Model comparison
GLM-4.6V vs GPT-4.5
GLM-4.6V is the stronger model overall, scoring 40.9 to 36.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. GLM-4.6V scores higher in 3 categories and GPT-4.5 in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6V leads 26.5 to 14.1.
- GLM-4.6V has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6V | GPT-4.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 40.9 | 36.9 |
| Released | 2025-12-08 | 2025-02-27 |
| Weights | Open | Proprietary |
| Context window | 128K | — |
| Max output | 33K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $0.90 | — |
| Results tracked | 12 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GLM-4.6V: 40.2 (#128), GPT-4.5: 41.8 (#102)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1390 | 1397 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |
Agentic & Tool Use Not comparable
GLM-4.6V: —, GPT-4.5: 27.6 (#92)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |
Reasoning GLM-4.6V leads
GLM-4.6V: 26.5 (#117), GPT-4.5: 14.1 (#320)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1404 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| Epoch Capabilities Index | — | 136.74 |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |
Math Not comparable
GLM-4.6V: —, GPT-4.5: 31.0 (#200)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| LiveBench Math | — | 69.3% |
| LMArena Math | — | 1412 |
| MATH Level 5 | — | 78.6% |
Knowledge GLM-4.6V leads
GLM-4.6V: 37.4 (#148), GPT-4.5: 32.4 (#205)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Expert | 1372 | 1394 |
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
Multimodal GPT-4.5 leads
GLM-4.6V: 34.2 (#83), GPT-4.5: 37.0 (#68)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1164 | 1195 |
| VPCT | — | 45% |
Multilingual GPT-4.5 leads
GLM-4.6V: 48.8 (#135), GPT-4.5: 52.7 (#78)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1359 | 1413 |
| LMArena Chinese | 1426 | 1421 |
| LMArena Russian | 1341 | 1419 |
| LMArena French | — | 1417 |
| LMArena German | — | 1457 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1392 |
Instruction Following GPT-4.5 leads
GLM-4.6V: 71.6 (#145), GPT-4.5: 72.8 (#129)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1351 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
Long Context Too close to call
GLM-4.6V: 41.3 (#138), GPT-4.5: 40.4 (#150)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1358 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference Too close to call
GLM-4.6V: 56.8 (#132), GPT-4.5: 57.1 (#129)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Text | 1377 | 1417 |
| LMArena Creative Writing | 1347 | 1394 |
| LMArena Multi-Turn | 1359 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| EQ-Bench Creative Writing | — | 1258 |
| LiveBench Language | — | 61.5% |
Frequently asked questions
Is GLM-4.6V better than GPT-4.5?
GLM-4.6V is the stronger model overall, scoring 40.9 to 36.9 on the Noometry Index.
Is GLM-4.6V or GPT-4.5 better for coding?
GPT-4.5 scores higher on coding benchmarks: 41.8 versus 40.2 in the Noometry coding category.
How many benchmarks do GLM-4.6V and GPT-4.5 share?
12 benchmarks have published results for both models. GLM-4.6V has 12 scored results on Noometry and GPT-4.5 has 42.