Model comparison
GLM-5.1 vs GPT-5.6 Luna
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 47.8 on the Noometry Index.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. GLM-5.1 scores higher in 3 categories and GPT-5.6 Luna in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.6 Luna leads 77.7 to 49.7.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 36.8% for GLM-5.1 and 82.1% for GPT-5.6 Luna.
- GPT-5.6 Luna is cheaper at $0.20 / $1.20 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GPT-5.6 Luna accepts more context: 1.05M tokens versus 200K.
- GLM-5.1 has downloadable open weights; the other is API-only.
Side by side
| GLM-5.1 | GPT-5.6 Luna | |
|---|---|---|
| Provider | Z.ai (Zhipu) | OpenAI |
| Noometry Index | 47.8 | 54.6 |
| Released | 2026-04-07 | 2026-07-09 |
| Weights | Open | Proprietary |
| Context window | 200K | 1.05M |
| Max output | 131K | 128K |
| Input $ / M tokens | $1.40 | $0.20 |
| Output $ / M tokens | $4.40 | $1.20 |
| Results tracked | 41 | 52 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.6 Luna leads
GLM-5.1: 48.7 (#55), GPT-5.6 Luna: 54.5 (#28)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| LMArena WebDev | 1508 | 1519 |
| SciCode | 43.8% | 53.6% |
| WeirdML | 57.1% | 60.9% |
| LMArena Coding | 1485 | 1466 |
| ALE-Bench | 887.1 | 1,667 |
| SWE-bench Verified | 74.2% | — |
| DeepSWE | — | 67.2% |
| FrontierCode | — | 39.8% |
| CursorBench | — | 35.9% |
Agentic & Tool Use GPT-5.6 Luna leads
GLM-5.1: 24.9 (#113), GPT-5.6 Luna: 34.4 (#45)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| APEX-Agents | 40.9% | 43% |
| Vending-Bench 2 | 5,634 | 4,095 |
| BALROG | — | 45.6% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| GDP.pdf | — | 22.7% |
Reasoning GPT-5.6 Luna leads
GLM-5.1: 39.1 (#60), GPT-5.6 Luna: 47.6 (#43)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| SimpleBench | 55.1% | 46.8% |
| NYT Connections (extended) | 77.7% | 69.4% |
| CritPt | 4.6% | 20.6% |
| Chess Puzzles | 19% | 40% |
| LMArena Hard Prompts | 1472 | 1451 |
| Epoch Capabilities Index | 149.84 | 156.39 |
| ARC-AGI-2 | — | 59.5% |
| Kagi LLM Benchmark | — | 49.1% |
| ARC-AGI-1 | — | 88% |
| Thematic Generalization | 69.8% | — |
| Mystery Game Puzzles | — | 21% |
| DTBench | — | 89.1% |
| LMCA | — | 48.5% |
| Surface Evolver Bench | — | 61.9% |
Math GPT-5.6 Luna leads
GLM-5.1: 49.7 (#60), GPT-5.6 Luna: 77.7 (#14)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.8% | 82.1% |
| OTIS Mock AIME 2024-2025 | 93.3% | 98.3% |
| ProofBench | 22.2% | 60% |
| LMArena Math | 1473 | 1458 |
| FrontierMath Tier 4 | — | 61% |
| MathArena Final-Answer Competitions | 67.1% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5.6 Luna leads
GLM-5.1: 54.9 (#50), GPT-5.6 Luna: 58.5 (#34)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| GPQA Diamond | 89.9% | 91.6% |
| SimpleQA Verified | 34% | 41% |
| LMArena Expert | 1476 | 1478 |
Multimodal Not comparable
GLM-5.1: —, GPT-5.6 Luna: 42.7 (#28)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Vision | — | 1258 |
| Blueprint-Bench 2 | — | 22.6% |
| Furniture Assembly | — | 42.5% |
| LMArena Document | — | 1457 |
Multilingual GLM-5.1 leads
GLM-5.1: 55.0 (#36), GPT-5.6 Luna: 52.8 (#78)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Non-English | 1447 | 1417 |
| LMArena Chinese | 1515 | 1470 |
| LMArena French | 1474 | 1456 |
| LMArena German | 1465 | 1454 |
| LMArena Japanese | 1434 | 1411 |
| LMArena Korean | 1418 | 1415 |
| LMArena Russian | 1454 | 1428 |
| LMArena Spanish | 1469 | 1448 |
Instruction Following Too close to call
GLM-5.1: 76.3 (#42), GPT-5.6 Luna: 75.6 (#57)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Instruction Following | 1451 | 1437 |
Long Context Too close to call
GLM-5.1: 44.9 (#53), GPT-5.6 Luna: 43.9 (#82)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Longer Query | 1466 | 1436 |
Writing & Preference GPT-5.6 Luna leads
GLM-5.1: 66.9 (#31), GPT-5.6 Luna: 68.0 (#29)
| Benchmark | GLM-5.1 | GPT-5.6 Luna |
|---|---|---|
| LMArena Text | 1461 | 1431 |
| LMArena Creative Writing | 1453 | 1396 |
| EQ-Bench Creative Writing | 1592 | 1829 |
| LMArena Multi-Turn | 1472 | 1434 |
| EQ-Bench 4 | — | 1156 |
Frequently asked questions
Is GLM-5.1 better than GPT-5.6 Luna?
GPT-5.6 Luna is the stronger model overall, scoring 54.6 to 47.8 on the Noometry Index.
Which is cheaper, GLM-5.1 or GPT-5.6 Luna?
GPT-5.6 Luna is cheaper. It lists at $0.20 per million input tokens and $1.20 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-5.1 or GPT-5.6 Luna better for coding?
GPT-5.6 Luna scores higher on coding benchmarks: 54.5 versus 48.7 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Luna does, with 1.05M tokens against 200K.
How many benchmarks do GLM-5.1 and GPT-5.6 Luna share?
34 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and GPT-5.6 Luna has 52.