Model comparison
Claude 3 Opus vs Nemotron 3 Super
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 29.5 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIASummary
- They share 16 benchmarks with published results for both. Claude 3 Opus scores higher in 0 categories and Nemotron 3 Super in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Super leads 39.6 to 14.8.
- The biggest single-benchmark swing is WeirdML: 19.2% for Claude 3 Opus and 38% for Nemotron 3 Super.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| Claude 3 Opus | Nemotron 3 Super | |
|---|---|---|
| Provider | Anthropic | NVIDIA |
| Noometry Index | 29.5 | 40.1 |
| Released | 2024-02-29 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.45 |
| Results tracked | 46 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Claude 3 Opus: 32.9 (#267), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| WeirdML | 19.2% | 38% |
| LMArena Coding | 1264 | 1403 |
| SciCode | — | 36% |
| BigCodeBench Instruct | 45.5% | — |
| LiveBench Coding | 38.6% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 213.9 |
| HumanEval+ | 77.4% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Opus: 24.6 (#116), Nemotron 3 Super: —
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| Cybench | 10% | — |
| METR Time Horizons | 29.5% | — |
Reasoning Nemotron 3 Super leads
Claude 3 Opus: 14.6 (#324), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1245 | 1386 |
| SimpleBench | 23.5% | — |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
| Chess Puzzles | 5% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 40.6% | — |
| DTBench | 61.6% | — |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | 17% | — |
| Epoch Capabilities Index | 126.91 | — |
| ForecastBench | 58.4 | — |
| LiveBench | 49.2% | — |
| WinoGrande | 88.5% | — |
Math Nemotron 3 Super leads
Claude 3 Opus: 14.8 (#299), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1273 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 4.7% | — |
| LiveBench Math | 43.6% | — |
| MATH Level 5 | 37.5% | — |
Knowledge Nemotron 3 Super leads
Claude 3 Opus: 24.5 (#267), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1223 | 1398 |
| GPQA Diamond | 47.2% | — |
| SimpleQA Verified | 12.6% | — |
| Confabulations | 22.7% | — |
| MMLU | 84.6% | — |
Multimodal Not comparable
Claude 3 Opus: 27.1 (#116), Nemotron 3 Super: —
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Vision | 1023 | — |
Multilingual Nemotron 3 Super leads
Claude 3 Opus: 41.4 (#207), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1258 | 1355 |
| LMArena Chinese | 1248 | 1432 |
| LMArena French | 1275 | 1405 |
| LMArena German | 1258 | 1341 |
| LMArena Russian | 1280 | 1336 |
| LMArena Spanish | 1246 | 1417 |
| LMArena Japanese | 1204 | — |
| LMArena Korean | 1187 | — |
Instruction Following Nemotron 3 Super leads
Claude 3 Opus: 64.1 (#228), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1248 | 1347 |
| LiveBench Instruction Following | 63.9% | — |
Long Context Nemotron 3 Super leads
Claude 3 Opus: 38.2 (#202), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1259 | 1362 |
Writing & Preference Nemotron 3 Super leads
Claude 3 Opus: 47.2 (#213), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Claude 3 Opus | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1262 | 1378 |
| LMArena Creative Writing | 1235 | 1317 |
| LMArena Multi-Turn | 1275 | 1369 |
| LiveBench Language | 50.4% | — |
Frequently asked questions
Is Claude 3 Opus better than Nemotron 3 Super?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 29.5 on the Noometry Index.
Is Claude 3 Opus or Nemotron 3 Super better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3 Opus and Nemotron 3 Super share?
16 benchmarks have published results for both models. Claude 3 Opus has 46 scored results on Noometry and Nemotron 3 Super has 21.