Model comparison
GLM-4.5-Air vs Yi-Lightning
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 37.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GLM-4.5-Air scores higher in 6 categories and Yi-Lightning in 2 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.5-Air leads 49.1 to 42.2.
- GLM-4.5-Air has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5-Air | Yi-Lightning | |
|---|---|---|
| Provider | Z.ai (Zhipu) | 01.AI |
| Noometry Index | 38.9 | 37.1 |
| Released | 2025-07-20 | 2024-12-02 |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 98K | — |
| Input $ / M tokens | $0.20 | — |
| Output $ / M tokens | $1.10 | — |
| Results tracked | 27 | 18 |
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), Yi-Lightning: 27.4 (#320)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Coding | 1397 | 1312 |
| Aider Polyglot | — | 12.9% |
| GSO | 2.9% | — |
Reasoning Yi-Lightning leads
GLM-4.5-Air: 24.1 (#166), Yi-Lightning: 25.9 (#139)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Hard Prompts | 1379 | 1302 |
| Kagi LLM Benchmark | 43% | — |
| ForecastBench | 59.2 | — |
Math Too close to call
GLM-4.5-Air: 36.2 (#170), Yi-Lightning: 36.2 (#172)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Math | 1396 | 1300 |
| Omni-MATH | 39.1% | — |
Knowledge Too close to call
GLM-4.5-Air: 35.0 (#191), Yi-Lightning: 35.4 (#185)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Expert | 1370 | 1286 |
| 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), Yi-Lightning: 42.2 (#196)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Non-English | 1366 | 1269 |
| LMArena Chinese | 1426 | 1320 |
| LMArena French | 1399 | 1305 |
| LMArena German | 1377 | 1267 |
| LMArena Japanese | 1348 | 1228 |
| LMArena Korean | 1308 | 1192 |
| LMArena Russian | 1373 | 1255 |
| LMArena Spanish | 1386 | 1315 |
Instruction Following GLM-4.5-Air leads
GLM-4.5-Air: 69.6 (#171), Yi-Lightning: 67.4 (#196)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Instruction Following | 1354 | 1278 |
| IFEval | 81.2% | — |
Long Context GLM-4.5-Air leads
GLM-4.5-Air: 41.6 (#135), Yi-Lightning: 39.4 (#181)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Longer Query | 1366 | 1297 |
Writing & Preference GLM-4.5-Air leads
GLM-4.5-Air: 55.9 (#139), Yi-Lightning: 50.2 (#184)
| Benchmark | GLM-4.5-Air | Yi-Lightning |
|---|---|---|
| LMArena Text | 1384 | 1302 |
| LMArena Creative Writing | 1343 | 1280 |
| LMArena Multi-Turn | 1371 | 1311 |
| WildBench | 78.9% | — |
Frequently asked questions
Is GLM-4.5-Air better than Yi-Lightning?
GLM-4.5-Air is the stronger model overall, scoring 38.9 to 37.1 on the Noometry Index.
Is GLM-4.5-Air or Yi-Lightning better for coding?
GLM-4.5-Air scores higher on coding benchmarks: 33.3 versus 27.4 in the Noometry coding category.
How many benchmarks do GLM-4.5-Air and Yi-Lightning share?
17 benchmarks have published results for both models. GLM-4.5-Air has 27 scored results on Noometry and Yi-Lightning has 18.