Model comparison
C4ai Aya Expanse 8b vs GLM-5
GLM-5 is the stronger model overall, scoring 45.9 to 34.3 on the Noometry Index.
Last verified . 15 shared benchmarks.
CohereSummary
- They share 15 benchmarks with published results for both. C4ai Aya Expanse 8b scores higher in 0 categories and GLM-5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-5 leads 66.2 to 39.2.
- GLM-5 accepts more context: 205K tokens versus 8K.
Side by side
| C4ai Aya Expanse 8b | GLM-5 | |
|---|---|---|
| Provider | Cohere | Z.ai (Zhipu) |
| Noometry Index | 34.3 | 45.9 |
| Released | 2024-10-24 | 2026-02-11 |
| Weights | Open | Open |
| Context window | 8K | 205K |
| Max output | 4K | 131K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $3.20 |
| Results tracked | 15 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
C4ai Aya Expanse 8b: 33.2 (#252), GLM-5: 49.0 (#47)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| LMArena Coding | 1161 | 1461 |
| SWE-bench Verified | — | 72.1% |
| SWE-bench Verified (bash only) | — | 72.8% |
| LMArena WebDev | — | 1434 |
| SWE-bench Multilingual | — | 69.7% |
| WeirdML | — | 48.2% |
| ALE-Bench | — | 765.62 |
Agentic & Tool Use Not comparable
C4ai Aya Expanse 8b: —, GLM-5: 30.9 (#65)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| Terminal-Bench | — | 52.4% |
| τ²-bench Airline | — | 82.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 73.7% |
| τ²-bench Telecom | — | 86.8% |
| Vending-Bench 2 | — | 4,432 |
Reasoning GLM-5 leads
C4ai Aya Expanse 8b: 21.4 (#198), GLM-5: 27.6 (#100)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| LMArena Hard Prompts | 1156 | 1451 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | — | 53.2% |
| Kagi LLM Benchmark | — | 75% |
| NYT Connections (extended) | — | 74.8% |
| ARC-AGI-1 | — | 44.7% |
| Chess Puzzles | — | 10% |
| Epoch Capabilities Index | — | 145.84 |
| ForecastBench | — | 61 |
Math GLM-5 leads
C4ai Aya Expanse 8b: 30.8 (#204), GLM-5: 44.8 (#66)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| LMArena Math | 1168 | 1440 |
| MathArena Final-Answer Competitions | — | 65.7% |
| OTIS Mock AIME 2024-2025 | — | 80% |
| FrontierMath (Feb 2025 set) | — | 16.4% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-5 leads
C4ai Aya Expanse 8b: 33.0 (#197), GLM-5: 52.2 (#59)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 10.1% |
| LMArena Expert | 1153 | 1454 |
| GPQA Diamond | — | 87.8% |
Multilingual GLM-5 leads
C4ai Aya Expanse 8b: 36.3 (#237), GLM-5: 53.9 (#57)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| LMArena Non-English | 1180 | 1430 |
| LMArena Chinese | 1181 | 1511 |
| LMArena German | 1188 | 1445 |
| LMArena Japanese | 1120 | 1416 |
| LMArena Russian | 1197 | 1436 |
| LMArena French | — | 1455 |
| LMArena Korean | — | 1421 |
| LMArena Spanish | — | 1452 |
Instruction Following GLM-5 leads
C4ai Aya Expanse 8b: 60.4 (#248), GLM-5: 75.4 (#64)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| LMArena Instruction Following | 1155 | 1427 |
Long Context GLM-5 leads
C4ai Aya Expanse 8b: 36.1 (#231), GLM-5: 44.6 (#58)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| LMArena Longer Query | 1192 | 1446 |
| CL-bench | — | 18.7% |
Writing & Preference GLM-5 leads
C4ai Aya Expanse 8b: 39.2 (#245), GLM-5: 66.2 (#38)
| Benchmark | C4ai Aya Expanse 8b | GLM-5 |
|---|---|---|
| LMArena Text | 1185 | 1446 |
| LMArena Creative Writing | 1168 | 1438 |
| LMArena Multi-Turn | 1160 | 1456 |
| EQ-Bench Creative Writing | — | 1601 |
Frequently asked questions
Is C4ai Aya Expanse 8b better than GLM-5?
GLM-5 is the stronger model overall, scoring 45.9 to 34.3 on the Noometry Index.
Is C4ai Aya Expanse 8b or GLM-5 better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
GLM-5 does, with 205K tokens against 8K.
How many benchmarks do C4ai Aya Expanse 8b and GLM-5 share?
15 benchmarks have published results for both models. C4ai Aya Expanse 8b has 15 scored results on Noometry and GLM-5 has 45.