Model comparison
Codestral vs Llama 3.3 Nemotron 49b Super v1
Llama 3.3 Nemotron 49b Super v1 is the stronger model overall, scoring 39.6 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
NVIDIASummary
- The widest gap is in coding, where Llama 3.3 Nemotron 49b Super v1 leads 37.3 to 26.9.
Side by side
| Codestral | Llama 3.3 Nemotron 49b Super v1 | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 30.1 | 39.6 |
| Released | 2024-05-29 | — |
| Weights | Open | Open |
| Context window | 256K | — |
| Max output | 4K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.3 Nemotron 49b Super v1 leads
Codestral: 26.9 (#316), Llama 3.3 Nemotron 49b Super v1: 37.3 (#183)
| Benchmark | Codestral | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1296 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Llama 3.3 Nemotron 49b Super v1 leads
Codestral: 19.1 (#244), Llama 3.3 Nemotron 49b Super v1: 25.1 (#133)
| Benchmark | Codestral | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1311 |
Multilingual Not comparable
Codestral: —, Llama 3.3 Nemotron 49b Super v1: 41.3 (#206)
| Benchmark | Codestral | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Non-English | — | 1253 |
| LMArena Chinese | — | 1277 |
| LMArena Russian | — | 1269 |
Instruction Following Not comparable
Codestral: —, Llama 3.3 Nemotron 49b Super v1: 68.5 (#184)
| Benchmark | Codestral | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Instruction Following | — | 1294 |
Long Context Not comparable
Codestral: —, Llama 3.3 Nemotron 49b Super v1: 39.5 (#171)
| Benchmark | Codestral | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Longer Query | — | 1300 |
Writing & Preference Not comparable
Codestral: —, Llama 3.3 Nemotron 49b Super v1: 51.0 (#173)
| Benchmark | Codestral | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Text | — | 1308 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1315 |
Frequently asked questions
Is Codestral better than Llama 3.3 Nemotron 49b Super v1?
Llama 3.3 Nemotron 49b Super v1 is the stronger model overall, scoring 39.6 to 30.1 on the Noometry Index.
Is Codestral or Llama 3.3 Nemotron 49b Super v1 better for coding?
Llama 3.3 Nemotron 49b Super v1 scores higher on coding benchmarks: 37.3 versus 26.9 in the Noometry coding category.
How many benchmarks do Codestral and Llama 3.3 Nemotron 49b Super v1 share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Llama 3.3 Nemotron 49b Super v1 has 10.