Model comparison
GLM-5 vs GPT-5.4 nano
GLM-5 is the stronger model overall, scoring 46.1 to 41.9 on the Noometry Index. GPT-5.4 nano costs 3.4× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. GLM-5 scores higher in 8 categories and GPT-5.4 nano in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GLM-5 leads 52.3 to 41.9.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for GLM-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 $1 / $3.20 for GLM-5.
- GPT-5.4 nano accepts more context: 400K tokens versus 205K.
- GLM-5 has downloadable open weights; the other is API-only.
Side by side
| GLM-5 | GPT-5.4 nano | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 46.1 | 41.9 |
| Released | 2026-02-11 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 205K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $1 | $0.20 |
| Output $ / M tokens | $3.20 | $1.25 |
| Results tracked | 45 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5 leads
GLM-5: 49.0 (#52), GPT-5.4 nano: 43.6 (#84)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| WeirdML | 48.2% | 49.2% |
| LMArena Coding | 1461 | 1405 |
| ALE-Bench | 765.62 | 1,005 |
| SWE-bench Verified | 72.1% | — |
| SWE-bench Verified (bash only) | 72.8% | — |
| LMArena WebDev | 1434 | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 46.9% |
Agentic & Tool Use Not comparable
GLM-5: 31.1 (#71), GPT-5.4 nano: —
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| Terminal-Bench | 52.4% | — |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| Vending-Bench 2 | 4,432 | — |
Reasoning GLM-5 leads
GLM-5: 27.6 (#116), GPT-5.4 nano: 23.7 (#173)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| ARC-AGI-2 | 4.9% | 5.7% |
| Kagi LLM Benchmark | 75% | 39.7% |
| ARC-AGI-1 | 44.7% | 51.5% |
| Chess Puzzles | 10% | 30% |
| LMArena Hard Prompts | 1452 | 1381 |
| Epoch Capabilities Index | 145.83 | 145.81 |
| ForecastBench | 61 | 57.3 |
| SimpleBench | 53.2% | — |
| NYT Connections (extended) | 74.8% | — |
| CritPt | — | 9.3% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 36.9% |
Math GLM-5 leads
GLM-5: 46.4 (#71), GPT-5.4 nano: 40.9 (#88)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 80% | 87.8% |
| LMArena Math | 1440 | 1406 |
| FrontierMath (Feb 2025 set) | 16.4% | 25.9% |
| FrontierMath Tier 4 (v1) | 2.1% | 6.3% |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| MathArena Final-Answer Competitions | 65.7% | — |
| ProofBench | — | 5% |
Knowledge GLM-5 leads
GLM-5: 52.3 (#64), GPT-5.4 nano: 41.9 (#103)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| GPQA Diamond | 87.8% | 78.5% |
| Vectara Hallucination Rate | 10.1% | 3.1% |
| LMArena Expert | 1454 | 1396 |
| SimpleQA Verified | — | 11.7% |
Multimodal Not comparable
GLM-5: —, GPT-5.4 nano: 36.7 (#78)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | — | 1196 |
Multilingual GLM-5 leads
GLM-5: 53.7 (#58), GPT-5.4 nano: 48.6 (#140)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1430 | 1359 |
| LMArena Chinese | 1511 | 1392 |
| LMArena French | 1455 | 1396 |
| LMArena German | 1445 | 1367 |
| LMArena Japanese | 1416 | 1343 |
| LMArena Korean | 1423 | 1320 |
| LMArena Russian | 1436 | 1363 |
| LMArena Spanish | 1454 | 1371 |
Instruction Following GLM-5 leads
GLM-5: 75.2 (#67), GPT-5.4 nano: 71.9 (#144)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1428 | 1362 |
Long Context GLM-5 leads
GLM-5: 44.7 (#60), GPT-5.4 nano: 41.6 (#137)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1446 | 1366 |
| CL-bench | 18.7% | — |
Writing & Preference GLM-5 leads
GLM-5: 66.0 (#38), GPT-5.4 nano: 55.7 (#142)
| Benchmark | GLM-5 | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1446 | 1372 |
| LMArena Creative Writing | 1439 | 1314 |
| LMArena Multi-Turn | 1456 | 1382 |
| EQ-Bench Creative Writing | 1601 | — |
Frequently asked questions
Is GLM-5 better than GPT-5.4 nano?
GLM-5 is the stronger model overall, scoring 46.1 to 41.9 on the Noometry Index. GPT-5.4 nano costs 3.4× less per token, which makes it the better buy when GLM-5's lead doesn't matter for your workload.
Which is cheaper, GLM-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-5 lists at $1 and $3.20.
Is GLM-5 or GPT-5.4 nano better for coding?
GLM-5 scores higher on coding benchmarks: 49.0 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 205K.
How many benchmarks do GLM-5 and GPT-5.4 nano share?
30 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and GPT-5.4 nano has 40.