Model comparison
GLM-4.5-Air vs Llama 3-8B
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 25.5 on the Noometry Index.
Last verified . 18 shared benchmarks.
MetaSummary
- They share 18 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-4.5-Air leads 36.2 to 8.8.
Side by side
| GLM-4.5-Air | Llama 3-8B | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 38.9 | 25.5 |
| 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 | 34 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.5-Air leads
GLM-4.5-Air: 33.3 (#259), Llama 3-8B: 31.0 (#289)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Coding | 1397 | 1152 |
| GSO | 2.9% | — |
| BigCodeBench Instruct | — | 31.9% |
| BigCodeBench Complete | — | 36.9% |
| HumanEval+ | — | 56.7% |
| MBPP+ | — | 54.8% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Llama 3-8B: 14.3 (#326)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1133 |
| ForecastBench | 59.2 | 58.6 |
| Kagi LLM Benchmark | 43% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 43.9% |
| Adversarial NLI | — | 57.3% |
| Epoch Capabilities Index | — | 116.45 |
| WinoGrande | — | 75.7% |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Llama 3-8B: 8.8 (#323)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Math | 1396 | 1151 |
| OTIS Mock AIME 2024-2025 | — | 1.9% |
| Omni-MATH | 39.1% | — |
| MATH Level 5 | — | 6.1% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Llama 3-8B: 7.8 (#308)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Expert | 1370 | 1113 |
| GPQA Diamond | — | 26.1% |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| ARC (AI2) Challenge | — | 82.8% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 82.6% |
| TriviaQA | — | 67.7% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Llama 3-8B: 30.8 (#261)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Non-English | 1366 | 1098 |
| LMArena Chinese | 1426 | 1076 |
| LMArena French | 1399 | 1159 |
| LMArena German | 1377 | 1104 |
| LMArena Japanese | 1348 | 967 |
| LMArena Korean | 1308 | 1004 |
| LMArena Russian | 1373 | 1109 |
| LMArena Spanish | 1386 | 1173 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Llama 3-8B: 58.4 (#260)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Instruction Following | 1354 | 1127 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Llama 3-8B: 34.2 (#251)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Longer Query | 1366 | 1128 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Llama 3-8B: 37.5 (#256)
| Benchmark | GLM-4.5-Air | Llama 3-8B |
|---|---|---|
| LMArena Text | 1384 | 1166 |
| LMArena Creative Writing | 1343 | 1150 |
| LMArena Multi-Turn | 1371 | 1152 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Llama 3-8B?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 25.5 on the Noometry Index.
Is GLM-4.5-Air or Llama 3-8B better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 31.0 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Llama 3-8B share?
18 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Llama 3-8B has 34.