Model comparison
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.
Last verified . 0 shared benchmarks.
MetaSummary
- 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.
Side by side
| Claude Haiku 5.5 | Codellama 70b Instruct | |
|---|---|---|
| Provider | Anthropic | Meta |
| Noometry Index | 49.5 | 33.7 |
| Released | 2026-10-07 | — |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.50 | — |
| Results tracked | 9 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 5.5 leads
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 leads
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 Not comparable
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 Not comparable
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 Not comparable
Claude Haiku 5.5: 43.7 (#21), Codellama 70b Instruct: —
| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| Furniture Assembly | 47.5% | — |
Multilingual Not comparable
Claude Haiku 5.5: —, Codellama 70b Instruct: 24.8 (#288)
| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| LMArena Non-English | — | 992 |
Instruction Following Not comparable
Claude Haiku 5.5: —, Codellama 70b Instruct: 51.9 (#293)
| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1024 |
Writing & Preference Not comparable
Claude Haiku 5.5: —, Codellama 70b Instruct: 33.4 (#277)
| Benchmark | Claude Haiku 5.5 | Codellama 70b Instruct |
|---|---|---|
| LMArena Text | — | 1057 |
Frequently asked questions
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.