Model comparison
GLM-4.6 vs GPT-5 Pro
GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.4 on the Noometry Index. GLM-4.6 costs 41× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GLM-4.6 scores higher in 0 categories and GPT-5 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5 Pro leads 56.7 to 40.2.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 47.4% for GLM-4.6 and 76.8% for GPT-5 Pro.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 205K.
- GLM-4.6 has downloadable open weights; the other is API-only.
Side by side
| GLM-4.6 | GPT-5 Pro | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 41.4 | 46.4 |
| Released | 2025-09-30 | 2025-10-06 |
| Weights | Open | Proprietary |
| Context window | 205K | 400K |
| Max output | 131K | 272K |
| Input $ / M tokens | $0.60 | $15 |
| Output $ / M tokens | $2.20 | $120 |
| Results tracked | 29 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GLM-4.6: 40.1 (#148), GPT-5 Pro: 44.0 (#80)
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| SWE-bench Verified (bash only) | 55.4% | — |
| LMArena WebDev | 1340 | — |
| SciCode | 38.4% | — |
| WeirdML | — | 60.4% |
| LMArena Coding | 1449 | — |
| ALE-Bench | 340.82 | — |
| AlgoTune | — | 1.31 |
Agentic & Tool Use Not comparable
GLM-4.6: 32.3 (#66), GPT-5 Pro: —
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
Reasoning GPT-5 Pro leads
GLM-4.6: 23.7 (#172), GPT-5 Pro: 38.9 (#62)
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 76.8% |
| ARC-AGI-2 | — | 18.3% |
| SimpleBench | — | 61.6% |
| ARC-AGI-1 | — | 70.2% |
| CritPt | 1.1% | — |
| EnigmaEval | — | 18.8% |
| LMArena Hard Prompts | 1440 | — |
| Epoch Capabilities Index | — | 150.28 |
Math GPT-5 Pro leads
GLM-4.6: 39.1 (#111), GPT-5 Pro: 48.5 (#63)
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| FrontierMath Tier 4 (v1) | 2.1% | 14.6% |
| FrontierMath (Tiers 1-3) | — | 55.8% |
| FrontierMath Tier 4 | — | 19.5% |
| LMArena Math | 1432 | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
Knowledge GPT-5 Pro leads
GLM-4.6: 40.2 (#124), GPT-5 Pro: 56.7 (#42)
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| Humanity's Last Exam | — | 31.6% |
| Vectara Hallucination Rate | 9.5% | — |
| LMArena Expert | 1431 | — |
Multilingual Not comparable
GLM-4.6: 53.5 (#66), GPT-5 Pro: —
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1426 | — |
| LMArena Chinese | 1499 | — |
| LMArena French | 1459 | — |
| LMArena German | 1447 | — |
| LMArena Japanese | 1393 | — |
| LMArena Korean | 1400 | — |
| LMArena Russian | 1419 | — |
| LMArena Spanish | 1436 | — |
Instruction Following Not comparable
GLM-4.6: 74.3 (#98), GPT-5 Pro: —
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| LMArena Instruction Following | 1410 | — |
Long Context Not comparable
GLM-4.6: 43.4 (#94), GPT-5 Pro: —
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| LMArena Longer Query | 1422 | — |
Writing & Preference Not comparable
GLM-4.6: 61.1 (#90), GPT-5 Pro: —
| Benchmark | GLM-4.6 | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1440 | — |
| LMArena Creative Writing | 1411 | — |
| EQ-Bench Creative Writing | 1411 | — |
| LMArena Multi-Turn | 1427 | — |
Frequently asked questions
Is GLM-4.6 better than GPT-5 Pro?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.4 on the Noometry Index. GLM-4.6 costs 41× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or GPT-5 Pro?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GLM-4.6 or GPT-5 Pro better for coding?
GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 205K.
How many benchmarks do GLM-4.6 and GPT-5 Pro share?
2 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GPT-5 Pro has 12.