Model comparison
Codellama 70b Instruct vs Grok Build 0.1
Grok Build 0.1 is the stronger model overall, scoring 36.4 to 33.7 on the Noometry Index.
Last verified . 0 shared benchmarks.
MetaSummary
- The widest gap is in reasoning, where Grok Build 0.1 leads 32.2 to 20.1.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Grok Build 0.1 | |
|---|---|---|
| Provider | Meta | xAI |
| Noometry Index | 33.7 | 36.4 |
| Released | — | 2026-04-16 |
| Weights | Open | Proprietary |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2 |
| Results tracked | 7 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok Build 0.1 leads
Codellama 70b Instruct: 37.6 (#193), Grok Build 0.1: 43.1 (#91)
| Benchmark | Codellama 70b Instruct | Grok Build 0.1 |
|---|---|---|
| SciCode | — | 50.2% |
| BigCodeBench Instruct | 40.7% | — |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Grok Build 0.1: 22.7 (#129)
| Benchmark | Codellama 70b Instruct | Grok Build 0.1 |
|---|---|---|
| GBAEval | — | 2.4% |
Reasoning Grok Build 0.1 leads
Codellama 70b Instruct: 20.1 (#242), Grok Build 0.1: 32.2 (#77)
| Benchmark | Codellama 70b Instruct | Grok Build 0.1 |
|---|---|---|
| CritPt | — | 9.1% |
| LMArena Hard Prompts | 1052 | — |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), Grok Build 0.1: —
| Benchmark | Codellama 70b Instruct | Grok Build 0.1 |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 51.9 (#293), Grok Build 0.1: —
| Benchmark | Codellama 70b Instruct | Grok Build 0.1 |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.4 (#277), Grok Build 0.1: —
| Benchmark | Codellama 70b Instruct | Grok Build 0.1 |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than Grok Build 0.1?
Grok Build 0.1 is the stronger model overall, scoring 36.4 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Grok Build 0.1 better for coding?
Grok Build 0.1 scores higher on coding benchmarks: 43.1 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Grok Build 0.1 share?
0 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Grok Build 0.1 has 3.