Model comparison
GLM-4.5 vs GPT-5.4 nano
GLM-4.5 and GPT-5.4 nano score almost the same on the Noometry Index (41.4 vs 41.9), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. GLM-4.5 scores higher in 4 categories and GPT-5.4 nano in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 nano leads 41.8 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.9% for GLM-4.5 and 39.7% for GPT-5.4 nano.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- GPT-5.4 nano accepts more context: 400K tokens versus 131K.
- GLM-4.5 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.5 | GPT-5.4 nano | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 41.9 |
| Released | 2025-07-27 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 131K | 400K |
| Max output | 98K | 128K |
| Input $ / M tokens | $0.60 | $0.20 |
| Output $ / M tokens | $2.20 | $1.25 |
| Results tracked | 27 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GLM-4.5: 41.1 (#121), GPT-5.4 nano: 43.1 (#82)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| WeirdML | 40.6% | 49.2% |
| LMArena Coding | 1434 | 1404 |
| ALE-Bench | 344.82 | 1,005 |
| SWE-bench Verified (bash only) | 54.2% | — |
| SciCode | — | 46.9% |
| AlgoTune | 1.52 | — |
Reasoning GLM-4.5 leads
GLM-4.5: 27.7 (#99), GPT-5.4 nano: 23.8 (#159)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| Kagi LLM Benchmark | 57.9% | 39.7% |
| LMArena Hard Prompts | 1430 | 1380 |
| ARC-AGI-2 | — | 5.7% |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 145.78 |
| ForecastBench | — | 57.3 |
Math GPT-5.4 nano leads
GLM-4.5: 36.3 (#119), GPT-5.4 nano: 40.7 (#76)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| LMArena Math | 1427 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 5% |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5.4 nano leads
GLM-4.5: 35.5 (#172), GPT-5.4 nano: 41.8 (#94)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| LMArena Expert | 1433 | 1397 |
| GPQA Diamond | — | 78.5% |
| Humanity's Last Exam | 8.3% | — |
| SimpleQA Verified | — | 11.7% |
| Confabulations | 11.3% | — |
| Vectara Hallucination Rate | — | 3.1% |
Multimodal Not comparable
GLM-4.5: —, GPT-5.4 nano: 36.0 (#73)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | — | 1196 |
Multilingual GLM-4.5 leads
GLM-4.5: 53.0 (#74), GPT-5.4 nano: 48.8 (#136)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1417 | 1359 |
| LMArena Chinese | 1465 | 1391 |
| LMArena French | 1423 | 1396 |
| LMArena German | 1406 | 1368 |
| LMArena Japanese | 1416 | 1342 |
| LMArena Korean | 1382 | 1321 |
| LMArena Russian | 1414 | 1363 |
| LMArena Spanish | 1454 | 1368 |
Instruction Following GLM-4.5 leads
GLM-4.5: 74.3 (#100), GPT-5.4 nano: 72.1 (#139)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1405 | 1362 |
Long Context GPT-5.4 nano leads
GLM-4.5: 38.2 (#196), GPT-5.4 nano: 41.6 (#131)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1413 | 1365 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference GLM-4.5 leads
GLM-4.5: 57.7 (#121), GPT-5.4 nano: 55.9 (#137)
| Benchmark | GLM-4.5 | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1430 | 1372 |
| LMArena Creative Writing | 1395 | 1313 |
| LMArena Multi-Turn | 1415 | 1382 |
| Short-Story Creative Writing | 73.4% | — |
| EQ-Bench Creative Writing | 1343 | — |
Frequently asked questions
Is GLM-4.5 better than GPT-5.4 nano?
GLM-4.5 and GPT-5.4 nano score almost the same on the Noometry Index (41.4 vs 41.9), so choose on price, context window or the category you care about most.
Which is cheaper, GLM-4.5 or GPT-5.4 nano?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.
Is GLM-4.5 or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 41.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 131K.
How many benchmarks do GLM-4.5 and GPT-5.4 nano share?
20 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and GPT-5.4 nano has 40.