Model comparison
GLM-4.5-Air vs Phi 3 Small 8k Instruct
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
MicrosoftSummary
- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 8 categories and Phi 3 Small 8k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 31.1.
Side by side
| GLM-4.5-Air | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 38.9 | 29.3 |
| Released | 2025-07-20 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 32 |
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), Phi 3 Small 8k Instruct: 27.9 (#318)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1397 | 1101 |
| GSO | 2.9% | — |
| LiveBench Coding | — | 20.3% |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Phi 3 Small 8k Instruct: 14.8 (#323)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1100 |
| Kagi LLM Benchmark | 43% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| ForecastBench | 59.2 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Phi 3 Small 8k Instruct: 27.6 (#248)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1396 | 1151 |
| Omni-MATH | 39.1% | — |
| LiveBench Math | — | 17.6% |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Phi 3 Small 8k Instruct: 29.1 (#240)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1370 | 1067 |
| Humanity's Last Exam | 8.1% | — |
| MMLU-Pro | 76.2% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 59.4% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual GLM-4.5-Air leads
GLM-4.5-Air: 49.1 (#135), Phi 3 Small 8k Instruct: 28.5 (#272)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1366 | 1058 |
| LMArena Chinese | 1426 | 1061 |
| LMArena French | 1399 | 1135 |
| LMArena German | 1377 | 1080 |
| LMArena Japanese | 1348 | 966 |
| LMArena Korean | 1308 | 894 |
| LMArena Russian | 1373 | 1111 |
| LMArena Spanish | 1386 | 1111 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Phi 3 Small 8k Instruct: 51.9 (#292)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1354 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Phi 3 Small 8k Instruct: 33.0 (#267)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1366 | 1088 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Phi 3 Small 8k Instruct: 31.1 (#284)
| Benchmark | GLM-4.5-Air | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1384 | 1110 |
| LMArena Creative Writing | 1343 | 1083 |
| LMArena Multi-Turn | 1371 | 1068 |
| WildBench | 78.9% | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is GLM-4.5-Air better than Phi 3 Small 8k Instruct?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 29.3 on the Noometry Index.
Is GLM-4.5-Air or Phi 3 Small 8k Instruct better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 27.9 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Phi 3 Small 8k Instruct share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Phi 3 Small 8k Instruct has 32.