Model comparison
GLM-4.7 vs GLM-5V-Turbo
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 41.7 on the Noometry Index. GLM-4.7 costs 1.9× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GLM-4.7 scores higher in 3 categories and GLM-5V-Turbo in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-4.7 leads 47.0 to 39.9.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.20 / $4 for GLM-5V-Turbo.
- GLM-4.7 accepts more context: 205K tokens versus 200K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | GLM-5V-Turbo | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 41.7 | 43.1 |
| Released | 2025-12-22 | 2026-04-01 |
| Weights | Open | Proprietary |
| Context window | 205K | 200K |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.60 | $1.20 |
| Output $ / M tokens | $2.20 | $4 |
| Results tracked | 36 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-4.7 leads
GLM-4.7: 43.6 (#74), GLM-5V-Turbo: 41.8 (#105)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena WebDev | 1435 | 1400 |
| LMArena Coding | 1454 | 1467 |
| SciCode | 45.1% | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.4 (#96), GLM-5V-Turbo: —
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning GLM-5V-Turbo leads
GLM-4.7: 23.7 (#161), GLM-5V-Turbo: 28.5 (#87)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Hard Prompts | 1443 | 1443 |
| SimpleBench | 47.7% | — |
| CritPt | 1.7% | — |
| Chess Puzzles | 6% | — |
| Epoch Capabilities Index | 143.53 | — |
Math GLM-4.7 leads
GLM-4.7: 37.7 (#92), GLM-5V-Turbo: 36.6 (#109)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Math | 1423 | 1440 |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| FrontierMath (Feb 2025 set) | 2.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge GLM-4.7 leads
GLM-4.7: 47.0 (#74), GLM-5V-Turbo: 39.9 (#113)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Expert | 1424 | 1451 |
| GPQA Diamond | 83.3% | — |
| SimpleQA Verified | 32.2% | — |
| Vectara Hallucination Rate | 11.7% | — |
Multimodal Not comparable
GLM-4.7: —, GLM-5V-Turbo: 40.1 (#41)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Vision | — | 1264 |
| LMArena Document | — | 1416 |
Multilingual Too close to call
GLM-4.7: 53.0 (#75), GLM-5V-Turbo: 53.2 (#69)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Non-English | 1417 | 1420 |
| LMArena Chinese | 1495 | 1488 |
| LMArena French | 1432 | 1443 |
| LMArena German | 1426 | 1422 |
| LMArena Korean | 1401 | 1399 |
| LMArena Russian | 1423 | 1432 |
| LMArena Spanish | 1433 | 1446 |
| LMArena Japanese | 1439 | — |
Instruction Following Too close to call
GLM-4.7: 74.6 (#90), GLM-5V-Turbo: 75.1 (#75)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Instruction Following | 1411 | 1422 |
Long Context GLM-5V-Turbo leads
GLM-4.7: 42.8 (#111), GLM-5V-Turbo: 44.0 (#76)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Longer Query | 1432 | 1439 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GLM-5V-Turbo leads
GLM-4.7: 61.1 (#89), GLM-5V-Turbo: 62.6 (#69)
| Benchmark | GLM-4.7 | GLM-5V-Turbo |
|---|---|---|
| LMArena Text | 1436 | 1437 |
| LMArena Creative Writing | 1401 | 1414 |
| LMArena Multi-Turn | 1446 | 1432 |
| EQ-Bench Creative Writing | 1413 | — |
Frequently asked questions
Is GLM-4.7 better than GLM-5V-Turbo?
GLM-5V-Turbo is the stronger model overall, scoring 43.1 to 41.7 on the Noometry Index. GLM-4.7 costs 1.9× less per token, which makes it the better buy when GLM-5V-Turbo's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7 or GLM-5V-Turbo?
GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GLM-5V-Turbo lists at $1.20 and $4.
Is GLM-4.7 or GLM-5V-Turbo better for coding?
GLM-4.7 scores higher on coding benchmarks: 43.6 versus 41.8 in the Noometry coding category.
Which has the bigger context window?
GLM-4.7 does, with 205K tokens against 200K.
How many benchmarks do GLM-4.7 and GLM-5V-Turbo share?
17 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and GLM-5V-Turbo has 19.