Model comparison
Llama 3.1 Nemotron 70b Instruct vs Llama 3.2 90B
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 27.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
NVIDIA
MetaSummary
- The widest gap is in math, where Llama 3.1 Nemotron 70b Instruct leads 35.5 to 11.1.
Side by side
| Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B | |
|---|---|---|
| Provider | NVIDIA | Meta |
| Noometry Index | 37.6 | 27.5 |
| Released | 2024-12-18 | 2024-09-24 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 14 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Llama 3.1 Nemotron 70b Instruct: 35.9 (#216), Llama 3.2 90B: —
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| BigCodeBench Instruct | 38.7% | — |
| LMArena Coding | 1272 | — |
| BigCodeBench Complete | 48.2% | — |
Agentic & Tool Use Not comparable
Llama 3.1 Nemotron 70b Instruct: —, Llama 3.2 90B: 30.0 (#80)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| BALROG | — | 27.3% |
Reasoning Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 25.0 (#152), Llama 3.2 90B: 21.7 (#217)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| EnigmaEval | — | 0.4% |
| LMArena Hard Prompts | 1266 | — |
| Epoch Capabilities Index | — | 125.5 |
Math Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 35.5 (#182), Llama 3.2 90B: 11.1 (#308)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.6% |
| LMArena Math | 1271 | — |
| MATH Level 5 | — | 39.4% |
Knowledge Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 34.1 (#199), Llama 3.2 90B: 21.7 (#274)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| GPQA Diamond | — | 41% |
| LMArena Expert | 1242 | — |
| MMLU | — | 80.3% |
Multimodal Not comparable
Llama 3.1 Nemotron 70b Instruct: —, Llama 3.2 90B: 25.4 (#124)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Vision | — | 1000 |
| GeoBench | — | 52% |
Multilingual Not comparable
Llama 3.1 Nemotron 70b Instruct: 40.5 (#217), Llama 3.2 90B: —
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Non-English | 1245 | — |
| LMArena Chinese | 1263 | — |
| LMArena Russian | 1227 | — |
Instruction Following Not comparable
Llama 3.1 Nemotron 70b Instruct: 65.9 (#213), Llama 3.2 90B: —
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Instruction Following | 1252 | — |
Long Context Not comparable
Llama 3.1 Nemotron 70b Instruct: 37.6 (#215), Llama 3.2 90B: —
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Longer Query | 1238 | — |
Writing & Preference Not comparable
Llama 3.1 Nemotron 70b Instruct: 48.4 (#203), Llama 3.2 90B: —
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Llama 3.2 90B |
|---|---|---|
| LMArena Text | 1283 | — |
| LMArena Creative Writing | 1269 | — |
| LMArena Multi-Turn | 1275 | — |
Frequently asked questions
Is Llama 3.1 Nemotron 70b Instruct better than Llama 3.2 90B?
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 27.5 on the Noometry Index.
How many benchmarks do Llama 3.1 Nemotron 70b Instruct and Llama 3.2 90B share?
0 benchmarks have published results for both models. Llama 3.1 Nemotron 70b Instruct has 14 scored results on Noometry and Llama 3.2 90B has 9.