Model comparison
Inkling vs MiMo-V2.5-Pro
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 44.1 on the Noometry Index.
Last verified . 26 shared benchmarks.
Summary
- They share 26 benchmarks with published results for both. Inkling scores higher in 2 categories and MiMo-V2.5-Pro in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Inkling leads 40.4 to 26.8.
- The biggest single-benchmark swing is ProofBench: 0% for Inkling and 22% for MiMo-V2.5-Pro.
- MiMo-V2.5-Pro is cheaper at $0.43 / $0.87 per million input/output tokens, against $1.87 / $4.68 for Inkling.
- MiMo-V2.5-Pro accepts more context: 1.05M tokens versus 66K.
Side by side
| Inkling | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Thinking Machines Lab | Xiaomi |
| Noometry Index | 44.1 | 45.2 |
| Released | 2026-07-15 | 2026-04-22 |
| Weights | Open | Open |
| Context window | 66K | 1.05M |
| Max output | 66K | 131K |
| Input $ / M tokens | $1.87 | $0.43 |
| Output $ / M tokens | $4.68 | $0.87 |
| Results tracked | 41 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Inkling: 34.5 (#234), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1413 | 1479 |
| SciCode | 47% | 50.2% |
| LMArena Coding | 1464 | 1503 |
| ALE-Bench | 946 | 899.8 |
| FrontierCode | 14% | — |
| FrontierSWE | 4.1% | — |
| WeirdML | 32.3% | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), MiMo-V2.5-Pro: —
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| CritPt | 5.4% | 4% |
| LMArena Hard Prompts | 1451 | 1488 |
| DTBench | 87.5% | 84.5% |
| LMCA | 37.6% | 29.5% |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| NYT Connections (extended) | — | 34.4% |
| ARC-AGI-1 | 79.5% | — |
| Chess Puzzles | 21% | — |
| Epoch Capabilities Index | 148.54 | — |
Math MiMo-V2.5-Pro leads
Inkling: 31.3 (#225), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| ProofBench | 0% | 22% |
| LMArena Math | 1479 | 1481 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1465 | 1503 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
Multilingual MiMo-V2.5-Pro leads
Inkling: 54.0 (#52), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1434 | 1449 |
| LMArena Chinese | 1490 | 1507 |
| LMArena French | 1458 | 1488 |
| LMArena German | 1446 | 1458 |
| LMArena Japanese | 1429 | 1412 |
| LMArena Korean | 1404 | 1437 |
| LMArena Russian | 1429 | 1450 |
| LMArena Spanish | 1448 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Inkling: 75.1 (#71), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1426 | 1477 |
Long Context MiMo-V2.5-Pro leads
Inkling: 43.8 (#86), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1434 | 1483 |
Writing & Preference Too close to call
Inkling: 65.2 (#51), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Inkling | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1441 | 1465 |
| LMArena Creative Writing | 1387 | 1440 |
| EQ-Bench Creative Writing | 1611 | 1493 |
| EQ-Bench 4 | 1226 | 1208 |
| LMArena Multi-Turn | 1436 | 1477 |
Frequently asked questions
Is Inkling better than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the stronger model overall, scoring 45.2 to 44.1 on the Noometry Index.
Which is cheaper, Inkling or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. It lists at $0.43 per million input tokens and $0.87 per million output tokens; Inkling lists at $1.87 and $4.68.
Is Inkling or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 34.5 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5-Pro does, with 1.05M tokens against 66K.
How many benchmarks do Inkling and MiMo-V2.5-Pro share?
26 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and MiMo-V2.5-Pro has 27.