Model comparison
GLM-4.5 vs GPT-5.5
GPT-5.5 is the stronger model overall, scoring 63.4 to 41.4 on the Noometry Index. GLM-4.5 costs 11× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Summary
- They share 21 benchmarks with published results for both. GLM-4.5 scores higher in 0 categories and GPT-5.5 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.5 leads 81.5 to 36.3.
- The biggest single-benchmark swing is WeirdML: 40.6% for GLM-4.5 and 84.9% for GPT-5.5.
- GLM-4.5 is cheaper at $0.60 / $2.20 per million input/output tokens, against $5 / $30 for GPT-5.5.
- GPT-5.5 accepts more context: 1.05M tokens versus 131K.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5 | GPT-5.5 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 63.4 |
| Released | 2025-07-27 | 2026-04-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 1.05M |
| Max output | 98K | 128K |
| Input $ / M tokens | $0.60 | $5 |
| Output $ / M tokens | $2.20 | $30 |
| Results tracked | 27 | 71 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.5 leads
GLM-4.5: 41.1 (#121), GPT-5.5: 58.3 (#13)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| WeirdML | 40.6% | 84.9% |
| LMArena Coding | 1434 | 1494 |
| ALE-Bench | 344.82 | 1,943 |
| SWE-bench Verified | — | 80.6% |
| DeepSWE | — | 67% |
| FrontierCode | — | 43% |
| SWE-bench Verified (bash only) | 54.2% | — |
| LMArena WebDev | — | 1512 |
| SciCode | — | 56.1% |
| GSO | — | 40.2% |
| MirrorCode | — | 10% |
| AlgoTune | 1.52 | — |
Agentic & Tool Use Not comparable
GLM-4.5: —, GPT-5.5: 50.7 (#6)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| Terminal-Bench | — | 84.7% |
| APEX-Agents | — | 55.1% |
| OSWorld 2.0 | — | 13% |
| Remote Labor Index | — | 6.3% |
| τ²-bench Banking | — | 44.6% |
| DeepResearch Bench | — | 54% |
| PostTrainBench | — | 27.2% |
| ExploitBench | — | 47.4% |
| GBAEval | — | 53.2% |
| GDP.pdf | — | 26% |
| LMArena Search | — | 1242 |
| Vending-Bench 2 | — | 7,524 |
Reasoning GPT-5.5 leads
GLM-4.5: 27.7 (#99), GPT-5.5: 72.7 (#8)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 88.8% |
| LMArena Hard Prompts | 1430 | 1489 |
| ARC-AGI-2 | — | 85% |
| SimpleBench | — | 69% |
| NYT Connections (extended) | — | 96.2% |
| ARC-AGI-1 | — | 95% |
| CritPt | — | 27.1% |
| Chess Puzzles | — | 54% |
| EBR-Bench | — | 34.3% |
| Mystery Game Puzzles | — | 56% |
| DTBench | — | 96% |
| LMCA | — | 54.3% |
| Surface Evolver Bench | — | 88.1% |
| Bench to the Future 3 | — | 0.14 |
| Epoch Capabilities Index | — | 159.25 |
| ForecastBench | — | 60.6 |
Math GPT-5.5 leads
GLM-4.5: 36.3 (#119), GPT-5.5: 81.5 (#9)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| LMArena Math | 1427 | 1486 |
| FrontierMath (Tiers 1-3) | — | 85.3% |
| FrontierMath Tier 4 | — | 72.5% |
| MathArena Final-Answer Competitions | — | 94.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 50% |
| FrontierMath (Feb 2025 set) | — | 51.7% |
| FrontierMath Erdős | — | 0% |
| FrontierMath Tier 4 (v1) | — | 35.4% |
Knowledge GPT-5.5 leads
GLM-4.5: 35.5 (#172), GPT-5.5: 64.4 (#14)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| LMArena Expert | 1433 | 1508 |
| GPQA Diamond | — | 94% |
| Humanity's Last Exam | 8.3% | — |
| SimpleQA Verified | — | 63% |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 9.3% |
Multimodal Not comparable
GLM-4.5: —, GPT-5.5: 47.1 (#11)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| LMArena Vision | — | 1297 |
| Blueprint-Bench 2 | — | 36.2% |
| Furniture Assembly | — | 44.2% |
| LMArena Document | — | 1486 |
Multilingual GPT-5.5 leads
GLM-4.5: 53.0 (#74), GPT-5.5: 56.5 (#19)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| LMArena Non-English | 1417 | 1467 |
| LMArena Chinese | 1465 | 1535 |
| LMArena French | 1423 | 1486 |
| LMArena German | 1406 | 1478 |
| LMArena Japanese | 1416 | 1498 |
| LMArena Korean | 1382 | 1461 |
| LMArena Russian | 1414 | 1473 |
| LMArena Spanish | 1454 | 1469 |
Instruction Following GPT-5.5 leads
GLM-4.5: 74.3 (#100), GPT-5.5: 77.7 (#18)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1479 |
Long Context GPT-5.5 leads
GLM-4.5: 38.2 (#196), GPT-5.5: 48.3 (#12)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| LMArena Longer Query | 1413 | 1484 |
| Fiction.LiveBench | 58.3% | — |
| CL-bench Life | — | 22.2% |
Writing & Preference GPT-5.5 leads
GLM-4.5: 57.7 (#121), GPT-5.5: 72.8 (#13)
| Benchmark | GLM-4.5 | GPT-5.5 |
|---|---|---|
| LMArena Text | 1430 | 1471 |
| LMArena Creative Writing | 1395 | 1455 |
| EQ-Bench Creative Writing | 1343 | 1844 |
| LMArena Multi-Turn | 1415 | 1477 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench 4 | — | 1315 |
Frequently asked questions
Is GLM-4.5 better than GPT-5.5?
GPT-5.5 is the stronger model overall, scoring 63.4 to 41.4 on the Noometry Index. GLM-4.5 costs 11× less per token, which makes it the better buy when GPT-5.5's lead doesn't matter for your workload.
Which is cheaper, GLM-4.5 or GPT-5.5?
GLM-4.5 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5.5 lists at $5 and $30.
Is GLM-4.5 or GPT-5.5 better for coding?
GPT-5.5 scores higher on coding benchmarks: 58.3 versus 41.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.5 does, with 1.05M tokens against 131K.
How many benchmarks do GLM-4.5 and GPT-5.5 share?
21 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and GPT-5.5 has 71.