Model comparison
Codellama 34b Instruct vs DeepSeek-V3.1-Terminus
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 30.2 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
DeepSeekSummary
- They share 9 benchmarks with published results for both. Codellama 34b Instruct scores higher in 0 categories and DeepSeek-V3.1-Terminus in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 28.4.
Side by side
| Codellama 34b Instruct | DeepSeek-V3.1-Terminus | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.2 | 42.6 |
| Released | — | 2025-09-22 |
| Weights | Open | Open |
| Context window | — | 164K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1 |
| Results tracked | 14 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
Codellama 34b Instruct: 28.0 (#310), DeepSeek-V3.1-Terminus: 41.5 (#114)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Coding | 1046 | 1426 |
| SciCode | — | 40.6% |
| BigCodeBench Instruct | 29% | — |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 745.17 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Reasoning DeepSeek-V3.1-Terminus leads
Codellama 34b Instruct: 18.8 (#250), DeepSeek-V3.1-Terminus: 25.7 (#126)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1427 |
| Kagi LLM Benchmark | — | 57.4% |
| CritPt | — | 1.7% |
| DTBench | — | 81.3% |
| LMCA | — | 28.6% |
Math DeepSeek-V3.1-Terminus leads
Codellama 34b Instruct: 28.5 (#227), DeepSeek-V3.1-Terminus: 35.7 (#138)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Math | 1056 | 1402 |
Multilingual DeepSeek-V3.1-Terminus leads
Codellama 34b Instruct: 25.9 (#279), DeepSeek-V3.1-Terminus: 52.3 (#87)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Non-English | 1011 | 1407 |
| LMArena Chinese | 976 | — |
| LMArena Russian | — | 1434 |
Instruction Following DeepSeek-V3.1-Terminus leads
Codellama 34b Instruct: 52.4 (#286), DeepSeek-V3.1-Terminus: 74.4 (#96)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Instruction Following | 1028 | 1406 |
Long Context DeepSeek-V3.1-Terminus leads
Codellama 34b Instruct: 30.8 (#279), DeepSeek-V3.1-Terminus: 43.5 (#88)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Longer Query | 1014 | 1426 |
Writing & Preference DeepSeek-V3.1-Terminus leads
Codellama 34b Instruct: 28.4 (#292), DeepSeek-V3.1-Terminus: 61.3 (#87)
| Benchmark | Codellama 34b Instruct | DeepSeek-V3.1-Terminus |
|---|---|---|
| LMArena Text | 1066 | 1420 |
| LMArena Creative Writing | 1032 | 1404 |
| LMArena Multi-Turn | 1015 | 1411 |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek-V3.1-Terminus?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 30.2 on the Noometry Index.
Is Codellama 34b Instruct or DeepSeek-V3.1-Terminus better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 28.0 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek-V3.1-Terminus share?
9 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek-V3.1-Terminus has 16.