Model comparison
Ministral 8B vs Nemotron 4 340b Instruct
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 28.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AI
NVIDIASummary
- They share 12 benchmarks with published results for both. Ministral 8B scores higher in 0 categories and Nemotron 4 340b Instruct in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 4 340b Instruct leads 32.0 to 12.6.
Side by side
| Ministral 8B | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | Mistral AI | NVIDIA |
| Noometry Index | 28.2 | 35.9 |
| Released | 2024-10-01 | 2024-06-14 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 17 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Ministral 8B: 35.0 (#230), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1202 | 1209 |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Nemotron 4 340b Instruct: —
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Nemotron 4 340b Instruct leads
Ministral 8B: 18.4 (#281), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1202 |
| DTBench | 45.7% | — |
Math Nemotron 4 340b Instruct leads
Ministral 8B: 25.7 (#267), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1188 | 1216 |
| MATH Level 5 | 14.9% | — |
Knowledge Nemotron 4 340b Instruct leads
Ministral 8B: 12.6 (#297), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1170 | 1171 |
| GPQA Diamond | 27.1% | — |
| Vectara Hallucination Rate | 7.4% | — |
Multilingual Nemotron 4 340b Instruct leads
Ministral 8B: 35.1 (#247), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1165 | 1206 |
| LMArena Chinese | 1193 | 1214 |
| LMArena Russian | 1195 | 1219 |
| LMArena French | — | 1197 |
| LMArena German | — | 1192 |
| LMArena Japanese | — | 1128 |
| LMArena Korean | — | 1148 |
| LMArena Spanish | — | 1195 |
Instruction Following Nemotron 4 340b Instruct leads
Ministral 8B: 60.5 (#250), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1161 | 1203 |
Long Context Too close to call
Ministral 8B: 36.7 (#227), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1212 | 1225 |
Writing & Preference Nemotron 4 340b Instruct leads
Ministral 8B: 39.6 (#246), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | Ministral 8B | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1191 | 1225 |
| LMArena Creative Writing | 1175 | 1203 |
| LMArena Multi-Turn | 1166 | 1214 |
Frequently asked questions
Is Ministral 8B better than Nemotron 4 340b Instruct?
Nemotron 4 340b Instruct is the stronger model overall, scoring 35.9 to 28.2 on the Noometry Index.
Is Ministral 8B or Nemotron 4 340b Instruct better for coding?
They score almost the same on coding (35.0 vs 35.2); test both on your own repository before choosing.
How many benchmarks do Ministral 8B and Nemotron 4 340b Instruct share?
12 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Nemotron 4 340b Instruct has 17.