Model comparison
GLM-4.5-Air vs Llama 3.1 Nemotron Ultra 253b v1
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 36.7 on the Noometry Index.
Last verified . 10 shared benchmarks.
NVIDIASummary
- They share 10 benchmarks with published results for both. GLM-4.5-Air scores higher in 4 categories and Llama 3.1 Nemotron Ultra 253b v1 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.5-Air leads 49.1 to 43.1.
Side by side
| GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | NVIDIA |
| Noometry Index | 38.9 | 36.7 |
| Released | 2025-07-20 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1 Nemotron Ultra 253b v1 leads
GLM-4.5-Air: 33.3 (#259), Llama 3.1 Nemotron Ultra 253b v1: 38.4 (#177)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Coding | 1397 | 1312 |
| GSO | 2.9% | — |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Llama 3.1 Nemotron Ultra 253b v1: 15.7 (#149)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 10% |
Reasoning Llama 3.1 Nemotron Ultra 253b v1 leads
GLM-4.5-Air: 24.1 (#166), Llama 3.1 Nemotron Ultra 253b v1: 26.3 (#134)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1316 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math Llama 3.1 Nemotron Ultra 253b v1 leads
GLM-4.5-Air: 36.2 (#170), Llama 3.1 Nemotron Ultra 253b v1: 37.5 (#152)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Math | 1396 | 1360 |
| Omni-MATH | 39.1% | — |
Knowledge Not comparable
GLM-4.5-Air: 35.0 (#191), Llama 3.1 Nemotron Ultra 253b v1: —
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| LMArena Expert | 1370 | — |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Llama 3.1 Nemotron Ultra 253b v1: 43.1 (#187)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Non-English | 1366 | 1282 |
| LMArena Russian | 1373 | 1284 |
| LMArena Chinese | 1426 | — |
| LMArena French | 1399 | — |
| LMArena German | 1377 | — |
| LMArena Japanese | 1348 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1386 | — |
Instruction Following Too close to call
GLM-4.5-Air: 69.6 (#171), Llama 3.1 Nemotron Ultra 253b v1: 69.0 (#178)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Instruction Following | 1354 | 1308 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Llama 3.1 Nemotron Ultra 253b v1: 39.5 (#177)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Longer Query | 1366 | 1299 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Llama 3.1 Nemotron Ultra 253b v1: 52.2 (#175)
| Benchmark | GLM-4.5-Air | Llama 3.1 Nemotron Ultra 253b v1 |
|---|---|---|
| LMArena Text | 1384 | 1320 |
| LMArena Creative Writing | 1343 | 1314 |
| LMArena Multi-Turn | 1371 | 1317 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Llama 3.1 Nemotron Ultra 253b v1?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 36.7 on the Noometry Index.
Is GLM-4.5-Air or Llama 3.1 Nemotron Ultra 253b v1 better for coding?
Llama 3.1 Nemotron Ultra 253b v1 scores higher on coding benchmarks: 38.4 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Llama 3.1 Nemotron Ultra 253b v1 share?
10 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Llama 3.1 Nemotron Ultra 253b v1 has 11.