Model comparison
Codellama 34b Instruct vs Grok-2 (Dec 2024)
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 30.2 on the Noometry Index.
Last verified . 10 shared benchmarks.
MetaSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and Grok-2 (Dec 2024) in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok-2 (Dec 2024) leads 48.8 to 28.4.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | Grok-2 (Dec 2024) | |
|---|---|---|
| Provider | Meta | xAI |
| Noometry Index | 30.2 | 33.4 |
| Released | — | 2024-08-13 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-2 (Dec 2024) leads
Codellama 34b Instruct: 28.0 (#310), Grok-2 (Dec 2024): 32.9 (#254)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Coding | 1046 | 1288 |
| WeirdML | — | 22.2% |
| BigCodeBench Instruct | 29% | — |
| LiveBench Coding | — | 46.4% |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 18.8 (#250), Grok-2 (Dec 2024): 16.4 (#294)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1272 |
| SimpleBench | — | 22.7% |
| LiveBench Reasoning | — | 54.8% |
| DTBench | — | 65.2% |
| LiveBench Data Analysis | — | 54.5% |
| Epoch Capabilities Index | — | 130.48 |
| LiveBench | — | 54.3% |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 28.5 (#227), Grok-2 (Dec 2024): 19.6 (#278)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Math | 1056 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 11.5% |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |
Knowledge Not comparable
Codellama 34b Instruct: —, Grok-2 (Dec 2024): 29.8 (#225)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| GPQA Diamond | — | 53.8% |
| Confabulations | — | 20.1% |
| LMArena Expert | — | 1254 |
Multilingual Grok-2 (Dec 2024) leads
Codellama 34b Instruct: 25.9 (#279), Grok-2 (Dec 2024): 43.3 (#183)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1011 | 1282 |
| LMArena Chinese | 976 | 1289 |
| LMArena French | — | 1317 |
| LMArena German | — | 1287 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1237 |
| LMArena Russian | — | 1286 |
| LMArena Spanish | — | 1281 |
Instruction Following Grok-2 (Dec 2024) leads
Codellama 34b Instruct: 52.4 (#286), Grok-2 (Dec 2024): 67.1 (#197)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1028 | 1270 |
| LiveBench Instruction Following | — | 69.6% |
Long Context Grok-2 (Dec 2024) leads
Codellama 34b Instruct: 30.8 (#279), Grok-2 (Dec 2024): 38.7 (#186)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1014 | 1276 |
Writing & Preference Grok-2 (Dec 2024) leads
Codellama 34b Instruct: 28.4 (#292), Grok-2 (Dec 2024): 48.8 (#192)
| Benchmark | Codellama 34b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1066 | 1305 |
| LMArena Creative Writing | 1032 | 1284 |
| LMArena Multi-Turn | 1015 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| LiveBench Language | — | 45.6% |
Frequently asked questions
Is Codellama 34b Instruct better than Grok-2 (Dec 2024)?
Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 30.2 on the Noometry Index.
Is Codellama 34b Instruct or Grok-2 (Dec 2024) better for coding?
Grok-2 (Dec 2024) scores higher on coding benchmarks: 32.9 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and Grok-2 (Dec 2024) share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and Grok-2 (Dec 2024) has 34.