# Kimi K2 (Jul 2025) vs Step 3

> Kimi K2 (Jul 2025) and Step 3 score almost the same on the Noometry Index (41.2 vs 40.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/kimi-k2-vs-step-3
- Last updated: 2026-10-11
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 7 categories and Step 3 in 1 category; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.3 to 54.3.

## Snapshot

| | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 41.2 | 40.5 |
| Rank | 140 | 149 |
| Context | 262K | — |
| Input $/M | $0.57 | — |
| Output $/M | $2.30 | — |
| Weights | Open | Open |

## Coding

- Kimi K2 (Jul 2025): 42.4 (#102)
- Step 3: 40.1 (#147)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Coding | 1399 | 1367 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| ALE-Bench | 597.5 | — |

## Agentic & Tool Use

- Kimi K2 (Jul 2025): 32.4 (#64)
- Step 3: —

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |

## Reasoning

- Kimi K2 (Jul 2025): 23.3 (#179)
- Step 3: 28.4 (#105)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 64.4% | 62.3% |
| LMArena Hard Prompts | 1384 | 1355 |
| SimpleBench | 26.3% | — |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |

## Math

- Kimi K2 (Jul 2025): 42.7 (#83)
- Step 3: 37.6 (#148)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Math | 1397 | 1366 |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Kimi K2 (Jul 2025): 37.3 (#157)
- Step 3: 36.8 (#164)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Expert | 1365 | 1333 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |

## Multimodal

- Kimi K2 (Jul 2025): —
- Step 3: 35.5 (#86)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |

## Multilingual

- Kimi K2 (Jul 2025): 49.6 (#130)
- Step 3: 46.3 (#159)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Non-English | 1372 | 1327 |
| LMArena Chinese | 1415 | 1397 |
| LMArena German | 1387 | 1371 |
| LMArena Korean | 1325 | 1269 |
| LMArena Russian | 1385 | 1331 |
| LMArena Spanish | 1386 | 1371 |
| LMArena French | 1379 | — |
| LMArena Japanese | 1349 | — |

## Instruction Following

- Kimi K2 (Jul 2025): 71.1 (#156)
- Step 3: 70.4 (#164)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1348 | 1332 |
| IFEval | 85% | — |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#145)
- Step 3: 40.3 (#157)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Longer Query | 1353 | 1326 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |

## Writing & Preference

- Kimi K2 (Jul 2025): 62.3 (#78)
- Step 3: 54.3 (#151)

| Benchmark | Kimi K2 (Jul 2025) | Step 3 |
|---|---|---|
| LMArena Text | 1380 | 1350 |
| LMArena Creative Writing | 1350 | 1321 |
| LMArena Multi-Turn | 1371 | 1341 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |

## FAQ

### Is Kimi K2 (Jul 2025) better than Step 3?

Kimi K2 (Jul 2025) and Step 3 score almost the same on the Noometry Index (41.2 vs 40.5), so choose on price, context window or the category you care about most.

### Is Kimi K2 (Jul 2025) or Step 3 better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 40.1 in the Noometry coding category.

### How many benchmarks do Kimi K2 (Jul 2025) and Step 3 share?

16 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Step 3 has 17.