Model comparison
Mistral Small 3 vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 31.2 on the Noometry Index. Mistral Small 3 costs 16× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 20 benchmarks with published results for both. Mistral Small 3 scores higher in 0 categories and Nemotron 3 Ultra in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 32.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for Mistral Small 3 and 86.7% for Nemotron 3 Ultra.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 33K.
Side by side
| Mistral Small 3 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 31.2 | 42.5 |
| Released | 2025-01-30 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 33K | 262K |
| Max output | 16K | 128K |
| Input $ / M tokens | $0.05 | $0.50 |
| Output $ / M tokens | $0.08 | $2.20 |
| Results tracked | 24 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Mistral Small 3: 36.5 (#207), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Coding | 1246 | 1468 |
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Agentic & Tool Use Not comparable
Mistral Small 3: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
Mistral Small 3: 18.9 (#273), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| Chess Puzzles | 0% | 12% |
| LMArena Hard Prompts | 1233 | 1452 |
| Epoch Capabilities Index | 127.07 | 146.17 |
| CritPt | — | 3.1% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
Math Nemotron 3 Ultra leads
Mistral Small 3: 16.3 (#295), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.7% | 86.7% |
| LMArena Math | 1240 | 1457 |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
Mistral Small 3: 25.1 (#263), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 47.3% | 85.4% |
| LMArena Expert | 1202 | 1472 |
| Confabulations | 25.2% | — |
Multilingual Nemotron 3 Ultra leads
Mistral Small 3: 37.3 (#236), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1198 | 1427 |
| LMArena Chinese | 1204 | 1497 |
| LMArena French | 1203 | 1472 |
| LMArena German | 1211 | 1471 |
| LMArena Korean | 1188 | 1386 |
| LMArena Russian | 1216 | 1417 |
| LMArena Japanese | 1111 | — |
| LMArena Spanish | — | 1454 |
Instruction Following Nemotron 3 Ultra leads
Mistral Small 3: 63.7 (#229), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1214 | 1418 |
Long Context Nemotron 3 Ultra leads
Mistral Small 3: 37.8 (#211), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1246 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Mistral Small 3: 32.2 (#280), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Mistral Small 3 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1234 | 1445 |
| LMArena Creative Writing | 1195 | 1398 |
| EQ-Bench Creative Writing | 707 | 1692 |
| LMArena Multi-Turn | 1217 | 1411 |
Frequently asked questions
Is Mistral Small 3 better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 31.2 on the Noometry Index. Mistral Small 3 costs 16× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.
Which is cheaper, Mistral Small 3 or Nemotron 3 Ultra?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is Mistral Small 3 or Nemotron 3 Ultra better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 33K.
How many benchmarks do Mistral Small 3 and Nemotron 3 Ultra share?
20 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Nemotron 3 Ultra has 30.