# Codellama 70b Instruct vs Kimi K2.5

> Kimi K2.5 is the stronger model overall, scoring 47.8 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-kimi-k2-5
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Kimi K2.5 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2.5 leads 65.3 to 33.6.

## Snapshot

| | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| Provider | Meta | Moonshot AI |
| Noometry Index | 33.3 | 47.8 |
| Rank | 236 | 50 |
| Context | — | 262K |
| Input $/M | — | $0.45 |
| Output $/M | — | $2.25 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Kimi K2.5: 48.7 (#48)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| SWE-bench Verified | — | 73.8% |
| SWE-bench Verified (bash only) | — | 70.8% |
| LMArena WebDev | — | 1436 |
| SWE-bench Multilingual | — | 67.3% |
| SciCode | — | 49% |
| WeirdML | — | 45.6% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1474 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 821.65 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Kimi K2.5: 34.0 (#44)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| Terminal-Bench | — | 43.2% |
| OSWorld | — | 63.3% |
| Vending-Bench 2 | — | 1,198 |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Kimi K2.5: 31.2 (#74)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1454 |
| ARC-AGI-2 | — | 11.8% |
| SimpleBench | — | 46.8% |
| Kagi LLM Benchmark | — | 78.5% |
| NYT Connections (extended) | — | 69.9% |
| ARC-AGI-1 | — | 65.3% |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| EnigmaEval | — | 3.4% |
| Thematic Generalization | — | 69.4% |
| Epoch Capabilities Index | — | 148.05 |

## Math

- Codellama 70b Instruct: —
- Kimi K2.5: 50.3 (#46)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| MathArena Final-Answer Competitions | — | 62.3% |
| OTIS Mock AIME 2024-2025 | — | 92.2% |
| LMArena Math | — | 1470 |
| FrontierMath (Feb 2025 set) | — | 27.9% |
| FrontierMath Tier 4 (v1) | — | 4.2% |

## Knowledge

- Codellama 70b Instruct: —
- Kimi K2.5: 53.6 (#52)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| GPQA Diamond | — | 87.6% |
| Humanity's Last Exam | — | 24.4% |
| SimpleQA Verified | — | 34.3% |
| Vectara Hallucination Rate | — | 14.2% |
| LMArena Expert | — | 1466 |

## Multimodal

- Codellama 70b Instruct: —
- Kimi K2.5: 40.4 (#37)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Vision | — | 1269 |
| LMArena Document | — | 1430 |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Kimi K2.5: 54.1 (#50)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Non-English | 992 | 1433 |
| LMArena Chinese | — | 1495 |
| LMArena French | — | 1454 |
| LMArena German | — | 1441 |
| LMArena Japanese | — | 1422 |
| LMArena Korean | — | 1412 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1450 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Kimi K2.5: 75.5 (#60)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1431 |

## Long Context

- Codellama 70b Instruct: —
- Kimi K2.5: 52.1 (#7)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| Fiction.LiveBench | — | 86.1% |
| CL-bench | — | 19.3% |
| CL-bench Life | — | 13.2% |
| LMArena Longer Query | — | 1445 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Kimi K2.5: 65.3 (#51)

| Benchmark | Codellama 70b Instruct | Kimi K2.5 |
|---|---|---|
| LMArena Text | 1057 | 1445 |
| LMArena Creative Writing | — | 1423 |
| EQ-Bench Creative Writing | — | 1579 |
| LMArena Multi-Turn | — | 1444 |

## FAQ

### Is Codellama 70b Instruct better than Kimi K2.5?

Kimi K2.5 is the stronger model overall, scoring 47.8 to 33.3 on the Noometry Index.

### Is Codellama 70b Instruct or Kimi K2.5 better for coding?

Kimi K2.5 scores higher on coding benchmarks: 48.7 versus 37.0 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Kimi K2.5 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Kimi K2.5 has 51.