Model comparison
GLM-5.2 vs GPT-6 Luna
GPT-6 Luna is the stronger model overall, scoring 53.3 to 51.1 on the Noometry Index.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. GLM-5.2 scores higher in 5 categories and GPT-6 Luna in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6 Luna leads 76.1 to 55.7.
- The biggest single-benchmark swing is ARC-AGI-2: 22.8% for GLM-5.2 and 59.3% 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 | 51.1 | 53.3 |
| 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 | 51 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Luna leads
GLM-5.2: 51.3 (#41), GPT-6 Luna: 55.5 (#25)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| DeepSWE | 43.8% | 66.6% |
| FrontierCode | 24.5% | 42.4% |
| LMArena WebDev | 1603 | 1581 |
| SciCode | 50.5% | 54.6% |
| LMArena Coding | 1485 | 1439 |
| ALE-Bench | 1,047 | 1,577 |
| SWE-bench Verified | 78.7% | — |
| WeirdML | 70.1% | — |
Agentic & Tool Use Too close to call
GLM-5.2: 32.4 (#63), GPT-6 Luna: 33.3 (#54)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| APEX-Agents | 45.2% | 44.3% |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 31.7% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 23% |
| Vending-Bench 2 | 8,314 | — |
Reasoning GPT-6 Luna leads
GLM-5.2: 42.3 (#52), GPT-6 Luna: 48.2 (#41)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| ARC-AGI-2 | 22.8% | 59.3% |
| NYT Connections (extended) | 74.3% | 68.7% |
| ARC-AGI-1 | 77% | 86.7% |
| CritPt | 20.9% | 19.4% |
| Chess Puzzles | 21% | 31% |
| LMArena Hard Prompts | 1480 | 1411 |
| Mystery Game Puzzles | 19% | 7% |
| DTBench | 93.6% | 90.1% |
| LMCA | 45.8% | 44.5% |
| Epoch Capabilities Index | 151.78 | 156.28 |
| SimpleBench | 58.8% | — |
| Kagi LLM Benchmark | 62.6% | — |
| EBR-Bench | 9.5% | — |
| Surface Evolver Bench | 55.6% | — |
Math GPT-6 Luna leads
GLM-5.2: 55.7 (#43), GPT-6 Luna: 76.1 (#15)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 59.2% | 78.9% |
| FrontierMath Tier 4 | 29.3% | 56.1% |
| OTIS Mock AIME 2024-2025 | 86.4% | 98.9% |
| ProofBench | 35% | 64% |
| LMArena Math | 1482 | 1416 |
| MathArena Final-Answer Competitions | 67.6% | — |
Knowledge Too close to call
GLM-5.2: 57.1 (#40), GPT-6 Luna: 57.0 (#41)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| GPQA Diamond | 91.9% | 90.5% |
| SimpleQA Verified | 34.2% | 41.4% |
| LMArena Expert | 1486 | 1444 |
Multimodal Not comparable
GLM-5.2: —, GPT-6 Luna: 42.4 (#30)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Vision | — | 1217 |
| Blueprint-Bench 2 | — | 31.2% |
| Furniture Assembly | — | 44.2% |
Multilingual GLM-5.2 leads
GLM-5.2: 55.8 (#26), GPT-6 Luna: 50.5 (#117)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Non-English | 1459 | 1386 |
| LMArena Chinese | 1519 | 1433 |
| LMArena French | 1479 | 1420 |
| LMArena German | 1468 | 1369 |
| LMArena Japanese | 1451 | 1369 |
| LMArena Korean | 1445 | 1360 |
| LMArena Russian | 1466 | 1394 |
| LMArena Spanish | 1477 | 1393 |
Instruction Following GLM-5.2 leads
GLM-5.2: 76.9 (#34), GPT-6 Luna: 74.3 (#99)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Instruction Following | 1465 | 1409 |
Long Context GLM-5.2 leads
GLM-5.2: 45.3 (#43), GPT-6 Luna: 43.0 (#111)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Longer Query | 1479 | 1409 |
Writing & Preference GLM-5.2 leads
GLM-5.2: 70.4 (#21), GPT-6 Luna: 58.3 (#119)
| Benchmark | GLM-5.2 | GPT-6 Luna |
|---|---|---|
| LMArena Text | 1470 | 1391 |
| LMArena Creative Writing | 1462 | 1363 |
| LMArena Multi-Turn | 1469 | 1396 |
| EQ-Bench Creative Writing | 1757 | — |
| EQ-Bench 4 | 1222 | — |
Frequently asked questions
Is GLM-5.2 better than GPT-6 Luna?
GPT-6 Luna is the stronger model overall, scoring 53.3 to 51.1 on the Noometry Index.
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: 55.5 versus 51.3 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?
38 benchmarks have published results for both models. GLM-5.2 has 51 scored results on Noometry and GPT-6 Luna has 42.