Model comparison
GLM-5 vs Nemotron 3 Ultra
GLM-5 is the stronger model overall, scoring 46.1 to 42.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
NVIDIASummary
- They share 22 benchmarks with published results for both. GLM-5 scores higher in 6 categories and Nemotron 3 Ultra in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5 leads 46.4 to 35.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 86.7% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.60 / $2.40 per million input/output tokens, against $1 / $3.20 for GLM-5.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 205K.
Side by side
| GLM-5 | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Z.ai (Zhipu) | NVIDIA |
| Noometry Index | 46.1 | 42.5 |
| Released | 2026-02-11 | 2026-06-04 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1 | $0.60 |
| Output $ / M tokens | $3.20 | $2.40 |
| Results tracked | 45 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| WeirdML | 48.2% | 43.5% |
| LMArena Coding | 1461 | 1468 |
| SWE-bench Verified | 72.1% | — |
| FrontierCode | — | 13.6% |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 40.3% |
| ALE-Bench | 765.62 | — |
Agentic & Tool Use GLM-5 leads
GLM-5: 31.1 (#71), Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| APEX-Agents | — | 22.7% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning Nemotron 3 Ultra leads
GLM-5: 27.6 (#116), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| Chess Puzzles | 10% | 12% |
| LMArena Hard Prompts | 1452 | 1452 |
| Epoch Capabilities Index | 145.83 | 146.17 |
| ARC-AGI-2 | 4.9% | — |
| SimpleBench | 53.2% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 74.8% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 3.1% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| ForecastBench | 61 | — |
Math GLM-5 leads
GLM-5: 46.4 (#71), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 86.7% |
| LMArena Math | 1440 | 1457 |
| MathArena Final-Answer Competitions | 65.7% | — |
| ProofBench | — | 2% |
| FrontierMath (Feb 2025 set) | 16.4% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Too close to call
GLM-5: 52.3 (#64), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 87.8% | 85.4% |
| LMArena Expert | 1454 | 1472 |
| Vectara Hallucination Rate | 10.1% | — |
Multilingual Too close to call
GLM-5: 53.7 (#58), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1430 | 1427 |
| LMArena Chinese | 1511 | 1497 |
| LMArena French | 1455 | 1472 |
| LMArena German | 1445 | 1471 |
| LMArena Korean | 1423 | 1386 |
| LMArena Russian | 1436 | 1417 |
| LMArena Spanish | 1454 | 1454 |
| LMArena Japanese | 1416 | — |
Instruction Following Too close to call
GLM-5: 75.2 (#67), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1428 | 1418 |
Long Context Too close to call
GLM-5: 44.7 (#60), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1446 | 1437 |
| CL-bench | 18.7% | — |
Writing & Preference Too close to call
GLM-5: 66.0 (#38), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | GLM-5 | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1446 | 1445 |
| LMArena Creative Writing | 1439 | 1398 |
| EQ-Bench Creative Writing | 1601 | 1692 |
| LMArena Multi-Turn | 1456 | 1411 |
Frequently asked questions
Is GLM-5 better than Nemotron 3 Ultra?
GLM-5 is the stronger model overall, scoring 46.1 to 42.5 on the Noometry Index.
Which is cheaper, GLM-5 or Nemotron 3 Ultra?
Nemotron 3 Ultra is cheaper. It lists at $0.60 per million input tokens and $2.40 per million output tokens; GLM-5 lists at $1 and $3.20.
Is GLM-5 or Nemotron 3 Ultra better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 38.1 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Ultra does, with 262K tokens against 205K.
How many benchmarks do GLM-5 and Nemotron 3 Ultra share?
22 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and Nemotron 3 Ultra has 30.