Model comparison
Codestral vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 30.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
NVIDIASummary
- The widest gap is in coding, where Nemotron 4 340b Instruct leads 35.2 to 27.3.
- Nemotron 4 340b Instruct has downloadable open weights; the other is API-only.
Side by side
| Codestral | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 30.6 | 35.9 |
| Released | 2024-05-29 | 2024-06-14 |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 7 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
Codestral: 27.3 (#321), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1209 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Nemotron 4 340b Instruct leads
Codestral: 19.8 (#251), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1202 |
Math Not comparable
Codestral: —, Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | — | 1216 |
Knowledge Not comparable
Codestral: —, Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | — | 1171 |
Multilingual Not comparable
Codestral: —, Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | — | 1206 |
| LMArena Chinese | — | 1214 |
| LMArena French | — | 1197 |
| LMArena German | — | 1192 |
| LMArena Japanese | — | 1128 |
| LMArena Korean | — | 1148 |
| LMArena Russian | — | 1219 |
| LMArena Spanish | — | 1195 |
Instruction Following Not comparable
Codestral: —, Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | — | 1203 |
Long Context Not comparable
Codestral: —, Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | — | 1225 |
Writing & Preference Not comparable
Codestral: —, Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Codestral | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | — | 1225 |
| LMArena Creative Writing | — | 1203 |
| LMArena Multi-Turn | — | 1214 |
Frequently asked questions
Is Codestral better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 30.6 on the Noometry Index.
Is Codestral or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 27.3 in the Noometry coding category.
How many benchmarks do Codestral and Nemotron 4 340b Instruct share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and Nemotron 4 340b Instruct has 17.