Model comparison
GLM-4.5-Air vs Llama 3-70B
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 28.8 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. GLM-4.5-Air scores higher in 7 categories and Llama 3-70B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 36.2 to 12.8.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 43% for GLM-4.5-Air and 35.1% for Llama 3-70B.
Side by side
| GLM-4.5-Air | Llama 3-70B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 38.9 | 28.8 |
| Released | 2025-07-20 | 2024-04-18 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-70B leads
GLM-4.5-Air: 33.3 (#259), Llama 3-70B: 35.8 (#218)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| LMArena Coding | 1397 | 1206 |
| GSO | 2.9% | — |
| BigCodeBench Instruct | — | 43.6% |
| BigCodeBench Complete | — | 54.5% |
| HumanEval+ | — | 72% |
| MBPP+ | — | 69% |
Agentic & Tool Use Not comparable
GLM-4.5-Air: —, Llama 3-70B: 21.1 (#139)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| Cybench | — | 5% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Llama 3-70B: 18.0 (#288)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| Kagi LLM Benchmark | 43% | 35.1% |
| LMArena Hard Prompts | 1379 | 1195 |
| ForecastBench | 59.2 | 57.1 |
| DTBench | — | 54.2% |
| Epoch Capabilities Index | — | 122.93 |
| WinoGrande | — | 83.5% |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Llama 3-70B: 12.8 (#305)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| LMArena Math | 1396 | 1218 |
| OTIS Mock AIME 2024-2025 | — | 4.3% |
| Omni-MATH | 39.1% | — |
| MATH Level 5 | — | 22.6% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Llama 3-70B: 20.8 (#277)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| LMArena Expert | 1370 | 1149 |
| GPQA Diamond | — | 40.6% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| MMLU | — | 79.3% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Llama 3-70B: 33.6 (#251)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| LMArena Non-English | 1366 | 1142 |
| LMArena Chinese | 1426 | 1114 |
| LMArena French | 1399 | 1232 |
| LMArena German | 1377 | 1169 |
| LMArena Japanese | 1348 | 1017 |
| LMArena Korean | 1308 | 1017 |
| LMArena Russian | 1373 | 1159 |
| LMArena Spanish | 1386 | 1241 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Llama 3-70B: 62.5 (#238)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| LMArena Instruction Following | 1354 | 1194 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Llama 3-70B: 35.6 (#240)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| LMArena Longer Query | 1366 | 1174 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Llama 3-70B: 42.8 (#231)
| Benchmark | GLM-4.5-Air | Llama 3-70B |
|---|---|---|
| LMArena Text | 1384 | 1221 |
| LMArena Creative Writing | 1343 | 1210 |
| LMArena Multi-Turn | 1371 | 1223 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Llama 3-70B?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 28.8 on the Noometry Index.
Is GLM-4.5-Air or Llama 3-70B better for coding?
Llama 3-70B scores higher on coding benchmarks: 35.8 versus 33.3 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Llama 3-70B share?
19 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Llama 3-70B has 31.