Model comparison
Nemotron 3 Ultra vs Yi-34B
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 27.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
NVIDIASummary
- They share 18 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 8 categories and Yi-34B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 7.5.
- The biggest single-benchmark swing is GPQA Diamond: 85.4% for Nemotron 3 Ultra and 14.7% for Yi-34B.
Side by side
| Nemotron 3 Ultra | Yi-34B | |
|---|---|---|
| Provider | NVIDIA | 01.AI |
| Noometry Index | 42.5 | 27.8 |
| Released | 2026-06-04 | 2023-11-02 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.50 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 30 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Nemotron 3 Ultra: 38.1 (#182), Yi-34B: 32.3 (#274)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| LMArena Coding | 1468 | 1112 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
Agentic & Tool Use Not comparable
Nemotron 3 Ultra: 23.4 (#126), Yi-34B: —
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| APEX-Agents | 22.7% | — |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 31.0 (#82), Yi-34B: 21.2 (#226)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1104 |
| Epoch Capabilities Index | 146.17 | 117.39 |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LMCA | 36.9% | — |
| BIG-Bench Hard | — | 71.7% |
Math Nemotron 3 Ultra leads
Nemotron 3 Ultra: 35.3 (#187), Yi-34B: 21.6 (#282)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| LMArena Math | 1457 | 1114 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#61), Yi-34B: 7.5 (#309)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| GPQA Diamond | 85.4% | 14.7% |
| LMArena Expert | 1472 | 1061 |
| MMLU | — | 76.3% |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.5 (#64), Yi-34B: 29.7 (#264)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| LMArena Non-English | 1427 | 1079 |
| LMArena Chinese | 1497 | 1176 |
| LMArena French | 1472 | 1081 |
| LMArena German | 1471 | 1042 |
| LMArena Korean | 1386 | 959 |
| LMArena Russian | 1417 | 1050 |
| LMArena Spanish | 1454 | 1070 |
| LMArena Japanese | — | 993 |
Instruction Following Nemotron 3 Ultra leads
Nemotron 3 Ultra: 74.7 (#88), Yi-34B: 56.2 (#274)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1418 | 1091 |
Long Context Nemotron 3 Ultra leads
Nemotron 3 Ultra: 43.9 (#81), Yi-34B: 33.2 (#264)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1437 | 1094 |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#36), Yi-34B: 34.1 (#273)
| Benchmark | Nemotron 3 Ultra | Yi-34B |
|---|---|---|
| LMArena Text | 1445 | 1129 |
| LMArena Creative Writing | 1398 | 1108 |
| LMArena Multi-Turn | 1411 | 1113 |
| EQ-Bench Creative Writing | 1692 | — |
Frequently asked questions
Is Nemotron 3 Ultra better than Yi-34B?
Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 27.8 on the Noometry Index.
Is Nemotron 3 Ultra or Yi-34B better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 32.3 in the Noometry coding category.
How many benchmarks do Nemotron 3 Ultra and Yi-34B share?
18 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Yi-34B has 23.