Model comparison
GLM-4.5-Air vs Phi 3 Medium 4k Instruct
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.0 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 Medium 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5-Air leads 55.9 to 34.1.
Side by side
| GLM-4.5-Air | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Microsoft |
| Noometry Index | 38.9 | 33.0 |
| 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 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5-Air: 33.3 (#259), Phi 3 Medium 4k Instruct: 32.9 (#268)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1397 | 1130 |
| GSO | 2.9% | — |
Reasoning GLM-4.5-Air leads
GLM-4.5-Air: 24.1 (#166), Phi 3 Medium 4k Instruct: 21.7 (#214)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1127 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math GLM-4.5-Air leads
GLM-4.5-Air: 36.2 (#170), Phi 3 Medium 4k Instruct: 33.4 (#202)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1396 | 1173 |
| Omni-MATH | 39.1% | — |
Knowledge GLM-4.5-Air leads
GLM-4.5-Air: 35.0 (#191), Phi 3 Medium 4k Instruct: 30.2 (#229)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1370 | 1108 |
| 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), Phi 3 Medium 4k Instruct: 30.6 (#263)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1366 | 1094 |
| LMArena Chinese | 1426 | 1108 |
| LMArena French | 1399 | 1110 |
| LMArena German | 1377 | 1101 |
| LMArena Japanese | 1348 | 1042 |
| LMArena Korean | 1308 | 954 |
| LMArena Russian | 1373 | 1145 |
| LMArena Spanish | 1386 | 1095 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Phi 3 Medium 4k Instruct: 57.6 (#268)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1354 | 1113 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Phi 3 Medium 4k Instruct: 34.0 (#255)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1366 | 1120 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Phi 3 Medium 4k Instruct: 34.1 (#272)
| Benchmark | GLM-4.5-Air | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1384 | 1138 |
| LMArena Creative Writing | 1343 | 1107 |
| LMArena Multi-Turn | 1371 | 1088 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Phi 3 Medium 4k Instruct?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 33.0 on the Noometry Index.
Is GLM-4.5-Air or Phi 3 Medium 4k Instruct better for coding?
They score almost the same on coding (33.3 vs 32.9); test both on your own repository before choosing.
How many benchmarks do GLM-4.5-Air and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.