# Codellama 70b Instruct vs Kimi K2 (Jul 2025)

> Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-kimi-k2
- Last updated: 2026-10-11
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Kimi K2 (Jul 2025) in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.3 to 33.4.

## Snapshot

| | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| Provider | Meta | Moonshot AI |
| Noometry Index | 33.7 | 41.2 |
| Rank | 237 | 140 |
| Context | — | 262K |
| Input $/M | — | $0.57 |
| Output $/M | — | $2.30 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Kimi K2 (Jul 2025): 42.4 (#102)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| SWE-bench Verified (bash only) | — | 63.4% |
| Aider Polyglot | — | 59.1% |
| GSO | — | 4.9% |
| WeirdML | — | 42.8% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1399 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 597.5 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Kimi K2 (Jul 2025): 32.4 (#64)

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

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Kimi K2 (Jul 2025): 23.3 (#179)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1384 |
| SimpleBench | — | 26.3% |
| Kagi LLM Benchmark | — | 64.4% |
| Epoch Capabilities Index | — | 146.01 |
| ForecastBench | — | 60.2 |

## Math

- Codellama 70b Instruct: —
- Kimi K2 (Jul 2025): 42.7 (#83)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| Omni-MATH | — | 65.4% |
| LMArena Math | — | 1397 |
| FrontierMath (Feb 2025 set) | — | 21.4% |
| FrontierMath Tier 4 (v1) | — | 0% |

## Knowledge

- Codellama 70b Instruct: —
- Kimi K2 (Jul 2025): 37.3 (#157)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| MMLU-Pro | — | 81.9% |
| Confabulations | — | 20.4% |
| Vectara Hallucination Rate | — | 17.9% |
| GPQA (HELM) | — | 65.3% |
| LMArena Expert | — | 1365 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Kimi K2 (Jul 2025): 49.6 (#130)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Non-English | 992 | 1372 |
| LMArena Chinese | — | 1415 |
| LMArena French | — | 1379 |
| LMArena German | — | 1387 |
| LMArena Japanese | — | 1349 |
| LMArena Korean | — | 1325 |
| LMArena Russian | — | 1385 |
| LMArena Spanish | — | 1386 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Kimi K2 (Jul 2025): 71.1 (#156)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Instruction Following | 1024 | 1348 |
| IFEval | — | 85% |

## Long Context

- Codellama 70b Instruct: —
- Kimi K2 (Jul 2025): 41.2 (#145)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 17.6% |
| LMArena Longer Query | — | 1353 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Kimi K2 (Jul 2025): 62.3 (#78)

| Benchmark | Codellama 70b Instruct | Kimi K2 (Jul 2025) |
|---|---|---|
| LMArena Text | 1057 | 1380 |
| LMArena Creative Writing | — | 1350 |
| Short-Story Creative Writing | — | 85.6% |
| EQ-Bench Creative Writing | — | 1666 |
| WildBench | — | 86.2% |
| LMArena Multi-Turn | — | 1371 |

## FAQ

### Is Codellama 70b Instruct better than Kimi K2 (Jul 2025)?

Kimi K2 (Jul 2025) is the stronger model overall, scoring 41.2 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Kimi K2 (Jul 2025) better for coding?

Kimi K2 (Jul 2025) scores higher on coding benchmarks: 42.4 versus 37.6 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Kimi K2 (Jul 2025) share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Kimi K2 (Jul 2025) has 42.