Model comparison
Codellama 70b Instruct vs DeepSeek LLM 67B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 24.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
DeepSeekSummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 3 categories and DeepSeek LLM 67B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 31.9.
Side by side
| Codellama 70b Instruct | DeepSeek LLM 67B | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.7 | 24.9 |
| Released | — | 2023-11-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), DeepSeek LLM 67B: 31.9 (#278)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1096 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning Codellama 70b Instruct leads
Codellama 70b Instruct: 20.1 (#242), DeepSeek LLM 67B: 16.5 (#304)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1070 |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 110.5 |
Math Not comparable
Codellama 70b Instruct: —, DeepSeek LLM 67B: 8.7 (#324)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0.8% |
| LMArena Math | — | 1108 |
| MATH Level 5 | — | 6.4% |
Knowledge Not comparable
Codellama 70b Instruct: —, DeepSeek LLM 67B: 7.0 (#313)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| GPQA Diamond | — | 24.6% |
Multilingual DeepSeek LLM 67B leads
Codellama 70b Instruct: 24.8 (#288), DeepSeek LLM 67B: 29.4 (#267)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Non-English | 992 | 1073 |
| LMArena Chinese | — | 1132 |
Instruction Following DeepSeek LLM 67B leads
Codellama 70b Instruct: 51.9 (#293), DeepSeek LLM 67B: 55.4 (#277)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Instruction Following | 1024 | 1079 |
Long Context Not comparable
Codellama 70b Instruct: —, DeepSeek LLM 67B: 33.1 (#265)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Longer Query | — | 1092 |
Writing & Preference Codellama 70b Instruct leads
Codellama 70b Instruct: 33.4 (#277), DeepSeek LLM 67B: 31.6 (#282)
| Benchmark | Codellama 70b Instruct | DeepSeek LLM 67B |
|---|---|---|
| LMArena Text | 1057 | 1105 |
| LMArena Creative Writing | — | 1067 |
| LMArena Multi-Turn | — | 1082 |
Frequently asked questions
Is Codellama 70b Instruct better than DeepSeek LLM 67B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 24.9 on the Noometry Index.
Is Codellama 70b Instruct or DeepSeek LLM 67B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 31.9 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and DeepSeek LLM 67B share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek LLM 67B has 15.