Model comparison
Nemotron 3 Ultra vs Olmo 3.1 32b Think
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 37.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
NVIDIA
Allen Institute for AI (Ai2)Summary
- They share 15 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 7 categories and Olmo 3.1 32b Think in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 46.2.
Side by side
| Nemotron 3 Ultra | Olmo 3.1 32b Think | |
|---|---|---|
| Provider | NVIDIA | Allen Institute for AI (Ai2) |
| Noometry Index | 42.5 | 37.9 |
| 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 | 30 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Nemotron 3 Ultra: 38.1 (#182), Olmo 3.1 32b Think: 37.7 (#189)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Coding | 1468 | 1291 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
Agentic & Tool Use Not comparable
Nemotron 3 Ultra: 23.4 (#126), Olmo 3.1 32b Think: —
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| APEX-Agents | 22.7% | — |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 31.0 (#82), Olmo 3.1 32b Think: 25.2 (#150)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1272 |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 146.17 | — |
Math Too close to call
Nemotron 3 Ultra: 35.3 (#187), Olmo 3.1 32b Think: 36.3 (#168)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Math | 1457 | 1305 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#61), Olmo 3.1 32b Think: 35.7 (#181)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Expert | 1472 | 1295 |
| GPQA Diamond | 85.4% | — |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.5 (#64), Olmo 3.1 32b Think: 38.1 (#231)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Non-English | 1427 | 1209 |
| LMArena Chinese | 1497 | 1242 |
| LMArena French | 1472 | 1260 |
| LMArena German | 1471 | 1262 |
| LMArena Russian | 1417 | 1193 |
| LMArena Spanish | 1454 | 1289 |
| LMArena Korean | 1386 | — |
Instruction Following Nemotron 3 Ultra leads
Nemotron 3 Ultra: 74.7 (#88), Olmo 3.1 32b Think: 65.6 (#218)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Instruction Following | 1418 | 1247 |
Long Context Nemotron 3 Ultra leads
Nemotron 3 Ultra: 43.9 (#81), Olmo 3.1 32b Think: 38.6 (#195)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Longer Query | 1437 | 1272 |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#36), Olmo 3.1 32b Think: 46.2 (#220)
| Benchmark | Nemotron 3 Ultra | Olmo 3.1 32b Think |
|---|---|---|
| LMArena Text | 1445 | 1272 |
| LMArena Creative Writing | 1398 | 1226 |
| LMArena Multi-Turn | 1411 | 1252 |
| EQ-Bench Creative Writing | 1692 | — |
Frequently asked questions
Is Nemotron 3 Ultra better than Olmo 3.1 32b Think?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 37.9 on the Noometry Index.
Is Nemotron 3 Ultra or Olmo 3.1 32b Think better for coding?
They score almost the same on coding (38.1 vs 37.7); test both on your own repository before choosing.
How many benchmarks do Nemotron 3 Ultra and Olmo 3.1 32b Think share?
15 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Olmo 3.1 32b Think has 15.