Model comparison
Llama 3.1 Nemotron 70b Instruct vs Phi-4
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 31.2 on the Noometry Index.
Last verified . 14 shared benchmarks.
NVIDIA
MicrosoftSummary
- They share 14 benchmarks with published results for both. Llama 3.1 Nemotron 70b Instruct scores higher in 8 categories and Phi-4 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 3.1 Nemotron 70b Instruct leads 35.5 to 20.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 48.2% for Llama 3.1 Nemotron 70b Instruct and 55.4% for Phi-4.
Side by side
| Llama 3.1 Nemotron 70b Instruct | Phi-4 | |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 37.6 | 31.2 |
| Released | 2024-12-18 | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.07 |
| Output $ / M tokens | — | $0.14 |
| Results tracked | 14 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 35.9 (#216), Phi-4: 34.4 (#239)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| BigCodeBench Instruct | 38.7% | 45.5% |
| LMArena Coding | 1272 | 1231 |
| BigCodeBench Complete | 48.2% | 55.4% |
| LiveBench Coding | — | 30.7% |
Agentic & Tool Use Not comparable
Llama 3.1 Nemotron 70b Instruct: —, Phi-4: 22.8 (#128)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 25.0 (#152), Phi-4: 17.7 (#291)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1266 | 1220 |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 35.5 (#182), Phi-4: 20.8 (#285)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Math | 1271 | 1246 |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 34.1 (#199), Phi-4: 32.6 (#209)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Expert | 1242 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |
Multilingual Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 40.5 (#217), Phi-4: 37.2 (#237)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Non-English | 1245 | 1197 |
| LMArena Chinese | 1263 | 1212 |
| LMArena Russian | 1227 | 1209 |
| LMArena French | — | 1224 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
| LMArena Spanish | — | 1234 |
Instruction Following Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 65.9 (#213), Phi-4: 60.4 (#251)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1252 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Too close to call
Llama 3.1 Nemotron 70b Instruct: 37.6 (#215), Phi-4: 36.9 (#226)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1238 | 1217 |
Writing & Preference Llama 3.1 Nemotron 70b Instruct leads
Llama 3.1 Nemotron 70b Instruct: 48.4 (#203), Phi-4: 40.5 (#244)
| Benchmark | Llama 3.1 Nemotron 70b Instruct | Phi-4 |
|---|---|---|
| LMArena Text | 1283 | 1217 |
| LMArena Creative Writing | 1269 | 1182 |
| LMArena Multi-Turn | 1275 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Llama 3.1 Nemotron 70b Instruct better than Phi-4?
Llama 3.1 Nemotron 70b Instruct is the stronger model overall, scoring 37.6 to 31.2 on the Noometry Index.
Is Llama 3.1 Nemotron 70b Instruct or Phi-4 better for coding?
Llama 3.1 Nemotron 70b Instruct scores higher on coding benchmarks: 35.9 versus 34.4 in the Noometry coding category.
How many benchmarks do Llama 3.1 Nemotron 70b Instruct and Phi-4 share?
14 benchmarks have published results for both models. Llama 3.1 Nemotron 70b Instruct has 14 scored results on Noometry and Phi-4 has 37.