Model comparison
Devstral Small 2505 vs Llama 3.3 Nemotron 49b Super v1
Llama 3.3 Nemotron 49b Super v1 is the stronger model overall, scoring 40.1 to 34.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
Mistral AI
NVIDIASummary
- The widest gap is in reasoning, where Llama 3.3 Nemotron 49b Super v1 leads 26.2 to 19.7.
Side by side
| Devstral Small 2505 | Llama 3.3 Nemotron 49b Super v1 | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 34.3 | 40.1 |
| Released | 2025-05-07 | — |
| Weights | Open | Open |
| Context window | 128K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.10 | — |
| Output $ / M tokens | $0.30 | — |
| Results tracked | 4 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Devstral Small 2505 leads
Devstral Small 2505: 38.9 (#166), Llama 3.3 Nemotron 49b Super v1: 37.9 (#186)
| Benchmark | Devstral Small 2505 | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| SWE-bench Verified (bash only) | 56.4% | — |
| SciCode | 28.8% | — |
| LMArena Coding | — | 1296 |
Reasoning Llama 3.3 Nemotron 49b Super v1 leads
Devstral Small 2505: 19.7 (#252), Llama 3.3 Nemotron 49b Super v1: 26.2 (#135)
| Benchmark | Devstral Small 2505 | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| Kagi LLM Benchmark | 37.7% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | — | 1311 |
Multilingual Not comparable
Devstral Small 2505: —, Llama 3.3 Nemotron 49b Super v1: 41.1 (#211)
| Benchmark | Devstral Small 2505 | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Non-English | — | 1253 |
| LMArena Chinese | — | 1277 |
| LMArena Russian | — | 1269 |
Instruction Following Not comparable
Devstral Small 2505: —, Llama 3.3 Nemotron 49b Super v1: 68.3 (#189)
| Benchmark | Devstral Small 2505 | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Instruction Following | — | 1293 |
Long Context Not comparable
Devstral Small 2505: —, Llama 3.3 Nemotron 49b Super v1: 39.5 (#176)
| Benchmark | Devstral Small 2505 | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Longer Query | — | 1299 |
Writing & Preference Not comparable
Devstral Small 2505: —, Llama 3.3 Nemotron 49b Super v1: 50.8 (#179)
| Benchmark | Devstral Small 2505 | Llama 3.3 Nemotron 49b Super v1 |
|---|---|---|
| LMArena Text | — | 1308 |
| LMArena Creative Writing | — | 1288 |
| LMArena Multi-Turn | — | 1315 |
Frequently asked questions
Is Devstral Small 2505 better than Llama 3.3 Nemotron 49b Super v1?
Llama 3.3 Nemotron 49b Super v1 is the stronger model overall, scoring 40.1 to 34.3 on the Noometry Index.
Is Devstral Small 2505 or Llama 3.3 Nemotron 49b Super v1 better for coding?
Devstral Small 2505 scores higher on coding benchmarks: 38.9 versus 37.9 in the Noometry coding category.
How many benchmarks do Devstral Small 2505 and Llama 3.3 Nemotron 49b Super v1 share?
0 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and Llama 3.3 Nemotron 49b Super v1 has 10.