Model comparison
Llama 3.1 Nemotron Ultra 253b v1 vs Ministral 8B
Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 28.2 on the Noometry Index.
Last verified . 11 shared benchmarks.
NVIDIA
Mistral AISummary
- They share 11 benchmarks with published results for both. Llama 3.1 Nemotron Ultra 253b v1 scores higher in 7 categories and Ministral 8B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama 3.1 Nemotron Ultra 253b v1 leads 52.2 to 39.6.
Side by side
| Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B | |
|---|---|---|
| Provider | NVIDIA | Mistral AI |
| Noometry Index | 36.7 | 28.2 |
| Released | — | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 11 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177), Ministral 8B: 35.0 (#230)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1312 | 1202 |
Agentic & Tool Use Too close to call
Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149), Ministral 8B: 16.4 (#148)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 10% | 11.1% |
Reasoning Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134), Ministral 8B: 18.4 (#281)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1316 | 1191 |
| DTBench | — | 45.7% |
Math Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152), Ministral 8B: 25.7 (#267)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| LMArena Math | 1360 | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Not comparable
Llama 3.1 Nemotron Ultra 253b v1: —, Ministral 8B: 12.6 (#297)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
| LMArena Expert | — | 1170 |
Multilingual Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187), Ministral 8B: 35.1 (#247)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1282 | 1165 |
| LMArena Russian | 1284 | 1195 |
| LMArena Chinese | — | 1193 |
Instruction Following Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178), Ministral 8B: 60.5 (#250)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1308 | 1161 |
Long Context Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177), Ministral 8B: 36.7 (#227)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1299 | 1212 |
Writing & Preference Llama 3.1 Nemotron Ultra 253b v1 leads
Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175), Ministral 8B: 39.6 (#246)
| Benchmark | Llama 3.1 Nemotron Ultra 253b v1 | Ministral 8B |
|---|---|---|
| LMArena Text | 1320 | 1191 |
| LMArena Creative Writing | 1314 | 1175 |
| LMArena Multi-Turn | 1317 | 1166 |
Frequently asked questions
Is Llama 3.1 Nemotron Ultra 253b v1 better than Ministral 8B?
Llama 3.1 Nemotron Ultra 253b v1 is the stronger model overall, scoring 36.7 to 28.2 on the Noometry Index.
Is Llama 3.1 Nemotron Ultra 253b v1 or Ministral 8B better for coding?
Llama 3.1 Nemotron Ultra 253b v1 scores higher on coding benchmarks: 38.4 versus 35.0 in the Noometry coding category.
How many benchmarks do Llama 3.1 Nemotron Ultra 253b v1 and Ministral 8B share?
11 benchmarks have published results for both models. Llama 3.1 Nemotron Ultra 253b v1 has 11 scored results on Noometry and Ministral 8B has 17.