Model comparison
Inkling-Small vs MiMo-V2.5
Inkling-Small is the stronger model overall, scoring 46.5 to 43.4 on the Noometry Index. MiMo-V2.5 costs 3.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Last verified . 22 shared benchmarks.
Summary
- They share 22 benchmarks with published results for both. Inkling-Small scores higher in 3 categories and MiMo-V2.5 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling-Small leads 38.6 to 28.6.
- The biggest single-benchmark swing is ProofBench: 6% for Inkling-Small and 16% for MiMo-V2.5.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.45 / $1.20 for Inkling-Small.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 524K.
Side by side
| Inkling-Small | MiMo-V2.5 | |
|---|---|---|
| Provider | Thinking Machines Lab | Xiaomi |
| Noometry Index | 46.5 | 43.4 |
| Released | 2026-07-15 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 524K | 1.05M |
| Max output | 1.05M | 131K |
| Input $ / M tokens | $0.45 | $0.14 |
| Output $ / M tokens | $1.20 | $0.28 |
| Results tracked | 33 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Inkling-Small: 43.6 (#85), MiMo-V2.5: 43.9 (#81)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1409 | 1438 |
| SciCode | 48.7% | 43.1% |
| LMArena Coding | 1451 | 1469 |
| ALE-Bench | — | 513.95 |
Reasoning Inkling-Small leads
Inkling-Small: 38.6 (#63), MiMo-V2.5: 28.6 (#101)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| CritPt | 8.3% | 3.7% |
| LMArena Hard Prompts | 1423 | 1450 |
| ARC-AGI-2 | 40.1% | — |
| ARC-AGI-1 | 84% | — |
| Chess Puzzles | 18% | — |
| Mystery Game Puzzles | 6% | — |
| Epoch Capabilities Index | 150.15 | — |
Math Inkling-Small leads
Inkling-Small: 45.1 (#77), MiMo-V2.5: 36.8 (#163)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| ProofBench | 6% | 16% |
| LMArena Math | 1459 | 1436 |
| FrontierMath (Tiers 1-3) | 46.3% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 90% | — |
Knowledge Inkling-Small leads
Inkling-Small: 48.2 (#77), MiMo-V2.5: 40.8 (#115)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1442 | 1460 |
| GPQA Diamond | 88.5% | — |
| SimpleQA Verified | 19.1% | — |
Multimodal Too close to call
Inkling-Small: 39.1 (#62), MiMo-V2.5: 39.8 (#54)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | 1235 | 1247 |
Multilingual Too close to call
Inkling-Small: 51.7 (#104), MiMo-V2.5: 51.9 (#99)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1402 | 1404 |
| LMArena Chinese | 1465 | 1468 |
| LMArena French | 1436 | 1447 |
| LMArena German | 1405 | 1421 |
| LMArena Japanese | 1405 | 1306 |
| LMArena Korean | 1363 | 1363 |
| LMArena Russian | 1391 | 1395 |
| LMArena Spanish | 1428 | 1416 |
Instruction Following MiMo-V2.5 leads
Inkling-Small: 73.8 (#114), MiMo-V2.5: 75.5 (#60)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1399 | 1434 |
Long Context MiMo-V2.5 leads
Inkling-Small: 42.7 (#118), MiMo-V2.5: 44.2 (#73)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1401 | 1445 |
Writing & Preference MiMo-V2.5 leads
Inkling-Small: 59.6 (#107), MiMo-V2.5: 61.6 (#86)
| Benchmark | Inkling-Small | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1414 | 1428 |
| LMArena Creative Writing | 1331 | 1393 |
| LMArena Multi-Turn | 1418 | 1445 |
| EQ-Bench Creative Writing | 1491 | — |
Frequently asked questions
Is Inkling-Small better than MiMo-V2.5?
Inkling-Small is the stronger model overall, scoring 46.5 to 43.4 on the Noometry Index. MiMo-V2.5 costs 3.6× less per token, which makes it the better buy when Inkling-Small's lead doesn't matter for your workload.
Which is cheaper, Inkling-Small or MiMo-V2.5?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Inkling-Small lists at $0.45 and $1.20.
Is Inkling-Small or MiMo-V2.5 better for coding?
They score almost the same on coding (43.6 vs 43.9); test both on your own repository before choosing.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 524K.
How many benchmarks do Inkling-Small and MiMo-V2.5 share?
22 benchmarks have published results for both models. Inkling-Small has 33 scored results on Noometry and MiMo-V2.5 has 23.