Model comparison
GLM-4.6 vs GPT-4.5
GLM-4.6 is the stronger model overall, scoring 41.4 to 37.2 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and GPT-4.5 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6 leads 23.7 to 13.9.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | GPT-4.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 37.2 |
| Released | 2025-09-30 | 2025-02-27 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.20 | — |
| Results tracked | 29 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4.5 leads
GLM-4.6: 40.1 (#148), GPT-4.5: 42.2 (#109)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1449 | 1396 |
| SWE-bench Verified (bash only) | 55.4% | — |
| Aider Polyglot | — | 44.9% |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |
| ALE-Bench | 340.82 | — |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), GPT-4.5: 27.9 (#97)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| Cybench | — | 17.5% |
Reasoning GLM-4.6 leads
GLM-4.6: 23.7 (#172), GPT-4.5: 13.9 (#330)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1440 | 1403 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| Kagi LLM Benchmark | 47.4% | — |
| ARC-AGI-1 | — | 10.3% |
| CritPt | 1.1% | — |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| Epoch Capabilities Index | — | 136.74 |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |
Math GLM-4.6 leads
GLM-4.6: 39.1 (#111), GPT-4.5: 32.6 (#211)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Math | 1432 | 1412 |
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-4.6 leads
GLM-4.6: 40.2 (#124), GPT-4.5: 32.5 (#211)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Expert | 1431 | 1394 |
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |
| Confabulations | — | 13.6% |
| Vectara Hallucination Rate | 9.5% | — |
Multimodal Not comparable
GLM-4.6: —, GPT-4.5: 37.6 (#71)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Vision | — | 1195 |
| VPCT | — | 45% |
Multilingual Too close to call
GLM-4.6: 53.5 (#66), GPT-4.5: 52.5 (#83)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1426 | 1413 |
| LMArena Chinese | 1499 | 1421 |
| LMArena French | 1459 | 1418 |
| LMArena German | 1447 | 1457 |
| LMArena Japanese | 1393 | 1416 |
| LMArena Korean | 1400 | 1392 |
| LMArena Russian | 1419 | 1419 |
| LMArena Spanish | 1436 | — |
Instruction Following GLM-4.6 leads
GLM-4.6: 74.3 (#98), GPT-4.5: 72.6 (#134)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1404 |
| LiveBench Instruction Following | — | 72.3% |
Long Context GLM-4.6 leads
GLM-4.6: 43.4 (#94), GPT-4.5: 40.4 (#155)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1422 | 1406 |
| Fiction.LiveBench | — | 63.9% |
Writing & Preference GLM-4.6 leads
GLM-4.6: 61.1 (#90), GPT-4.5: 56.9 (#134)
| Benchmark | GLM-4.6 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1440 | 1417 |
| LMArena Creative Writing | 1411 | 1394 |
| EQ-Bench Creative Writing | 1411 | 1258 |
| LMArena Multi-Turn | 1427 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| LiveBench Language | — | 61.5% |
Frequently asked questions
Is GLM-4.6 better than GPT-4.5?
GLM-4.6 is the stronger model overall, scoring 41.4 to 37.2 on the Noometry Index.
Is GLM-4.6 or GPT-4.5 better for coding?
GPT-4.5 scores higher on coding benchmarks: 42.2 versus 40.1 in the Noometry coding category.
How many benchmarks do GLM-4.6 and GPT-4.5 share?
17 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-4.5 has 42.