Model comparison
GLM-4.6V vs GPT-4.5
GLM-4.6V is the stronger model overall, scoring 41.3 to 37.2 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 27.6 to 13.9.
- 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 | 41.3 | 37.2 |
| 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: 40.9 (#128), GPT-4.5: 42.2 (#109)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1390 | 1396 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |
Agentic & Tool Use Not comparable
GLM-4.6V: —, GPT-4.5: 27.9 (#97)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |
Reasoning GLM-4.6V leads
GLM-4.6V: 27.6 (#115), GPT-4.5: 13.9 (#330)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1368 | 1403 |
| 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: 32.6 (#211)
| 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: 38.0 (#149), GPT-4.5: 32.5 (#211)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Expert | 1371 | 1394 |
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
Multimodal GPT-4.5 leads
GLM-4.6V: 34.8 (#90), GPT-4.5: 37.6 (#71)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1164 | 1195 |
| VPCT | — | 45% |
Multilingual GPT-4.5 leads
GLM-4.6V: 48.6 (#141), GPT-4.5: 52.5 (#83)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1359 | 1413 |
| LMArena Chinese | 1425 | 1421 |
| LMArena Russian | 1340 | 1419 |
| LMArena French | — | 1418 |
| LMArena German | — | 1457 |
| LMArena Japanese | — | 1416 |
| LMArena Korean | — | 1392 |
Instruction Following GPT-4.5 leads
GLM-4.6V: 71.4 (#151), GPT-4.5: 72.6 (#134)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1352 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
Long Context Too close to call
GLM-4.6V: 41.3 (#143), GPT-4.5: 40.4 (#155)
| 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: 56.6 (#137), GPT-4.5: 56.9 (#134)
| Benchmark | GLM-4.6V | GPT-4.5 |
|---|---|---|
| LMArena Text | 1377 | 1417 |
| LMArena Creative Writing | 1347 | 1394 |
| LMArena Multi-Turn | 1360 | 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 41.3 to 37.2 on the Noometry Index.
Is GLM-4.6V or GPT-4.5 better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 40.9 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.