiniMax-M2.5 does, with 205K tokens against 66K.

### How many benchmarks do Inkling and MiniMax-M2.5 share?

24 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and MiniMax-M2.5 has 33.