Model comparison
MiMo-V2.5 vs Trinity Large Thinking
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 38.6 on the Noometry Index.
Last verified . 20 shared benchmarks.
Arcee AISummary
- They share 20 benchmarks with published results for both. MiMo-V2.5 scores higher in 6 categories and Trinity Large Thinking in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where MiMo-V2.5 leads 28.6 to 16.9.
- The biggest single-benchmark swing is SciCode: 43.1% for MiMo-V2.5 and 36.1% for Trinity Large Thinking.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.25 / $0.80 for Trinity Large Thinking.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 262K.
Side by side
| MiMo-V2.5 | Trinity Large Thinking | |
|---|---|---|
| Provider | Xiaomi | Arcee AI |
| Noometry Index | 43.4 | 38.6 |
| Released | 2026-04-22 | 2026-04-01 |
| Weights | Open | Open |
| Context window | 1.05M | 262K |
| Max output | 131K | 80K |
| Input $ / M tokens | $0.14 | $0.25 |
| Output $ / M tokens | $0.28 | $0.80 |
| Results tracked | 23 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Trinity Large Thinking: 34.1 (#244)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena WebDev | 1438 | 1238 |
| SciCode | 43.1% | 36.1% |
| LMArena Coding | 1469 | 1381 |
| ALE-Bench | 513.95 | — |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Trinity Large Thinking: 16.9 (#298)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| CritPt | 3.7% | 0.9% |
| LMArena Hard Prompts | 1450 | 1350 |
| NYT Connections (extended) | — | 16.5% |
| Thematic Generalization | — | 41.6% |
| Surface Evolver Bench | — | 15.6% |
Math Too close to call
MiMo-V2.5: 36.8 (#163), Trinity Large Thinking: 37.6 (#149)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Math | 1436 | 1366 |
| ProofBench | 16% | — |
Knowledge Too close to call
MiMo-V2.5: 40.8 (#115), Trinity Large Thinking: 40.9 (#113)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Expert | 1460 | 1360 |
| Vectara Hallucination Rate | — | 6.9% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Trinity Large Thinking: —
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Trinity Large Thinking: 46.2 (#160)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Non-English | 1404 | 1325 |
| LMArena Chinese | 1468 | 1373 |
| LMArena French | 1447 | 1374 |
| LMArena German | 1421 | 1356 |
| LMArena Japanese | 1306 | 1311 |
| LMArena Korean | 1363 | 1306 |
| LMArena Russian | 1395 | 1337 |
| LMArena Spanish | 1416 | 1357 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Trinity Large Thinking: 70.5 (#162)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Instruction Following | 1434 | 1334 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Trinity Large Thinking: 41.3 (#144)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Longer Query | 1445 | 1355 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Trinity Large Thinking: 53.8 (#158)
| Benchmark | MiMo-V2.5 | Trinity Large Thinking |
|---|---|---|
| LMArena Text | 1428 | 1340 |
| LMArena Creative Writing | 1393 | 1320 |
| LMArena Multi-Turn | 1445 | 1342 |
Frequently asked questions
Is MiMo-V2.5 better than Trinity Large Thinking?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 38.6 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or Trinity Large Thinking?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Trinity Large Thinking lists at $0.25 and $0.80.
Is MiMo-V2.5 or Trinity Large Thinking better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 262K.
How many benchmarks do MiMo-V2.5 and Trinity Large Thinking share?
20 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Trinity Large Thinking has 24.