Model comparison
Codellama 70b Instruct vs Grok 3
Grok 3 is the stronger model overall, scoring 39.6 to 33.3 on the Noometry Index.
Last verified . 4 shared benchmarks.
MetaSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 1 category and Grok 3 in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Grok 3 leads 52.5 to 24.9.
- Codellama 70b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 70b Instruct | Grok 3 | |
|---|---|---|
| Provider | Meta | xAI |
| Noometry Index | 33.3 | 39.6 |
| Released | — | 2025-04-09 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 3 leads
Codellama 70b Instruct: 37.0 (#189), Grok 3: 41.5 (#113)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| Aider Polyglot | — | 53.3% |
| WeirdML | — | 37.2% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1432 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Grok 3: 30.2 (#69)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| BALROG | — | 29.5% |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 19.2 (#241), Grok 3: 13.8 (#322)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1433 |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 36.1% |
| Kagi LLM Benchmark | — | 61.3% |
| ARC-AGI-1 | — | 5.5% |
| Epoch Capabilities Index | — | 138.34 |
Math Not comparable
Codellama 70b Instruct: —, Grok 3: 36.2 (#122)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| Omni-MATH | — | 46.4% |
| LMArena Math | — | 1390 |
| MATH Level 5 | — | 88.7% |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Not comparable
Codellama 70b Instruct: —, Grok 3: 46.0 (#76)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| GPQA Diamond | — | 75.8% |
| MMLU-Pro | — | 78.8% |
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 5.8% |
| GPQA (HELM) | — | 65% |
| LMArena Expert | — | 1420 |
Multilingual Grok 3 leads
Codellama 70b Instruct: 24.9 (#283), Grok 3: 52.5 (#81)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| LMArena Non-English | 992 | 1411 |
| LMArena Chinese | — | 1448 |
| LMArena French | — | 1460 |
| LMArena German | — | 1431 |
| LMArena Japanese | — | 1389 |
| LMArena Korean | — | 1374 |
| LMArena Russian | — | 1416 |
| LMArena Spanish | — | 1417 |
Instruction Following Grok 3 leads
Codellama 70b Instruct: 52.1 (#288), Grok 3: 75.2 (#69)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1409 |
| IFEval | — | 88.4% |
Long Context Not comparable
Codellama 70b Instruct: —, Grok 3: 38.7 (#187)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| Fiction.LiveBench | — | 58.3% |
| LMArena Longer Query | — | 1439 |
Writing & Preference Grok 3 leads
Codellama 70b Instruct: 33.6 (#272), Grok 3: 56.0 (#136)
| Benchmark | Codellama 70b Instruct | Grok 3 |
|---|---|---|
| LMArena Text | 1057 | 1426 |
| LMArena Creative Writing | — | 1414 |
| Short-Story Creative Writing | — | 76.4% |
| EQ-Bench Creative Writing | — | 1186 |
| WildBench | — | 84.9% |
| LMArena Multi-Turn | — | 1424 |
Frequently asked questions
Is Codellama 70b Instruct better than Grok 3?
Grok 3 is the stronger model overall, scoring 39.6 to 33.3 on the Noometry Index.
Is Codellama 70b Instruct or Grok 3 better for coding?
Grok 3 scores higher on coding benchmarks: 41.5 versus 37.0 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and Grok 3 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Grok 3 has 40.