Model comparison
Gemma 4 26B A4B IT vs Nemotron 3 Ultra
Gemma 4 26B A4B IT and Nemotron 3 Ultra score almost the same on the Noometry Index (43.5 vs 42.5), so choose on price, context window or the category you care about most.
Last verified . 24 shared benchmarks.
Google
NVIDIASummary
- They share 24 benchmarks with published results for both. Gemma 4 26B A4B IT scores higher in 3 categories and Nemotron 3 Ultra in 5 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Gemma 4 26B A4B IT leads 47.6 to 35.3.
- The biggest single-benchmark swing is DTBench: 74.9% for Gemma 4 26B A4B IT and 90.1% for Nemotron 3 Ultra.
- Gemma 4 26B A4B IT is cheaper at $0.0675 / $0.23 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
Side by side
| Gemma 4 26B A4B IT | Nemotron 3 Ultra | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 43.5 | 42.5 |
| Released | 2026-04-02 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 262K | 262K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.0675 | $0.50 |
| Output $ / M tokens | $0.23 | $2.20 |
| Results tracked | 28 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 4 26B A4B IT: 39.0 (#164), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 40% | 40.3% |
| WeirdML | 35.2% | 43.5% |
| LMArena Coding | 1447 | 1468 |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1359 | — |
| ALE-Bench | 927.17 | — |
Agentic & Tool Use Not comparable
Gemma 4 26B A4B IT: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Nemotron 3 Ultra leads
Gemma 4 26B A4B IT: 21.8 (#213), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 0% | 3.1% |
| Chess Puzzles | 6% | 12% |
| LMArena Hard Prompts | 1439 | 1452 |
| DTBench | 74.9% | 90.1% |
| LMCA | 29.7% | 36.9% |
| Epoch Capabilities Index | 141.85 | 146.17 |
| Mystery Game Puzzles | — | 20% |
Math Gemma 4 26B A4B IT leads
Gemma 4 26B A4B IT: 47.6 (#67), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 82.2% | 86.7% |
| LMArena Math | 1470 | 1457 |
| ProofBench | — | 2% |
Knowledge Nemotron 3 Ultra leads
Gemma 4 26B A4B IT: 45.7 (#85), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 73.2% | 85.4% |
| LMArena Expert | 1447 | 1472 |
| Vectara Hallucination Rate | 5.2% | — |
Multimodal Not comparable
Gemma 4 26B A4B IT: 40.6 (#46), Nemotron 3 Ultra: —
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1260 | — |
Multilingual Too close to call
Gemma 4 26B A4B IT: 53.1 (#71), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1421 | 1427 |
| LMArena Chinese | 1495 | 1497 |
| LMArena French | 1460 | 1472 |
| LMArena Russian | 1434 | 1417 |
| LMArena Spanish | 1417 | 1454 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
Instruction Following Too close to call
Gemma 4 26B A4B IT: 74.8 (#82), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1420 | 1418 |
Long Context Too close to call
Gemma 4 26B A4B IT: 43.6 (#91), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1428 | 1437 |
Writing & Preference Nemotron 3 Ultra leads
Gemma 4 26B A4B IT: 58.6 (#115), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Gemma 4 26B A4B IT | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1434 | 1445 |
| LMArena Creative Writing | 1402 | 1398 |
| EQ-Bench Creative Writing | 1305 | 1692 |
| LMArena Multi-Turn | 1441 | 1411 |
Frequently asked questions
Is Gemma 4 26B A4B IT better than Nemotron 3 Ultra?
Gemma 4 26B A4B IT and Nemotron 3 Ultra score almost the same on the Noometry Index (43.5 vs 42.5), so choose on price, context window or the category you care about most.
Which is cheaper, Gemma 4 26B A4B IT or Nemotron 3 Ultra?
Gemma 4 26B A4B IT is cheaper. It lists at $0.0675 per million input tokens and $0.23 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.
Is Gemma 4 26B A4B IT or Nemotron 3 Ultra better for coding?
They score almost the same on coding (39.0 vs 38.1); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 262K tokens.
How many benchmarks do Gemma 4 26B A4B IT and Nemotron 3 Ultra share?
24 benchmarks have published results for both models. Gemma 4 26B A4B IT has 28 scored results on Noometry and Nemotron 3 Ultra has 30.