Model comparison
C4ai Aya Expanse 32b vs GLM-4.6
GLM-4.6 is the stronger model overall, scoring 41.4 to 35.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
CohereSummary
- They share 18 benchmarks with published results for both. C4ai Aya Expanse 32b scores higher in 0 categories and GLM-4.6 in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.6 leads 61.1 to 42.2.
- GLM-4.6 accepts more context: 205K tokens versus 128K.
Side by side
| C4ai Aya Expanse 32b | GLM-4.6 | |
|---|---|---|
| Provider | Cohere | Z.ai (Zhipu) |
| Noometry Index | 35.9 | 41.4 |
| Released | 2024-10-24 | 2025-09-30 |
| Weights | Open | Open |
| Context window | 128K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 18 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.6 leads
C4ai Aya Expanse 32b: 34.8 (#231), GLM-4.6: 40.1 (#148)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1197 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 32b: —, GLM-4.6: 32.3 (#66)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning Too close to call
C4ai Aya Expanse 32b: 23.3 (#180), GLM-4.6: 23.7 (#172)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| LMArena Hard Prompts | 1193 | 1440 |
| Kagi LLM Benchmark | — | 47.4% |
| CritPt | — | 1.1% |
Math GLM-4.6 leads
C4ai Aya Expanse 32b: 34.0 (#197), GLM-4.6: 39.1 (#111)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| LMArena Math | 1200 | 1432 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-4.6 leads
C4ai Aya Expanse 32b: 33.2 (#206), GLM-4.6: 40.2 (#124)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| Vectara Hallucination Rate | 10.9% | 9.5% |
| LMArena Expert | 1182 | 1431 |
Multilingual GLM-4.6 leads
C4ai Aya Expanse 32b: 38.4 (#230), GLM-4.6: 53.5 (#66)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1213 | 1426 |
| LMArena Chinese | 1211 | 1499 |
| LMArena French | 1248 | 1459 |
| LMArena German | 1199 | 1447 |
| LMArena Japanese | 1163 | 1393 |
| LMArena Korean | 1158 | 1400 |
| LMArena Russian | 1227 | 1419 |
| LMArena Spanish | 1193 | 1436 |
Instruction Following GLM-4.6 leads
C4ai Aya Expanse 32b: 62.6 (#237), GLM-4.6: 74.3 (#98)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1196 | 1410 |
Long Context GLM-4.6 leads
C4ai Aya Expanse 32b: 37.2 (#220), GLM-4.6: 43.4 (#94)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1228 | 1422 |
Writing & Preference GLM-4.6 leads
C4ai Aya Expanse 32b: 42.2 (#235), GLM-4.6: 61.1 (#90)
| Benchmark | C4ai Aya Expanse 32b | GLM-4.6 |
|---|---|---|
| LMArena Text | 1224 | 1440 |
| LMArena Creative Writing | 1200 | 1411 |
| LMArena Multi-Turn | 1190 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |
Frequently asked questions
Is C4ai Aya Expanse 32b better than GLM-4.6?
GLM-4.6 is the stronger model overall, scoring 41.4 to 35.9 on the Noometry Index.
Is C4ai Aya Expanse 32b or GLM-4.6 better for coding?
GLM-4.6 scores higher on coding benchmarks: 40.1 versus 34.8 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 128K.
How many benchmarks do C4ai Aya Expanse 32b and GLM-4.6 share?
18 benchmarks have published results for both models. C4ai Aya Expanse 32b has 18 scored results on Noometry and GLM-4.6 has 29.