Model comparison
Kimi K2 Thinking Turbo vs MiMo-V2.5
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 43.4 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 3 categories and MiMo-V2.5 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 Thinking Turbo leads 47.4 to 36.8.
Side by side
| Kimi K2 Thinking Turbo | MiMo-V2.5 | |
|---|---|---|
| Provider | Moonshot AI | Xiaomi |
| Noometry Index | 45.8 | 43.4 |
| Released | 2025-11-06 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.14 |
| Output $ / M tokens | — | $0.28 |
| Results tracked | 21 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
Kimi K2 Thinking Turbo: 38.4 (#178), MiMo-V2.5: 43.9 (#81)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena WebDev | 1322 | 1438 |
| LMArena Coding | 1454 | 1469 |
| SciCode | — | 43.1% |
| ALE-Bench | — | 513.95 |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), MiMo-V2.5: 28.6 (#101)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1450 |
| CritPt | — | 3.7% |
| Chess Puzzles | 20% | — |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), MiMo-V2.5: 36.8 (#163)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Math | 1429 | 1436 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| ProofBench | — | 16% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#69), MiMo-V2.5: 40.8 (#115)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Expert | 1439 | 1460 |
| GPQA Diamond | 84.2% | — |
Multimodal Not comparable
Kimi K2 Thinking Turbo: —, MiMo-V2.5: 39.8 (#54)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Vision | — | 1247 |
Multilingual Too close to call
Kimi K2 Thinking Turbo: 51.4 (#109), MiMo-V2.5: 51.9 (#99)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Non-English | 1398 | 1404 |
| LMArena Chinese | 1456 | 1468 |
| LMArena French | 1425 | 1447 |
| LMArena German | 1390 | 1421 |
| LMArena Japanese | 1357 | 1306 |
| LMArena Korean | 1330 | 1363 |
| LMArena Russian | 1391 | 1395 |
| LMArena Spanish | 1406 | 1416 |
Instruction Following MiMo-V2.5 leads
Kimi K2 Thinking Turbo: 74.0 (#109), MiMo-V2.5: 75.5 (#60)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1434 |
Long Context Too close to call
Kimi K2 Thinking Turbo: 43.2 (#102), MiMo-V2.5: 44.2 (#73)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Longer Query | 1415 | 1445 |
Writing & Preference MiMo-V2.5 leads
Kimi K2 Thinking Turbo: 60.0 (#104), MiMo-V2.5: 61.6 (#86)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5 |
|---|---|---|
| LMArena Text | 1415 | 1428 |
| LMArena Creative Writing | 1374 | 1393 |
| LMArena Multi-Turn | 1414 | 1445 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than MiMo-V2.5?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 43.4 on the Noometry Index.
Is Kimi K2 Thinking Turbo or MiMo-V2.5 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 38.4 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and MiMo-V2.5 share?
18 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and MiMo-V2.5 has 23.