Model comparison
GLM-4.7 vs GPT-5.4 Pro
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 41.7 on the Noometry Index. GLM-4.7 costs 68× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 9 shared benchmarks.
Summary
- They share 9 benchmarks with published results for both. GLM-4.7 scores higher in 1 category and GPT-5.4 Pro in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 71.0 to 23.7.
- The biggest single-benchmark swing is Chess Puzzles: 6% for GLM-4.7 and 58.6% for GPT-5.4 Pro.
- GLM-4.7 is cheaper at $0.60 / $2.20 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 205K.
- GLM-4.7 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.7 | GPT-5.4 Pro | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.7 | 58.8 |
| Released | 2025-12-22 | 2026-03-05 |
| Weights | Open | Proprietary |
| Context window | 205K | 1.05M |
| Max output | 131K | 128K |
| Input $ / M tokens | $0.60 | $30 |
| Output $ / M tokens | $2.20 | $180 |
| Results tracked | 36 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GLM-4.7: 43.6 (#74), GPT-5.4 Pro: 42.6 (#89)
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| LMArena WebDev | 1435 | — |
| SciCode | 45.1% | — |
| WeirdML | — | 57.4% |
| LMArena Coding | 1454 | — |
| ALE-Bench | 399.48 | — |
Agentic & Tool Use Not comparable
GLM-4.7: 26.4 (#96), GPT-5.4 Pro: —
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| Terminal-Bench | 33.4% | — |
| Vending-Bench 2 | 2,377 | — |
Reasoning GPT-5.4 Pro leads
GLM-4.7: 23.7 (#161), GPT-5.4 Pro: 71.0 (#10)
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| SimpleBench | 47.7% | 74.1% |
| CritPt | 1.7% | 30% |
| Chess Puzzles | 6% | 58.6% |
| Epoch Capabilities Index | 143.53 | 159.12 |
| ARC-AGI-2 | — | 83.3% |
| ARC-AGI-1 | — | 94.5% |
| EnigmaEval | — | 23.8% |
| LMArena Hard Prompts | 1443 | — |
Math GPT-5.4 Pro leads
GLM-4.7: 37.7 (#92), GPT-5.4 Pro: 72.0 (#17)
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Feb 2025 set) | 2.4% | 50% |
| FrontierMath Tier 4 (v1) | 0% | 37.5% |
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| OTIS Mock AIME 2024-2025 | 83.3% | — |
| ProofBench | 6% | — |
| LMArena Math | 1423 | — |
Knowledge GPT-5.4 Pro leads
GLM-4.7: 47.0 (#74), GPT-5.4 Pro: 68.3 (#6)
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | 83.3% | 94.6% |
| SimpleQA Verified | 32.2% | 46.3% |
| Vectara Hallucination Rate | 11.7% | 8.3% |
| Humanity's Last Exam | — | 44.3% |
| LMArena Expert | 1424 | — |
Multilingual Not comparable
GLM-4.7: 53.0 (#75), GPT-5.4 Pro: —
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 1417 | — |
| LMArena Chinese | 1495 | — |
| LMArena French | 1432 | — |
| LMArena German | 1426 | — |
| LMArena Japanese | 1439 | — |
| LMArena Korean | 1401 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1433 | — |
Instruction Following Not comparable
GLM-4.7: 74.6 (#90), GPT-5.4 Pro: —
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1411 | — |
Long Context Not comparable
GLM-4.7: 42.8 (#111), GPT-5.4 Pro: —
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| CL-bench | 15.9% | — |
| CL-bench Life | 10.9% | — |
| LMArena Longer Query | 1432 | — |
Writing & Preference Not comparable
GLM-4.7: 61.1 (#89), GPT-5.4 Pro: —
| Benchmark | GLM-4.7 | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1436 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1413 | — |
| LMArena Multi-Turn | 1446 | — |
Frequently asked questions
Is GLM-4.7 better than GPT-5.4 Pro?
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 41.7 on the Noometry Index. GLM-4.7 costs 68× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, GLM-4.7 or GPT-5.4 Pro?
GLM-4.7 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is GLM-4.7 or GPT-5.4 Pro better for coding?
They score almost the same on coding (43.6 vs 42.6); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 205K.
How many benchmarks do GLM-4.7 and GPT-5.4 Pro share?
9 benchmarks have published results for both models. GLM-4.7 has 36 scored results on Noometry and GPT-5.4 Pro has 16.