Model comparison
Codellama 34b Instruct vs DeepSeek-V3.1
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.8 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 0 categories and DeepSeek-V3.1 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1 leads 60.3 to 28.2.
Side by side
| Codellama 34b Instruct | DeepSeek-V3.1 | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.8 | 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 | 14 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
Codellama 34b Instruct: 28.5 (#314), DeepSeek-V3.1: 40.3 (#144)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Coding | 1046 | 1417 |
| WeirdML | — | 38.4% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning DeepSeek-V3.1 leads
Codellama 34b Instruct: 19.6 (#255), DeepSeek-V3.1: 27.9 (#110)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1417 |
| SimpleBench | — | 40% |
| Kagi LLM Benchmark | — | 53.2% |
| DTBench | — | 82.7% |
| LMCA | — | 24.3% |
| Epoch Capabilities Index | — | 139.92 |
| ForecastBench | — | 58 |
Math DeepSeek-V3.1 leads
Codellama 34b Instruct: 31.0 (#230), DeepSeek-V3.1: 38.9 (#122)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Math | 1056 | 1420 |
Knowledge Not comparable
Codellama 34b Instruct: —, DeepSeek-V3.1: 43.7 (#90)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 5.5% |
| LMArena Expert | — | 1405 |
Multilingual DeepSeek-V3.1 leads
Codellama 34b Instruct: 25.8 (#284), DeepSeek-V3.1: 51.6 (#106)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Non-English | 1011 | 1400 |
| LMArena Chinese | 976 | 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 34b Instruct: 52.2 (#291), DeepSeek-V3.1: 73.9 (#110)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1400 |
Long Context DeepSeek-V3.1 leads
Codellama 34b Instruct: 30.9 (#284), DeepSeek-V3.1: 36.3 (#232)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Longer Query | 1013 | 1422 |
| Fiction.LiveBench | — | 52.8% |
Writing & Preference DeepSeek-V3.1 leads
Codellama 34b Instruct: 28.2 (#297), DeepSeek-V3.1: 60.3 (#98)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1 |
|---|---|---|
| LMArena Text | 1066 | 1420 |
| LMArena Creative Writing | 1032 | 1401 |
| LMArena Multi-Turn | 1015 | 1408 |
| EQ-Bench Creative Writing | — | 1436 |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek-V3.1?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or DeepSeek-V3.1 better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek-V3.1 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek-V3.1 has 27.