# Kimi K2 (Jul 2025) vs Llama 2-70B

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 24.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/kimi-k2-vs-llama-2-70b
- Last updated: 2026-10-11
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2 (Jul 2025) leads 42.7 to 8.1.

## Snapshot

| | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| Provider | Moonshot AI | Meta |
| Noometry Index | 41.2 | 24.4 |
| Rank | 140 | 349 |
| Context | 262K | — |
| Input $/M | $0.57 | — |
| Output $/M | $2.30 | — |
| Weights | Open | Open |

## Coding

- Kimi K2 (Jul 2025): 42.4 (#102)
- Llama 2-70B: 31.4 (#286)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1399 | 1079 |
| 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)
- Llama 2-70B: —

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |

## Reasoning

- Kimi K2 (Jul 2025): 23.3 (#179)
- Llama 2-70B: 14.4 (#325)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1073 |
| Epoch Capabilities Index | 146.01 | 113.79 |
| ForecastBench | 60.2 | 51.4 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |

## Math

- Kimi K2 (Jul 2025): 42.7 (#83)
- Llama 2-70B: 8.1 (#326)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Math | 1397 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| Omni-MATH | 65.4% | — |
| MATH Level 5 | — | 3.3% |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
| GSM8K | — | 69.6% |

## Knowledge

- Kimi K2 (Jul 2025): 37.3 (#157)
- Llama 2-70B: 7.4 (#310)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1365 | 1039 |
| GPQA Diamond | — | 26.3% |
| MMLU-Pro | 81.9% | — |
| Confabulations | 20.4% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| MMLU | — | 69.9% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |

## Multilingual

- Kimi K2 (Jul 2025): 49.6 (#130)
- Llama 2-70B: 27.7 (#274)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1372 | 1045 |
| LMArena Chinese | 1415 | 995 |
| LMArena French | 1379 | 1090 |
| LMArena German | 1387 | 1041 |
| LMArena Japanese | 1349 | 927 |
| LMArena Korean | 1325 | 964 |
| LMArena Russian | 1385 | 1083 |
| LMArena Spanish | 1386 | 1143 |

## Instruction Following

- Kimi K2 (Jul 2025): 71.1 (#156)
- Llama 2-70B: 54.9 (#278)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1348 | 1071 |
| IFEval | 85% | — |

## Long Context

- Kimi K2 (Jul 2025): 41.2 (#145)
- Llama 2-70B: 32.3 (#270)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1353 | 1062 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |

## Writing & Preference

- Kimi K2 (Jul 2025): 62.3 (#78)
- Llama 2-70B: 32.3 (#279)

| Benchmark | Kimi K2 (Jul 2025) | Llama 2-70B |
|---|---|---|
| LMArena Text | 1380 | 1115 |
| LMArena Creative Writing | 1350 | 1075 |
| LMArena Multi-Turn | 1371 | 1088 |
| Short-Story Creative Writing | 85.6% | — |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |

## FAQ

### Is Kimi K2 (Jul 2025) better than Llama 2-70B?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 24.4 on the Noometry Index.

### Is Kimi K2 (Jul 2025) or Llama 2-70B better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 31.4 in the Noometry coding category.

### How many benchmarks do Kimi K2 (Jul 2025) and Llama 2-70B share?

19 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Llama 2-70B has 35.