Model comparison
Kimi K2.5 Instant vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.6 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. Kimi K2.5 Instant scores higher in 0 categories and Step 5 Preview in 9 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 5 Preview leads 40.0 to 29.7.
- Kimi K2.5 Instant has downloadable open weights; the other is API-only.
Side by side
| Kimi K2.5 Instant | Step 5 Preview | |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 43.6 | 47.9 |
| Released | — | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 18 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Kimi K2.5 Instant: 42.6 (#97), Step 5 Preview: 51.8 (#36)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1404 | 1564 |
| LMArena Coding | 1484 | 1480 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Kimi K2.5 Instant: 29.7 (#90), Step 5 Preview: 40.0 (#57)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1465 |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
Kimi K2.5 Instant: 39.4 (#105), Step 5 Preview: 46.1 (#72)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Math | 1442 | 1470 |
| ProofBench | — | 42% |
Knowledge Too close to call
Kimi K2.5 Instant: 40.2 (#123), Step 5 Preview: 41.2 (#112)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1440 | 1470 |
Multimodal Too close to call
Kimi K2.5 Instant: 40.2 (#50), Step 5 Preview: 41.0 (#41)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1254 | 1267 |
Multilingual Step 5 Preview leads
Kimi K2.5 Instant: 52.0 (#94), Step 5 Preview: 53.8 (#54)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1406 | 1432 |
| LMArena Chinese | 1449 | 1519 |
| LMArena Russian | 1404 | 1436 |
| LMArena Spanish | 1447 | 1439 |
| LMArena French | 1403 | — |
| LMArena German | 1413 | — |
| LMArena Korean | 1378 | — |
Instruction Following Too close to call
Kimi K2.5 Instant: 75.3 (#65), Step 5 Preview: 76.0 (#50)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1430 | 1444 |
Long Context Too close to call
Kimi K2.5 Instant: 43.9 (#83), Step 5 Preview: 44.5 (#64)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1435 | 1455 |
Writing & Preference Step 5 Preview leads
Kimi K2.5 Instant: 60.6 (#95), Step 5 Preview: 62.8 (#71)
| Benchmark | Kimi K2.5 Instant | Step 5 Preview |
|---|---|---|
| LMArena Text | 1420 | 1442 |
| LMArena Creative Writing | 1381 | 1410 |
| LMArena Multi-Turn | 1427 | 1447 |
Frequently asked questions
Is Kimi K2.5 Instant better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.6 on the Noometry Index.
Is Kimi K2.5 Instant or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 42.6 in the Noometry coding category.
How many benchmarks do Kimi K2.5 Instant and Step 5 Preview share?
15 benchmarks have published results for both models. Kimi K2.5 Instant has 18 scored results on Noometry and Step 5 Preview has 18.