Model comparison
GLM-4.7 vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 42.0 on the Noometry Index. GLM-4.7 costs 1.7× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GLM-4.7 scores higher in 2 categories and GPT-5.4 mini in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 38.6.
- The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 24% for GPT-5.4 mini.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | GPT-5.4 mini | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 42.0 | 45.0 |
| Released | 2025-12-22 | 2026-03-17 |
| Weights | Open | Proprietary |
| Context window | 205K | 400K |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.60 | $0.75 |
| Output $ / M tokens | $2.20 | $4.50 |
| Results tracked | 36 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GLM-4.7: 44.0 (#79), GPT-5.4 mini: 45.2 (#72)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| LMArena WebDev | 1435 | 1397 |
| SciCode | 45.1% | 49.9% |
| LMArena Coding | 1454 | 1438 |
| ALE-Bench | 399.48 | 1,189 |
| FrontierCode | — | 27% |
| WeirdML | — | 60.3% |
Agentic & Tool Use GPT-5.4 mini leads
GLM-4.7: 26.5 (#103), GPT-5.4 mini: 29.9 (#81)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| DeepResearch Bench | — | 36.3% |
| Vending-Bench 2 | 2,377 | — |
Reasoning GPT-5.4 mini leads
GLM-4.7: 24.3 (#164), GPT-5.4 mini: 30.4 (#85)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| CritPt | 1.7% | 10% |
| Chess Puzzles | 6% | 24% |
| LMArena Hard Prompts | 1443 | 1424 |
| Epoch Capabilities Index | 143.51 | 148.84 |
| ARC-AGI-2 | — | 18.9% |
| SimpleBench | 47.7% | — |
| Kagi LLM Benchmark | — | 37.9% |
| NYT Connections (extended) | — | 61.8% |
| ARC-AGI-1 | — | 63.7% |
| Thematic Generalization | — | 61.7% |
| Mystery Game Puzzles | — | 11% |
| DTBench | — | 80% |
| LMCA | — | 40.8% |
| ForecastBench | — | 57 |
Math GPT-5.4 mini leads
GLM-4.7: 38.6 (#135), GPT-5.4 mini: 45.5 (#75)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 83.3% | 88.9% |
| ProofBench | 6% | 21% |
| LMArena Math | 1423 | 1419 |
| FrontierMath (Feb 2025 set) | 2.4% | 28.3% |
| FrontierMath Tier 4 (v1) | 0% | 2.1% |
| FrontierMath (Tiers 1-3) | — | 51.2% |
| FrontierMath Tier 4 | — | 9.8% |
Knowledge GPT-5.4 mini leads
GLM-4.7: 47.0 (#80), GPT-5.4 mini: 51.5 (#67)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 83.3% | 86.9% |
| SimpleQA Verified | 32.2% | 29.4% |
| Vectara Hallucination Rate | 11.7% | 5.5% |
| LMArena Expert | 1424 | 1435 |
Multimodal Not comparable
GLM-4.7: —, GPT-5.4 mini: 39.7 (#56)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual Too close to call
GLM-4.7: 52.8 (#79), GPT-5.4 mini: 51.9 (#96)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1417 | 1405 |
| LMArena Chinese | 1495 | 1446 |
| LMArena French | 1432 | 1440 |
| LMArena German | 1424 | 1409 |
| LMArena Japanese | 1439 | 1374 |
| LMArena Korean | 1399 | 1368 |
| LMArena Russian | 1423 | 1417 |
| LMArena Spanish | 1434 | 1405 |
Instruction Following Too close to call
GLM-4.7: 74.4 (#95), GPT-5.4 mini: 74.1 (#102)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1411 | 1405 |
Long Context Too close to call
GLM-4.7: 42.8 (#116), GPT-5.4 mini: 43.0 (#112)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1432 | 1407 |
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
Writing & Preference GPT-5.4 mini leads
GLM-4.7: 60.9 (#93), GPT-5.4 mini: 64.0 (#58)
| Benchmark | GLM-4.7 | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1435 | 1412 |
| LMArena Creative Writing | 1401 | 1370 |
| EQ-Bench Creative Writing | 1413 | 1665 |
| LMArena Multi-Turn | 1446 | 1429 |
Frequently asked questions
Is GLM-4.7 better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 42.0 on the Noometry Index. GLM-4.7 costs 1.7× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7 or GPT-5.4 mini?
GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GLM-4.7 or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 44.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 205K.
How many benchmarks do GLM-4.7 and GPT-5.4 mini share?
31 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and GPT-5.4 mini has 46.