Model comparison
Codellama 70b Instruct vs DeepSeek-R1-Distill-Qwen-1.5B
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 26.1 on the Noometry Index.
Last verified . 2 shared benchmarks.
Meta
DeepSeekSummary
- They share 2 benchmarks with published results for both. Codellama 70b Instruct scores higher in 2 categories and DeepSeek-R1-Distill-Qwen-1.5B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Codellama 70b Instruct leads 37.6 to 21.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 49.6% for Codellama 70b Instruct and 7.9% for DeepSeek-R1-Distill-Qwen-1.5B.
Side by side
| Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B | |
|---|---|---|
| Provider | Meta | DeepSeek |
| Noometry Index | 33.7 | 26.1 |
| Released | — | 2025-01-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Codellama 70b Instruct leads
Codellama 70b Instruct: 37.6 (#193), DeepSeek-R1-Distill-Qwen-1.5B: 21.8 (#336)
| Benchmark | Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| BigCodeBench Instruct | 40.7% | 7% |
| BigCodeBench Complete | 49.6% | 7.9% |
| HumanEval+ | 65.9% | — |
Reasoning Too close to call
Codellama 70b Instruct: 20.1 (#242), DeepSeek-R1-Distill-Qwen-1.5B: 19.2 (#262)
| Benchmark | Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1052 | — |
Math Not comparable
Codellama 70b Instruct: —, DeepSeek-R1-Distill-Qwen-1.5B: 23.0 (#274)
| Benchmark | Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 21.4% |
Knowledge Not comparable
Codellama 70b Instruct: —, DeepSeek-R1-Distill-Qwen-1.5B: 16.0 (#290)
| Benchmark | Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| GPQA Diamond | — | 33.6% |
Multilingual Not comparable
Codellama 70b Instruct: 24.8 (#288), DeepSeek-R1-Distill-Qwen-1.5B: —
| Benchmark | Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| LMArena Non-English | 992 | — |
Instruction Following Not comparable
Codellama 70b Instruct: 51.9 (#293), DeepSeek-R1-Distill-Qwen-1.5B: —
| Benchmark | Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| LMArena Instruction Following | 1024 | — |
Writing & Preference Not comparable
Codellama 70b Instruct: 33.4 (#277), DeepSeek-R1-Distill-Qwen-1.5B: —
| Benchmark | Codellama 70b Instruct | DeepSeek-R1-Distill-Qwen-1.5B |
|---|---|---|
| LMArena Text | 1057 | — |
Frequently asked questions
Is Codellama 70b Instruct better than DeepSeek-R1-Distill-Qwen-1.5B?
Codellama 70b Instruct is the stronger model overall, scoring 33.7 to 26.1 on the Noometry Index.
Is Codellama 70b Instruct or DeepSeek-R1-Distill-Qwen-1.5B better for coding?
Codellama 70b Instruct scores higher on coding benchmarks: 37.6 versus 21.8 in the Noometry coding category.
How many benchmarks do Codellama 70b Instruct and DeepSeek-R1-Distill-Qwen-1.5B share?
2 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and DeepSeek-R1-Distill-Qwen-1.5B has 5.