# Codellama 70b Instruct vs Mercury 2

> Mercury 2 is the stronger model overall, scoring 38.8 to 33.3 on the Noometry Index.

- Canonical page: https://noometry.com/compare/codellama-70b-instruct-vs-mercury-2
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Mercury 2 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Mercury 2 leads 46.8 to 24.9.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| Provider | Meta | Inception |
| Noometry Index | 33.3 | 38.8 |
| Rank | 236 | 167 |
| Context | — | 128K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.75 |
| Weights | Open | Proprietary |

## Coding

- Codellama 70b Instruct: 37.0 (#189)
- Mercury 2: 33.2 (#250)

| Benchmark | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| LMArena WebDev | — | 1170 |
| SciCode | — | 38.7% |
| WeirdML | — | 43.2% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1391 |
| BigCodeBench Complete | 49.6% | — |
| ALE-Bench | — | 785.58 |
| HumanEval+ | 65.9% | — |

## Reasoning

- Codellama 70b Instruct: 19.2 (#241)
- Mercury 2: 23.0 (#170)

| Benchmark | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1362 |
| CritPt | — | 0.8% |

## Knowledge

- Codellama 70b Instruct: —
- Mercury 2: 35.6 (#170)

| Benchmark | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.3% |
| LMArena Expert | — | 1358 |

## Multilingual

- Codellama 70b Instruct: 24.9 (#283)
- Mercury 2: 46.8 (#153)

| Benchmark | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| LMArena Non-English | 992 | 1331 |
| LMArena Chinese | — | 1416 |
| LMArena Russian | — | 1303 |

## Instruction Following

- Codellama 70b Instruct: 52.1 (#288)
- Mercury 2: 70.4 (#161)

| Benchmark | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1328 |

## Long Context

- Codellama 70b Instruct: —
- Mercury 2: 40.4 (#149)

| Benchmark | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| LMArena Longer Query | — | 1329 |

## Writing & Preference

- Codellama 70b Instruct: 33.6 (#272)
- Mercury 2: 54.0 (#151)

| Benchmark | Codellama 70b Instruct | Mercury 2 |
|---|---|---|
| LMArena Text | 1057 | 1355 |
| LMArena Creative Writing | — | 1289 |
| LMArena Multi-Turn | — | 1358 |

## FAQ

### Is Codellama 70b Instruct better than Mercury 2?

Mercury 2 is the stronger model overall, scoring 38.8 to 33.3 on the Noometry Index.

### Is Codellama 70b Instruct or Mercury 2 better for coding?

Codellama 70b Instruct scores higher on coding benchmarks: 37.0 versus 33.2 in the Noometry coding category.

### How many benchmarks do Codellama 70b Instruct and Mercury 2 share?

4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Mercury 2 has 17.