Model comparison
Codellama 70b Instruct vs Nemotron 3 Ultra
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.7 on the Noometry Index.
Last verified . 4 shared benchmarks.
Meta
NVIDIASummary
- They share 4 benchmarks with published results for both. Codellama 70b Instruct scores higher in 0 categories and Nemotron 3 Ultra in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 33.4.
Side by side
| Codellama 70b Instruct | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 33.7 | 42.5 |
| Released | — | 2026-06-04 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 7 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Codellama 70b Instruct: 37.6 (#193), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | — | 13.6% |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| BigCodeBench Instruct | 40.7% | — |
| LMArena Coding | — | 1468 |
| BigCodeBench Complete | 49.6% | — |
| HumanEval+ | 65.9% | — |
Agentic & Tool Use Not comparable
Codellama 70b Instruct: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
Codellama 70b Instruct: 20.1 (#242), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Hard Prompts | 1052 | 1452 |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |
Math Not comparable
Codellama 70b Instruct: —, Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| ProofBench | — | 2% |
| LMArena Math | — | 1457 |
Knowledge Not comparable
Codellama 70b Instruct: —, Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |
Multilingual Nemotron 3 Ultra leads
Codellama 70b Instruct: 24.8 (#288), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 992 | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |
Instruction Following Nemotron 3 Ultra leads
Codellama 70b Instruct: 51.9 (#293), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1024 | 1418 |
Long Context Not comparable
Codellama 70b Instruct: —, Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Codellama 70b Instruct: 33.4 (#277), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Codellama 70b Instruct | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1057 | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |
Frequently asked questions
Is Codellama 70b Instruct better than Nemotron 3 Ultra?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 33.7 on the Noometry Index.
Is Codellama 70b Instruct or Nemotron 3 Ultra better for coding?
They score almost the same on coding (37.6 vs 38.1); test both on your own repository before choosing.
How many benchmarks do Codellama 70b Instruct and Nemotron 3 Ultra share?
4 benchmarks have published results for both models. Codellama 70b Instruct has 7 scored results on Noometry and Nemotron 3 Ultra has 30.