Model comparison
GLM-4.5-Air vs Nemotron 4 340b Instruct
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 35.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
NVIDIASummary
- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 7 categories and Nemotron 4 340b Instruct in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 42.7.
Side by side
| GLM-4.5-Air | Nemotron 4 340b Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | NVIDIA |
| Noometry Index | 38.9 | 35.9 |
| Released | 2025-07-20 | 2024-06-14 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 4 340b Instruct leads
GLM-4.5-Air: 33.3 (#259), Nemotron 4 340b Instruct: 35.2 (#228)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Coding | 1397 | 1209 |
| GSO | 2.9% | — |
Reasoning Too close to call
GLM-4.5-Air: 24.1 (#166), Nemotron 4 340b Instruct: 23.4 (#178)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1202 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Nemotron 4 340b Instruct: 34.3 (#195)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Math | 1396 | 1216 |
| Omni-MATH | 39.1% | — |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Nemotron 4 340b Instruct: 32.0 (#216)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Expert | 1370 | 1171 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Nemotron 4 340b Instruct: 37.9 (#233)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Non-English | 1366 | 1206 |
| LMArena Chinese | 1426 | 1214 |
| LMArena French | 1399 | 1197 |
| LMArena German | 1377 | 1192 |
| LMArena Japanese | 1348 | 1128 |
| LMArena Korean | 1308 | 1148 |
| LMArena Russian | 1373 | 1219 |
| LMArena Spanish | 1386 | 1195 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Nemotron 4 340b Instruct: 63.1 (#232)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Instruction Following | 1354 | 1203 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Nemotron 4 340b Instruct: 37.1 (#221)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Longer Query | 1366 | 1225 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Nemotron 4 340b Instruct: 42.7 (#233)
| Benchmark | GLM-4.5-Air | Nemotron 4 340b Instruct |
|---|---|---|
| LMArena Text | 1384 | 1225 |
| LMArena Creative Writing | 1343 | 1203 |
| LMArena Multi-Turn | 1371 | 1214 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Nemotron 4 340b Instruct?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 35.9 on the Noometry Index.
Is GLM-4.5-Air or Nemotron 4 340b Instruct better for coding?
Nemotron 4 340b Instruct scores higher on coding benchmarks: 35.2 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Nemotron 4 340b Instruct share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Nemotron 4 340b Instruct has 17.