Model comparison
Codellama 70b Instruct vs DeepSeek-V3.1
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.7 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 0 categories and DeepSeek-V3.1 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 33.4.
Side by side
| Codellama 70b Instruct | DeepSeek-V3.1 | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.7 | 42.8 |
| Released | — | 2025-08-21 |
| Weights | Open | Open |
| Context window | — | 164K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.95 |
| Results tracked | 7 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
Codellama 70b Instruct: 37.6 (#193), DeepSeek-V3.1: 40.3 (#144)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| WeirdML | — | 38.4% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1417 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Reasoning DeepSeek-V3.1 leads
Codellama 70b Instruct: 20.1 (#242), DeepSeek-V3.1: 27.9 (#110)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1417 |
| SimpleBench | — | 40% |
| Kagi LLM Benchmark | — | 53.2% |
| DTBench | — | 82.7% |
| LMCA | — | 24.3% |
| Epoch Capabilities Index | — | 139.92 |
| ForecastBench | — | 58 |
Math Not comparable
Codellama 70b Instruct: —, DeepSeek-V3.1: 38.9 (#122)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | — | 1420 |
Knowledge Not comparable
Codellama 70b Instruct: —, DeepSeek-V3.1: 43.7 (#90)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 5.5% |
| LMArena Expert | — | 1405 |
Multilingual DeepSeek-V3.1 leads
Codellama 70b Instruct: 24.8 (#288), DeepSeek-V3.1: 51.6 (#106)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 992 | 1400 |
| LMArena Chinese | — | 1469 |
| LMArena French | — | 1447 |
| LMArena German | — | 1411 |
| LMArena Japanese | — | 1378 |
| LMArena Korean | — | 1337 |
| LMArena Russian | — | 1405 |
| LMArena Spanish | — | 1431 |
Instruction Following DeepSeek-V3.1 leads
Codellama 70b Instruct: 51.9 (#293), DeepSeek-V3.1: 73.9 (#110)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1024 | 1400 |
Long Context Not comparable
Codellama 70b Instruct: —, DeepSeek-V3.1: 36.3 (#232)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| Fiction.LiveBench | — | 52.8% |
| LMArena Longer Query | — | 1422 |
Writing & Preference DeepSeek-V3.1 leads
Codellama 70b Instruct: 33.4 (#277), DeepSeek-V3.1: 60.3 (#98)
| Benchmark | Codellama 70b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1057 | 1420 |
| LMArena Creative Writing | — | 1401 |
| EQ-Bench Creative Writing | — | 1436 |
| LMArena Multi-Turn | — | 1408 |
Frequently asked questions
Is Codellama 70b Instruct better than DeepSeek-V3.1?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or DeepSeek-V3.1 better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 37.6 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and DeepSeek-V3.1 share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek-V3.1 has 27.