Model comparison
Kimi K2 Thinking Turbo vs MiMo-V2.5-Pro
Kimi K2 Thinking Turbo and MiMo-V2.5-Pro score almost the same on the Noometry Index (45.8 vs 45.2), so choose on price, context window or the category you care about most.
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-Pro in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiMo-V2.5-Pro leads 47.4 to 38.4.
Side by side
| Kimi K2 Thinking Turbo | MiMo-V2.5-Pro | |
|---|---|---|
| Provider | Moonshot AI | Xiaomi |
| Noometry Index | 45.8 | 45.2 |
| Released | 2025-11-06 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 21 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5-Pro leads
Kimi K2 Thinking Turbo: 38.4 (#178), MiMo-V2.5-Pro: 47.4 (#60)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena WebDev | 1322 | 1479 |
| LMArena Coding | 1454 | 1503 |
| SciCode | — | 50.2% |
| ALE-Bench | — | 899.8 |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), MiMo-V2.5-Pro: 26.8 (#130)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1488 |
| NYT Connections (extended) | — | 34.4% |
| CritPt | — | 4% |
| Chess Puzzles | 20% | — |
| DTBench | — | 84.5% |
| LMCA | — | 29.5% |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), MiMo-V2.5-Pro: 40.0 (#96)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Math | 1429 | 1481 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| ProofBench | — | 22% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#69), MiMo-V2.5-Pro: 42.2 (#98)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Expert | 1439 | 1503 |
| GPQA Diamond | 84.2% | — |
Multilingual MiMo-V2.5-Pro leads
Kimi K2 Thinking Turbo: 51.4 (#109), MiMo-V2.5-Pro: 55.1 (#34)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Non-English | 1398 | 1449 |
| LMArena Chinese | 1456 | 1507 |
| LMArena French | 1425 | 1488 |
| LMArena German | 1390 | 1458 |
| LMArena Japanese | 1357 | 1412 |
| LMArena Korean | 1330 | 1437 |
| LMArena Russian | 1391 | 1450 |
| LMArena Spanish | 1406 | 1471 |
Instruction Following MiMo-V2.5-Pro leads
Kimi K2 Thinking Turbo: 74.0 (#109), MiMo-V2.5-Pro: 77.5 (#21)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Instruction Following | 1403 | 1477 |
Long Context MiMo-V2.5-Pro leads
Kimi K2 Thinking Turbo: 43.2 (#102), MiMo-V2.5-Pro: 45.4 (#37)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Longer Query | 1415 | 1483 |
Writing & Preference MiMo-V2.5-Pro leads
Kimi K2 Thinking Turbo: 60.0 (#104), MiMo-V2.5-Pro: 65.3 (#49)
| Benchmark | Kimi K2 Thinking Turbo | MiMo-V2.5-Pro |
|---|---|---|
| LMArena Text | 1415 | 1465 |
| LMArena Creative Writing | 1374 | 1440 |
| LMArena Multi-Turn | 1414 | 1477 |
| EQ-Bench Creative Writing | — | 1493 |
| EQ-Bench 4 | — | 1208 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than MiMo-V2.5-Pro?
Kimi K2 Thinking Turbo and MiMo-V2.5-Pro score almost the same on the Noometry Index (45.8 vs 45.2), so choose on price, context window or the category you care about most.
Is Kimi K2 Thinking Turbo or MiMo-V2.5-Pro better for coding?
MiMo-V2.5-Pro scores higher on coding benchmarks: 47.4 versus 38.4 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and MiMo-V2.5-Pro share?
18 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and MiMo-V2.5-Pro has 27.