Model comparison
Codellama 34b Instruct vs DeepSeek-R1
DeepSeek-R1 is the stronger model overall, scoring 42.3 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 1 category and DeepSeek-R1 in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1 leads 61.4 to 28.2.
- Codellama 34b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codellama 34b Instruct | DeepSeek-R1 | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 30.8 | 42.3 |
| Released | — | 2025-01-20 |
| Weights | Open | Proprietary |
| Context window | — | 164K |
| Max output | — | 64K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.15 |
| Results tracked | 14 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
Codellama 34b Instruct: 28.5 (#314), DeepSeek-R1: 46.3 (#68)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| LMArena Coding | 1046 | 1427 |
| Aider Polyglot | — | 71.4% |
| SciCode | — | 35.7% |
| WeirdML | — | 41.6% |
| BigCodeBench Instruct | 29% | — |
| LiveBench Coding | — | 66.7% |
| BigCodeBench Complete | 37.1% | — |
| ALE-Bench | — | 804.12 |
| AlgoTune | — | 1.7 |
| HumanEval+ | 43.9% | — |
| MBPP+ | 56.3% | — |
Agentic & Tool Use Not comparable
Codellama 34b Instruct: —, DeepSeek-R1: 30.7 (#75)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| DeepResearch Bench | — | 35.1% |
| BALROG | — | 34.9% |
| METR Time Horizons | — | 53.8% |
Reasoning Codellama 34b Instruct leads
Codellama 34b Instruct: 19.6 (#255), DeepSeek-R1: 18.6 (#278)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| LMArena Hard Prompts | 1032 | 1416 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 40.8% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 21.2% |
| CritPt | — | 1.1% |
| LiveBench Reasoning | — | 83.2% |
| LiveBench Data Analysis | — | 69.8% |
| Epoch Capabilities Index | — | 141.29 |
| ForecastBench | — | 60 |
| LiveBench | — | 71.6% |
Math DeepSeek-R1 leads
Codellama 34b Instruct: 31.0 (#230), DeepSeek-R1: 43.8 (#79)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| LMArena Math | 1056 | 1400 |
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| Omni-MATH | — | 42.4% |
| LiveBench Math | — | 80.7% |
| MATH Level 5 | — | 96.6% |
Knowledge Not comparable
Codellama 34b Instruct: —, DeepSeek-R1: 44.5 (#87)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| GPQA Diamond | — | 76.3% |
| MMLU-Pro | — | 79.3% |
| Confabulations | — | 12.7% |
| Vectara Hallucination Rate | — | 11.3% |
| GPQA (HELM) | — | 66.6% |
| LMArena Expert | — | 1394 |
Multilingual DeepSeek-R1 leads
Codellama 34b Instruct: 25.8 (#284), DeepSeek-R1: 52.4 (#85)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| LMArena Non-English | 1011 | 1412 |
| LMArena Chinese | 976 | 1442 |
| LMArena French | — | 1417 |
| LMArena German | — | 1404 |
| LMArena Japanese | — | 1391 |
| LMArena Korean | — | 1360 |
| LMArena Russian | — | 1423 |
| LMArena Spanish | — | 1411 |
Instruction Following DeepSeek-R1 leads
Codellama 34b Instruct: 52.2 (#291), DeepSeek-R1: 72.0 (#143)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| LMArena Instruction Following | 1028 | 1382 |
| LiveBench Instruction Following | — | 80.5% |
| IFEval | — | 78.4% |
Long Context DeepSeek-R1 leads
Codellama 34b Instruct: 30.9 (#284), DeepSeek-R1: 45.4 (#36)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| LMArena Longer Query | 1013 | 1391 |
| Fiction.LiveBench | — | 75% |
Writing & Preference DeepSeek-R1 leads
Codellama 34b Instruct: 28.2 (#297), DeepSeek-R1: 61.4 (#88)
| Benchmark | Codellama 34b Instruct | DeepSeek-R1 |
|---|---|---|
| LMArena Text | 1066 | 1428 |
| LMArena Creative Writing | 1032 | 1405 |
| LMArena Multi-Turn | 1015 | 1405 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1500 |
| WildBench | — | 82.8% |
| LiveBench Language | — | 48.5% |
Frequently asked questions
Is Codellama 34b Instruct better than DeepSeek-R1?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 30.8 on the Noometry Index.
Is Codellama 34b Instruct or DeepSeek-R1 better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 versus 28.5 in the Noometry coding category.
How many benchmarks do Codellama 34b Instruct and DeepSeek-R1 share?
10 benchmarks have published results for both models. Codellama 34b Instruct has 14 scored results on Noometry and DeepSeek-R1 has 52.