Model comparison
Codellama 34b Instruct vs DeepSeek LLM 67B
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 24.9 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
DeepSeekSummary
- They share 10 benchmarks with published results for both. Codellama 34b Instruct scores higher in 2 categories and DeepSeek LLM 67B in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Codellama 34b Instruct leads 31.0 to 8.7.
Side by side
| Codellama 34b Instruct | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.8 | 24.9 |
| Released | — | 2023-11-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek LLM 67B leads
Codellama 34b Instruct: 28.5 (#314), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Coding | 1046 | 1096 |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1070 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 110.5 |
Math Codellama 34b Instruct leads
Codellama 34b Instruct: 31.0 (#230), DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Math | 1056 | 1108 |
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| MATH Level 5 | — | 6.4% |
Knowledge Not comparable
Codellama 34b Instruct: —, DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
Multilingual DeepSeek LLM 67B leads
Codellama 34b Instruct: 25.8 (#284), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 1011 | 1073 |
| LMArena Chinese | 976 | 1132 |
Instruction Following DeepSeek LLM 67B leads
Codellama 34b Instruct: 52.2 (#291), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1028 | 1079 |
Long Context DeepSeek LLM 67B leads
Codellama 34b Instruct: 30.9 (#284), DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | 1013 | 1092 |
Writing & Preference DeepSeek LLM 67B leads
Codellama 34b Instruct: 28.2 (#297), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Codellama 34b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1066 | 1105 |
| LMArena Creative Writing | 1032 | 1067 |
| LMArena Multi-Turn | 1015 | 1082 |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek LLM 67B?
Codellama 34b Instruct is the stronger model overall, scoring 30.8 to 24.9 on the Noometry Index.
Is Codellama 34b Instruct or DeepSeek LLM 67B better for coding?
DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek LLM 67B share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek LLM 67B has 15.