Model comparison
Mistral Small 3 vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 31.2 on the Noometry Index.
Last verified . 16 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 16 benchmarks with published results for both. Mistral Small 3 scores higher in 3 categories and Nemotron 4 340b Instruct in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 4 340b Instruct leads 34.3 to 16.3.
Side by side
| Mistral Small 3 | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 31.2 | 35.9 |
| Released | 2025-01-30 | 2024-06-14 |
| Weights | Open | Open |
| Context window | 33K | — |
| Max output | 16K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.08 | — |
| Results tracked | 24 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Mistral Small 3 leads
Mistral Small 3: 36.5 (#207), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1246 | 1209 |
| BigCodeBench Instruct | 45.3% | — |
| BigCodeBench Complete | 50.4% | — |
Reasoning Nemotron 4 340b Instruct leads
Mistral Small 3: 18.9 (#273), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1233 | 1202 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 127.07 | — |
Math Nemotron 4 340b Instruct leads
Mistral Small 3: 16.3 (#295), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1240 | 1216 |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
Knowledge Nemotron 4 340b Instruct leads
Mistral Small 3: 25.1 (#263), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1202 | 1171 |
| GPQA Diamond | 47.3% | — |
| Confabulations | 25.2% | — |
Multilingual Too close to call
Mistral Small 3: 37.3 (#236), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1198 | 1206 |
| LMArena Chinese | 1204 | 1214 |
| LMArena French | 1203 | 1197 |
| LMArena German | 1211 | 1192 |
| LMArena Japanese | 1111 | 1128 |
| LMArena Korean | 1188 | 1148 |
| LMArena Russian | 1216 | 1219 |
| LMArena Spanish | — | 1195 |
Instruction Following Too close to call
Mistral Small 3: 63.7 (#229), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1214 | 1203 |
Long Context Too close to call
Mistral Small 3: 37.8 (#211), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1246 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
Mistral Small 3: 32.2 (#280), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Mistral Small 3 | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1234 | 1225 |
| LMArena Creative Writing | 1195 | 1203 |
| LMArena Multi-Turn | 1217 | 1214 |
| EQ-Bench Creative Writing | 707 | — |
Frequently asked questions
Is Mistral Small 3 better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 31.2 on the Noometry Index.
Is Mistral Small 3 or Nemotron 4 340b Instruct better for coding?
Mistral Small 3 scores higher on coding benchmarks: 36.5 versus 35.2 in the Noometry coding category.
How many benchmarks do Mistral Small 3 and Nemotron 4 340b Instruct share?
16 benchmarks have published results for both models. Mistral Small 3 has 24 scored results on Noometry and Nemotron 4 340b Instruct has 17.