# Claude Haiku 5.5 vs Codellama 70b Instruct

> Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 33.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-haiku-5-5-vs-codellama-70b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where Claude Haiku 5.5 leads 35.2 to 20.1.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 49.5 | 33.7 |
| Rank | 52 | 237 |
| Context | 1M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.50 | — |
| Weights | Proprietary | Open |

## Coding

- Claude Haiku 5.5: 49.2 (#50)
- Codellama 70b Instruct: 37.6 (#193)

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| LMArena WebDev | 1587 | — |
| BigCodeBench Instruct | — | 40.7% |
| BigCodeBench Complete | — | 49.6% |
| HumanEval+ | — | 65.9% |

## Reasoning

- Claude Haiku 5.5: 35.2 (#69)
- Codellama 70b Instruct: 20.1 (#242)

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| NYT Connections (extended) | 65.7% | — |
| LMArena Hard Prompts | — | 1052 |
| Mystery Game Puzzles | 30% | — |

## Math

- Claude Haiku 5.5: 73.6 (#18)
- Codellama 70b Instruct: —

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 98.9% | — |

## Knowledge

- Claude Haiku 5.5: 50.8 (#70)
- Codellama 70b Instruct: —

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| GPQA Diamond | 89.6% | — |
| SimpleQA Verified | 23.8% | — |

## Multimodal

- Claude Haiku 5.5: 43.7 (#21)
- Codellama 70b Instruct: —

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| Furniture Assembly | 47.5% | — |

## Multilingual

- Claude Haiku 5.5: —
- Codellama 70b Instruct: 24.8 (#288)

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| LMArena Non-English | — | 992 |

## Instruction Following

- Claude Haiku 5.5: —
- Codellama 70b Instruct: 51.9 (#293)

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1024 |

## Writing & Preference

- Claude Haiku 5.5: —
- Codellama 70b Instruct: 33.4 (#277)

| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| LMArena Text | — | 1057 |

## FAQ

### Is Claude Haiku 5.5 better than Codellama 70b Instruct?

Claude Haiku 5.5 is the stronger model overall, scoring 49.5 to 33.7 on the Noometry Index.

### Is Claude Haiku 5.5 or Codellama 70b Instruct better for coding?

Claude Haiku 5.5 scores higher on coding benchmarks: 49.2 versus 37.6 in the Noometry coding category.

### How many benchmarks do Claude Haiku 5.5 and Codellama 70b Instruct share?

0 benchmarks have published results for both models. Claude Haiku 5.5 has 9 scored results on Noometry and Codellama 70b Instruct has 7.