Model comparison
GLM-4.5V vs GLM-4.6
GLM-4.6 is the stronger model overall, scoring 41.4 to 39.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
Summary
- They share 14 benchmarks with published results for both. GLM-4.5V scores higher in 1 category and GLM-4.6 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GLM-4.6 leads 53.5 to 44.6.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 59.8% for GLM-4.5V and 47.4% for GLM-4.6.
- GLM-4.5V is cheaper at $0.60 / $1.80 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- GLM-4.6 accepts more context: 205K tokens versus 64K.
Side by side
| GLM-4.5V | GLM-4.6 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 39.8 | 41.4 |
| Released | 2025-08-11 | 2025-09-30 |
| Weights | Open | Open |
| Context window | 64K | 205K |
| Max output | 16K | 131K |
| Input $ / M tokens | $0.60 | $0.60 |
| Output $ / M tokens | $1.80 | $2.20 |
| Results tracked | 15 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.5V: 39.5 (#155), GLM-4.6: 40.1 (#148)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Coding | 1347 | 1449 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1340 |
| SciCode | — | 38.4% |
| ALE-Bench | — | 340.82 |
Agentic & Tool Use Not comparable
GLM-4.5V: —, GLM-4.6: 32.3 (#66)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| Terminal-Bench | — | 24.5% |
| Berkeley Function Calling Leaderboard | — | 72.4% |
Reasoning GLM-4.5V leads
GLM-4.5V: 27.4 (#119), GLM-4.6: 23.7 (#172)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| Kagi LLM Benchmark | 59.8% | 47.4% |
| LMArena Hard Prompts | 1334 | 1440 |
| CritPt | — | 1.1% |
Math GLM-4.6 leads
GLM-4.5V: 37.4 (#159), GLM-4.6: 39.1 (#111)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Math | 1354 | 1432 |
| FrontierMath (Feb 2025 set) | — | 3.8% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge GLM-4.6 leads
GLM-4.5V: 37.5 (#156), GLM-4.6: 40.2 (#124)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Expert | 1353 | 1431 |
| Vectara Hallucination Rate | — | 9.5% |
Multimodal Not comparable
GLM-4.5V: 34.3 (#92), GLM-4.6: —
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Vision | 1154 | — |
Multilingual GLM-4.6 leads
GLM-4.5V: 44.6 (#177), GLM-4.6: 53.5 (#66)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Non-English | 1303 | 1426 |
| LMArena Chinese | 1337 | 1499 |
| LMArena Russian | 1298 | 1419 |
| LMArena Spanish | 1336 | 1436 |
| LMArena French | — | 1459 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1393 |
| LMArena Korean | — | 1400 |
Instruction Following GLM-4.6 leads
GLM-4.5V: 69.2 (#175), GLM-4.6: 74.3 (#98)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Instruction Following | 1311 | 1410 |
Long Context GLM-4.6 leads
GLM-4.5V: 39.6 (#171), GLM-4.6: 43.4 (#94)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Longer Query | 1304 | 1422 |
Writing & Preference GLM-4.6 leads
GLM-4.5V: 52.5 (#170), GLM-4.6: 61.1 (#90)
| Benchmark | GLM-4.5V | GLM-4.6 |
|---|---|---|
| LMArena Text | 1333 | 1440 |
| LMArena Creative Writing | 1295 | 1411 |
| LMArena Multi-Turn | 1332 | 1427 |
| EQ-Bench Creative Writing | — | 1411 |
Frequently asked questions
Is GLM-4.5V better than GLM-4.6?
GLM-4.6 is the stronger model overall, scoring 41.4 to 39.8 on the Noometry Index.
Which is cheaper, GLM-4.5V or GLM-4.6?
GLM-4.5V is cheaper. It lists at $0.60 per million input tokens and $1.80 per million output tokens; GLM-4.6 lists at $0.60 and $2.20.
Is GLM-4.5V or GLM-4.6 better for coding?
They score almost the same on coding (39.5 vs 40.1); test both on your own repository before choosing.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 64K.
How many benchmarks do GLM-4.5V and GLM-4.6 share?
14 benchmarks have published results for both models. GLM-4.5V has 15 scored results on Noometry and GLM-4.6 has 29.