# Kimi K2 (Jul 2025) vs Llama 4 Scout

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 27.4 on the Noometry Index. Llama 4 Scout costs 6.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/kimi-k2-vs-llama-4-scout
- Last updated: 2026-10-10
- Shared benchmarks: 31

## Summary

- They share 31 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 9 categories and Llama 4 Scout in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.5 to 37.1.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 63.4% for Kimi K2 (Jul 2025) and 9.1% for Llama 4 Scout.
- Llama 4 Scout 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 128K.

## Snapshot

| | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 40.9 | 27.4 |
| Rank | 134 | 323 |
| Context | 262K | 128K |
| Input $/M | $0.57 | $0.10 |
| Output $/M | $2.30 | $0.30 |
| Weights | Open | Open |

## Coding

- Kimi K2 (Jul 2025): 43.1 (#83)
- Llama 4 Scout: 19.9 (#334)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| SWE-bench Verified (bash only) | 63.4% | 9.1% |
| LMArena Coding | 1399 | 1286 |
| Aider Polyglot | 59.1% | — |
| SciCode | — | 17% |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| BigCodeBench Complete | — | 43.1% |
| ALE-Bench | 597.5 | — |

## Agentic & Tool Use

- Kimi K2 (Jul 2025): 32.2 (#59)
- Llama 4 Scout: 24.4 (#109)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| Berkeley Function Calling Leaderboard | 59.1% | 28.1% |
| Terminal-Bench | 35.7% | — |
| METR Time Horizons | 59.2% | — |

## Reasoning

- Kimi K2 (Jul 2025): 22.7 (#173)
- Llama 4 Scout: 9.2 (#339)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| Kagi LLM Benchmark | 64.4% | 36.9% |
| LMArena Hard Prompts | 1384 | 1266 |
| Epoch Capabilities Index | 146.02 | 129.64 |
| ForecastBench | 60.2 | 57.5 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | 26.3% | — |
| ARC-AGI-1 | — | 0.5% |
| CritPt | — | 0% |
| DTBench | — | 57.9% |
| LMCA | — | 12% |

## Math

- Kimi K2 (Jul 2025): 40.1 (#81)
- Llama 4 Scout: 18.4 (#280)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| Omni-MATH | 65.4% | 37.3% |
| LMArena Math | 1396 | 1286 |
| FrontierMath (Feb 2025 set) | 21.4% | 0% |
| OTIS Mock AIME 2024-2025 | — | 7.8% |
| MATH Level 5 | — | 62.3% |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Kimi K2 (Jul 2025): 36.9 (#153)
- Llama 4 Scout: 31.8 (#208)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| MMLU-Pro | 81.9% | 74.2% |
| Vectara Hallucination Rate | 17.9% | 7.7% |
| GPQA (HELM) | 65.3% | 50.7% |
| LMArena Expert | 1363 | 1236 |
| GPQA Diamond | — | 51.8% |
| Confabulations | 20.4% | — |

## Multimodal

- Kimi K2 (Jul 2025): —
- Llama 4 Scout: 31.6 (#98)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| LMArena Vision | — | 1118 |
| SpatialViz-Bench | — | 34.2% |

## Multilingual

- Kimi K2 (Jul 2025): 49.8 (#125)
- Llama 4 Scout: 41.3 (#207)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| LMArena Non-English | 1372 | 1253 |
| LMArena Chinese | 1416 | 1256 |
| LMArena French | 1379 | 1283 |
| LMArena German | 1386 | 1274 |
| LMArena Japanese | 1349 | 1209 |
| LMArena Korean | 1324 | 1207 |
| LMArena Russian | 1384 | 1263 |
| LMArena Spanish | 1383 | 1277 |

## Instruction Following

- Kimi K2 (Jul 2025): 71.3 (#151)
- Llama 4 Scout: 66.0 (#212)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| IFEval | 85% | 81.8% |
| LMArena Instruction Following | 1347 | 1248 |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#140)
- Llama 4 Scout: 27.5 (#289)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| Fiction.LiveBench | 66.7% | 36% |
| LMArena Longer Query | 1353 | 1265 |
| CL-bench | 17.6% | — |

## Writing & Preference

- Kimi K2 (Jul 2025): 62.5 (#76)
- Llama 4 Scout: 37.1 (#256)

| Benchmark | Kimi K2 (Jul 2025) | Llama 4 Scout |
|---|---|---|
| LMArena Text | 1380 | 1279 |
| LMArena Creative Writing | 1349 | 1249 |
| EQ-Bench Creative Writing | 1666 | 783 |
| WildBench | 86.2% | 78% |
| LMArena Multi-Turn | 1371 | 1281 |
| Short-Story Creative Writing | 85.6% | — |

## FAQ

### Is Kimi K2 (Jul 2025) better than Llama 4 Scout?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 40.9 to 27.4 on the Noometry Index. Llama 4 Scout costs 6.7× less per token, which makes it the better buy when Kimi K2 (Jul 2025)'s lead doesn't matter for your workload.

### Which is cheaper, Kimi K2 (Jul 2025) or Llama 4 Scout?

Llama 4 Scout 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 Llama 4 Scout better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 43.1 versus 19.9 in the Noometry coding category.

### Which has the bigger context window?

Kimi K2 (Jul 2025) does, with 262K tokens against 128K.

### How many benchmarks do Kimi K2 (Jul 2025) and Llama 4 Scout share?

31 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Llama 4 Scout has 43.