# Codellama 70b Instruct vs Inkling

> Inkling is the stronger model overall, scoring 44.1 to 33.7 on the Noometry Index.

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

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Inkling in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.2 to 33.4.

## Snapshot

| | Codellama 70b Instruct | Inkling |
|---|---|---|
| Provider | Meta | Thinking Machines Lab |
| Noometry Index | 33.7 | 44.1 |
| Rank | 237 | 80 |
| Context | — | 66K |
| Input $/M | — | $1.87 |
| Output $/M | — | $4.68 |
| Weights | Open | Open |

## Coding

- Codellama 70b Instruct: 37.6 (#193)
- Inkling: 34.5 (#234)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| FrontierCode | — | 14% |
| LMArena WebDev | — | 1413 |
| FrontierSWE | — | 4.1% |
| SciCode | — | 47% |
| WeirdML | — | 32.3% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1464 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 946 |
| HumanEval+ | 65.9% | — |

## Agentic & Tool Use

- Codellama 70b Instruct: —
- Inkling: 29.6 (#85)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| APEX-Agents | — | 33.8% |
| τ²-bench Banking | — | 25% |

## Reasoning

- Codellama 70b Instruct: 20.1 (#242)
- Inkling: 40.4 (#56)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1451 |
| ARC-AGI-2 | — | 36.5% |
| SimpleBench | — | 50% |
| ARC-AGI-1 | — | 79.5% |
| CritPt | — | 5.4% |
| Chess Puzzles | — | 21% |
| DTBench | — | 87.5% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 148.54 |

## Math

- Codellama 70b Instruct: —
- Inkling: 31.3 (#225)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 33.3% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | — | 0% |
| LMArena Math | — | 1479 |

## Knowledge

- Codellama 70b Instruct: —
- Inkling: 55.1 (#49)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| GPQA Diamond | — | 88.3% |
| SimpleQA Verified | — | 40.3% |
| LMArena Expert | — | 1465 |

## Multilingual

- Codellama 70b Instruct: 24.8 (#288)
- Inkling: 54.0 (#52)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| LMArena Non-English | 992 | 1434 |
| LMArena Chinese | — | 1490 |
| LMArena French | — | 1458 |
| LMArena German | — | 1446 |
| LMArena Japanese | — | 1429 |
| LMArena Korean | — | 1404 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1448 |

## Instruction Following

- Codellama 70b Instruct: 51.9 (#293)
- Inkling: 75.1 (#71)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| LMArena Instruction Following | 1024 | 1426 |

## Long Context

- Codellama 70b Instruct: —
- Inkling: 43.8 (#86)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| LMArena Longer Query | — | 1434 |

## Writing & Preference

- Codellama 70b Instruct: 33.4 (#277)
- Inkling: 65.2 (#51)

| Benchmark | Codellama 70b Instruct | Inkling |
|---|---|---|
| LMArena Text | 1057 | 1441 |
| LMArena Creative Writing | — | 1387 |
| EQ-Bench Creative Writing | — | 1611 |
| EQ-Bench 4 | — | 1226 |
| LMArena Multi-Turn | — | 1436 |

## FAQ

### Is Codellama 70b Instruct better than Inkling?

Inkling is the stronger model overall, scoring 44.1 to 33.7 on the Noometry Index.

### Is Codellama 70b Instruct or Inkling better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 34.5 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Inkling share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Inkling has 41.