Model comparison
Codellama 34b Instruct vs DeepSeek-V3.2-Speciale
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 30.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
Meta
DeepSeekSummary
- The widest gap is in writing & preference, where DeepSeek-V3.2-Speciale leads 46.0 to 28.2.
Side by side
| Codellama 34b Instruct | DeepSeek-V3.2-Speciale | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.8 | 39.7 |
| Released | — | 2025-12-01 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.58 |
| Output $ / M tokens | — | $1.68 |
| Results tracked | 14 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Speciale leads
Codellama 34b Instruct: 28.5 (#314), DeepSeek-V3.2-Speciale: 40.4 (#140)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.2-Speciale |
|---|---|---|
| WeirdML | — | 46.7% |
| BigCodeBench Instruct | 29% | — |
| LMArena Coding | 1046 | — |
| BigCodeBench Complete | 37.1% | — |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning DeepSeek-V3.2-Speciale leads
Codellama 34b Instruct: 19.6 (#255), DeepSeek-V3.2-Speciale: 32.9 (#73)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.2-Speciale |
|---|---|---|
| SimpleBench | — | 52.6% |
| LMArena Hard Prompts | 1032 | — |
Math Not comparable
Codellama 34b Instruct: 31.0 (#230), DeepSeek-V3.2-Speciale: —
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Math | 1056 | — |
Multilingual Not comparable
Codellama 34b Instruct: 25.8 (#284), DeepSeek-V3.2-Speciale: —
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Non-English | 1011 | — |
| LMArena Chinese | 976 | — |
Instruction Following Not comparable
Codellama 34b Instruct: 52.2 (#291), DeepSeek-V3.2-Speciale: —
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Instruction Following | 1028 | — |
Long Context Not comparable
Codellama 34b Instruct: 30.9 (#284), DeepSeek-V3.2-Speciale: —
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Longer Query | 1013 | — |
Writing & Preference DeepSeek-V3.2-Speciale leads
Codellama 34b Instruct: 28.2 (#297), DeepSeek-V3.2-Speciale: 46.0 (#222)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.2-Speciale |
|---|---|---|
| LMArena Text | 1066 | — |
| LMArena Creative Writing | 1032 | — |
| EQ-Bench Creative Writing | — | 1276 |
| LMArena Multi-Turn | 1015 | — |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek-V3.2-Speciale?
DeepSeek-V3.2-Speciale is the stronger model overall, scoring 39.7 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or DeepSeek-V3.2-Speciale better for coding?
DeepSeek-V3.2-Speciale scores higher on coding benchmarks: 40.4 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek-V3.2-Speciale share?
0 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek-V3.2-Speciale has 3.