Model comparison
Kimi K2 Thinking Turbo vs Step 3
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 40.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. Kimi K2 Thinking Turbo scores higher in 7 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Kimi K2 Thinking Turbo leads 50.9 to 36.8.
Side by side
| Kimi K2 Thinking Turbo | Step 3 | |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 45.8 | 40.5 |
| Released | 2025-11-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Kimi K2 Thinking Turbo: 38.4 (#178), Step 3: 40.1 (#147)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Coding | 1454 | 1367 |
| LMArena WebDev | 1322 | — |
Reasoning Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 32.5 (#75), Step 3: 28.4 (#105)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1428 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| Chess Puzzles | 20% | — |
Math Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 47.4 (#68), Step 3: 37.6 (#148)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Math | 1429 | 1366 |
| OTIS Mock AIME 2024-2025 | 83.1% | — |
Knowledge Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 50.9 (#69), Step 3: 36.8 (#164)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Expert | 1439 | 1333 |
| GPQA Diamond | 84.2% | — |
Multimodal Not comparable
Kimi K2 Thinking Turbo: —, Step 3: 35.5 (#86)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 51.4 (#109), Step 3: 46.3 (#159)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Non-English | 1398 | 1327 |
| LMArena Chinese | 1456 | 1397 |
| LMArena German | 1390 | 1371 |
| LMArena Korean | 1330 | 1269 |
| LMArena Russian | 1391 | 1331 |
| LMArena Spanish | 1406 | 1371 |
| LMArena French | 1425 | — |
| LMArena Japanese | 1357 | — |
Instruction Following Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 74.0 (#109), Step 3: 70.4 (#164)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1332 |
Long Context Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 43.2 (#102), Step 3: 40.3 (#157)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Longer Query | 1415 | 1326 |
Writing & Preference Kimi K2 Thinking Turbo leads
Kimi K2 Thinking Turbo: 60.0 (#104), Step 3: 54.3 (#151)
| Benchmark | Kimi K2 Thinking Turbo | Step 3 |
|---|---|---|
| LMArena Text | 1415 | 1350 |
| LMArena Creative Writing | 1374 | 1321 |
| LMArena Multi-Turn | 1414 | 1341 |
Frequently asked questions
Is Kimi K2 Thinking Turbo better than Step 3?
Kimi K2 Thinking Turbo is the stronger model overall, scoring 45.8 to 40.5 on the Noometry Index.
Is Kimi K2 Thinking Turbo or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 38.4 in the Noometry coding category.
How many benchmarks do Kimi K2 Thinking Turbo and Step 3 share?
15 benchmarks have published results for both models. Kimi K2 Thinking Turbo has 21 scored results on Noometry and Step 3 has 17.