Model comparison
Kimi K2 Thinking Turbo vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
StepFunSummary
- They share 14 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 2 categories and Step 5 Preview in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 38.4.
- Kimi K2 Thinking Turbo has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 Thinking Turbo | Step 5 Preview | |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 45.8 | 47.9 |
| Released | 2025-11-06 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 21 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Kimi K2 Thinking Turbo: 38.4 (#178), Step 5 Preview: 51.8 (#36)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1322 | 1564 |
| LMArena Coding | 1454 | 1480 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Kimi K2 Thinking Turbo: 32.5 (#75), Step 5 Preview: 40.0 (#57)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1465 |
| CritPt | — | 20.9% |
| Chess Puzzles | 20% | — |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), Step 5 Preview: 46.1 (#72)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Math | 1429 | 1470 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |
| ProofBench | — | 42% |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#69), Step 5 Preview: 41.2 (#112)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1439 | 1470 |
| GPQA Diamond | 84.2% | — |
Multimodal Not comparable
Kimi K2 Thinking Turbo: —, Step 5 Preview: 41.0 (#41)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Step 5 Preview leads
Kimi K2 Thinking Turbo: 51.4 (#109), Step 5 Preview: 53.8 (#54)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1398 | 1432 |
| LMArena Chinese | 1456 | 1519 |
| LMArena Russian | 1391 | 1436 |
| LMArena Spanish | 1406 | 1439 |
| LMArena French | 1425 | — |
| LMArena German | 1390 | — |
| LMArena Japanese | 1357 | — |
| LMArena Korean | 1330 | — |
Instruction Following Step 5 Preview leads
Kimi K2 Thinking Turbo: 74.0 (#109), Step 5 Preview: 76.0 (#50)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1403 | 1444 |
Long Context Step 5 Preview leads
Kimi K2 Thinking Turbo: 43.2 (#102), Step 5 Preview: 44.5 (#64)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1415 | 1455 |
Writing & Preference Step 5 Preview leads
Kimi K2 Thinking Turbo: 60.0 (#104), Step 5 Preview: 62.8 (#71)
| Benchmark | Kimi K2 Thinking Turbo | Step 5 Preview |
|---|---|---|
| LMArena Text | 1415 | 1442 |
| LMArena Creative Writing | 1374 | 1410 |
| LMArena Multi-Turn | 1414 | 1447 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 45.8 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 38.4 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and Step 5 Preview share?
14 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Step 5 Preview has 18.