Model comparison
GLM-5.2 vs GPT-6 Luna
GLM-5.2 is the stronger model overall, scoring 50.9 to 45.1 on the Noometry Index. GPT-6 Luna costs 11× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GLM-5.2 scores higher in 7 categories and GPT-6 Luna in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GLM-5.2 leads 55.4 to 35.6.
- The biggest single-benchmark swing is DeepSWE: 43.8% for GLM-5.2 and 66.6% for GPT-6 Luna.
- GPT-6 Luna is cheaper at $0.10 / $0.50 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GPT-6 Luna accepts more context: 1.05M tokens versus 1M.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.2 | GPT-6 Luna | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 50.9 | 45.1 |
| Released | 2026-06-13 | 2026-09-22 |
| Weights | Open | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $0.10 |
| Output $ / M tokens | $4.40 | $0.50 |
| Results tracked | 50 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GLM-5.2: 50.9 (#37), GPT-6 Luna: 54.7 (#24)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| DeepSWE | 43.8% | 66.6% |
| FrontierCode | 24.5% | 42.4% |
| LMArena WebDev | 1604 | 1583 |
| LMArena Coding | 1484 | 1448 |
| SWE-bench Verified | 78.7% | — |
| SciCode | 50.5% | — |
| WeirdML | 70.1% | — |
| ALE-Bench | 1,047 | — |
Agentic & Tool Use Not comparable
GLM-5.2: 31.6 (#63), GPT-6 Luna: —
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 8,314 | — |
Reasoning GLM-5.2 leads
GLM-5.2: 42.1 (#46), GPT-6 Luna: 31.7 (#68)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| NYT Connections (extended) | 74.3% | 68.7% |
| LMArena Hard Prompts | 1480 | 1415 |
| ARC-AGI-2 | 22.8% | — |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| ARC-AGI-1 | 77% | — |
| CritPt | 20.9% | — |
| Chess Puzzles | 21% | — |
| EBR-Bench | 9.5% | — |
| Mystery Game Puzzles | 19% | — |
| DTBench | 93.6% | — |
| LMCA | 45.8% | — |
| Surface Evolver Bench | 55.6% | — |
| Epoch Capabilities Index | 151.76 | — |
Math GLM-5.2 leads
GLM-5.2: 55.4 (#35), GPT-6 Luna: 35.6 (#140)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Math | 1482 | 1396 |
| FrontierMath (Tiers 1-3) | 59.2% | — |
| FrontierMath Tier 4 | 29.3% | — |
| MathArena Final-Answer Competitions | 67.6% | — |
| OTIS Mock AIME 2024-2025 | 86.4% | — |
| ProofBench | 35% | — |
Knowledge GLM-5.2 leads
GLM-5.2: 57.1 (#36), GPT-6 Luna: 40.1 (#110)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Expert | 1484 | 1458 |
| GPQA Diamond | 91.9% | — |
| SimpleQA Verified | 34.2% | — |
Multimodal Not comparable
GLM-5.2: —, GPT-6 Luna: 42.0 (#27)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| Furniture Assembly | — | 44.2% |
Multilingual GLM-5.2 leads
GLM-5.2: 56.0 (#25), GPT-6 Luna: 51.0 (#111)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1459 | 1390 |
| LMArena Chinese | 1518 | 1425 |
| LMArena Russian | 1467 | 1392 |
| LMArena Spanish | 1477 | 1416 |
| LMArena French | 1476 | — |
| LMArena German | 1470 | — |
| LMArena Japanese | 1451 | — |
| LMArena Korean | 1445 | — |
Instruction Following GLM-5.2 leads
GLM-5.2: 77.1 (#32), GPT-6 Luna: 74.7 (#85)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1465 | 1414 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), GPT-6 Luna: 43.3 (#95)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1479 | 1417 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.7 (#20), GPT-6 Luna: 58.4 (#115)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1470 | 1392 |
| LMArena Creative Writing | 1465 | 1357 |
| LMArena Multi-Turn | 1468 | 1400 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than GPT-6 Luna?
GLM-5.2 is the stronger model overall, scoring 50.9 to 45.1 on the Noometry Index. GPT-6 Luna costs 11× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Which is cheaper, GLM-5.2 or GPT-6 Luna?
GPT-6 Luna is cheaper. It lists at $0.10 per million input tokens and $0.50 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-5.2 or GPT-6 Luna better for coding?
GPT-6 Luna scores higher on coding benchmarks: 54.7 versus 50.9 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Luna does, with 1.05M tokens against 1M.
How many benchmarks do GLM-5.2 and GPT-6 Luna share?
17 benchmarks have published results for both models. GLM-5.2 has 50 scored results on Noometry and GPT-6 Luna has 18.