Model comparison
Codestral vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 1 benchmark with published results for both. Codestral scores higher in 1 category and Nemotron 3 Super in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Nemotron 3 Super leads 39.4 to 27.3.
- Nemotron 3 Super is cheaper at $0.08 / $0.45 per million input/output tokens, against $0.30 / $0.90 for Codestral.
- Nemotron 3 Super accepts more context: 262K tokens versus 256K.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| Codestral | Nemotron 3 Super | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 30.6 | 40.1 |
| Released | 2024-05-29 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | 256K | 262K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.30 | $0.08 |
| Output $ / M tokens | $0.90 | $0.45 |
| Results tracked | 7 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Codestral: 27.3 (#321), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| ALE-Bench | 137.78 | 213.9 |
| Aider Polyglot | 11.1% | — |
| SciCode | — | 36% |
| WeirdML | — | 38% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1403 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning Codestral leads
Codestral: 19.8 (#251), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| LMArena Hard Prompts | — | 1386 |
Math Not comparable
Codestral: —, Nemotron 3 Super: 39.6 (#101)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| MathArena Final-Answer Competitions | — | 60.4% |
| LMArena Math | — | 1380 |
Knowledge Not comparable
Codestral: —, Nemotron 3 Super: 38.9 (#139)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | — | 1398 |
Multilingual Not comparable
Codestral: —, Nemotron 3 Super: 48.4 (#144)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | — | 1355 |
| LMArena Chinese | — | 1432 |
| LMArena French | — | 1405 |
| LMArena German | — | 1341 |
| LMArena Russian | — | 1336 |
| LMArena Spanish | — | 1417 |
Instruction Following Not comparable
Codestral: —, Nemotron 3 Super: 71.2 (#154)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | — | 1347 |
Long Context Not comparable
Codestral: —, Nemotron 3 Super: 41.5 (#139)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | — | 1362 |
Writing & Preference Not comparable
Codestral: —, Nemotron 3 Super: 55.9 (#140)
| Benchmark | Codestral | Nemotron 3 Super |
|---|---|---|
| LMArena Text | — | 1378 |
| LMArena Creative Writing | — | 1317 |
| LMArena Multi-Turn | — | 1369 |
Frequently asked questions
Is Codestral better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or Nemotron 3 Super?
Nemotron 3 Super is cheaper. It lists at $0.08 per million input tokens and $0.45 per million output tokens; Codestral lists at $0.30 and $0.90.
Is Codestral or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 256K.
How many benchmarks do Codestral and Nemotron 3 Super share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and Nemotron 3 Super has 21.