Model comparison
GLM-5.1 vs Nemotron 3 Ultra
GLM-5.1 is the stronger model overall, scoring 47.8 to 42.5 on the Noometry Index. Nemotron 3 Ultra costs 2.3× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
NVIDIASummary
- They share 26 benchmarks with published results for both. GLM-5.1 scores higher in 9 categories and Nemotron 3 Ultra in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.1 leads 49.7 to 35.3.
- The biggest single-benchmark swing is ProofBench: 22.2% for GLM-5.1 and 2% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.50 / $2.20 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 200K.
Side by side
| GLM-5.1 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Z.ai (Zhipu) | NVIDIA |
| Noometry Index | 47.8 | 42.5 |
| Released | 2026-04-07 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 200K | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $0.50 |
| Output $ / M tokens | $4.40 | $2.20 |
| Results tracked | 41 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-5.1: 48.7 (#55), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 43.8% | 40.3% |
| WeirdML | 57.1% | 43.5% |
| LMArena Coding | 1485 | 1468 |
| SWE-bench Verified | 74.2% | — |
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1508 | — |
| ALE-Bench | 887.1 | — |
Agentic & Tool Use GLM-5.1 leads
GLM-5.1: 24.9 (#113), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | 40.9% | 22.7% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |
Reasoning GLM-5.1 leads
GLM-5.1: 39.1 (#60), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 4.6% | 3.1% |
| Chess Puzzles | 19% | 12% |
| LMArena Hard Prompts | 1472 | 1452 |
| Epoch Capabilities Index | 149.84 | 146.17 |
| SimpleBench | 55.1% | — |
| NYT Connections (extended) | 77.7% | — |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
Math GLM-5.1 leads
GLM-5.1: 49.7 (#60), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 86.7% |
| ProofBench | 22.2% | 2% |
| LMArena Math | 1473 | 1457 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GLM-5.1 leads
GLM-5.1: 54.9 (#50), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 89.9% | 85.4% |
| LMArena Expert | 1476 | 1472 |
| SimpleQA Verified | 34% | — |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1447 | 1427 |
| LMArena Chinese | 1515 | 1497 |
| LMArena French | 1474 | 1472 |
| LMArena German | 1465 | 1471 |
| LMArena Korean | 1418 | 1386 |
| LMArena Russian | 1454 | 1417 |
| LMArena Spanish | 1469 | 1454 |
| LMArena Japanese | 1434 | — |
Instruction Following GLM-5.1 leads
GLM-5.1: 76.3 (#42), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1451 | 1418 |
Long Context Too close to call
GLM-5.1: 44.9 (#53), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1466 | 1437 |
Writing & Preference Too close to call
GLM-5.1: 66.9 (#31), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | GLM-5.1 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1461 | 1445 |
| LMArena Creative Writing | 1453 | 1398 |
| EQ-Bench Creative Writing | 1592 | 1692 |
| LMArena Multi-Turn | 1472 | 1411 |
Frequently asked questions
Is GLM-5.1 better than Nemotron 3 Ultra?
GLM-5.1 is the stronger model overall, scoring 47.8 to 42.5 on the Noometry Index. Nemotron 3 Ultra costs 2.3× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-5.1 or Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. It lists at $0.50 per million input tokens and $2.20 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or Nemotron 3 Ultra better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 200K.
How many benchmarks do GLM-5.1 and Nemotron 3 Ultra share?
26 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Nemotron 3 Ultra has 30.