# Kimi K2 (Jul 2025) vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 42.3 to 41.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-vs-step-3-5-flash
- Last updated: 2026-10-11
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 4 categories and Step 3.5 Flash in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.3 to 58.8.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.57 / $2.30 for Kimi K2 (Jul 2025).
- Kimi K2 (Jul 2025) accepts more context: 262K tokens versus 256K.

## Snapshot

| | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| Provider | Moonshot AI | StepFun |
| Noometry Index | 41.2 | 42.3 |
| Rank | 140 | 116 |
| Context | 262K | 256K |
| Input $/M | $0.57 | $0.10 |
| Output $/M | $2.30 | $0.30 |
| Weights | Open | Open |

## Coding

- Kimi K2 (Jul 2025): 42.4 (#102)
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1399 | 1436 |
| 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 3.5 Flash: —

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |

## Reasoning

- Kimi K2 (Jul 2025): 23.3 (#179)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1411 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| NYT Connections (extended) | — | 28.4% |
| Epoch Capabilities Index | 146.01 | — |
| ForecastBench | 60.2 | — |

## Math

- Kimi K2 (Jul 2025): 42.7 (#83)
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1397 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| Omni-MATH | 65.4% | — |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Kimi K2 (Jul 2025): 37.3 (#157)
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1365 | 1421 |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |

## Multilingual

- Kimi K2 (Jul 2025): 49.6 (#130)
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1372 | 1385 |
| LMArena Chinese | 1415 | 1447 |
| LMArena French | 1379 | 1421 |
| LMArena German | 1387 | 1405 |
| LMArena Japanese | 1349 | 1354 |
| LMArena Korean | 1325 | 1352 |
| LMArena Russian | 1385 | 1385 |
| LMArena Spanish | 1386 | 1419 |

## Instruction Following

- Kimi K2 (Jul 2025): 71.1 (#156)
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1348 | 1385 |
| IFEval | 85% | — |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#145)
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1353 | 1402 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |

## Writing & Preference

- Kimi K2 (Jul 2025): 62.3 (#78)
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Kimi K2 (Jul 2025) | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1380 | 1403 |
| LMArena Creative Writing | 1350 | 1357 |
| LMArena Multi-Turn | 1371 | 1405 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |

## FAQ

### Is Kimi K2 (Jul 2025) better than Step 3.5 Flash?

Step 3.5 Flash is the stronger model overall, scoring 42.3 to 41.2 on the Noometry Index.

### Which is cheaper, Kimi K2 (Jul 2025) or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Kimi K2 (Jul 2025) lists at $0.57 and $2.30.

### Is Kimi K2 (Jul 2025) or Step 3.5 Flash better for coding?

They score almost the same on coding (42.4 vs 42.4); test both on your own repository before choosing.

### Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 256K.

### How many benchmarks do Kimi K2 (Jul 2025) and Step 3.5 Flash share?

17 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Step 3.5 Flash has 19.