Model comparison
GLM-4.6 vs GLM-5.2
GLM-5.2 is the stronger model overall, scoring 50.9 to 40.9 on the Noometry Index. GLM-4.6 costs 2.1× less per token, which makes it the better buy when GLM-5.2's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
Summary
- They share 23 benchmarks with published results for both. GLM-4.6 scores higher in 1 category and GLM-5.2 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.2 leads 42.1 to 23.1.
- The biggest single-benchmark swing is CritPt: 1.1% for GLM-4.6 and 20.9% for GLM-5.2.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.40 / $4.40 for GLM-5.2.
- GLM-5.2 accepts more context: 1M tokens versus 205K.
Side by side
| GLM-4.6 | GLM-5.2 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 40.9 | 50.9 |
| Released | 2025-09-30 | 2026-06-13 |
| Weights | Open | Open |
| Context window | 205K | 1M |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.60 | $1.40 |
| Output $ / M tokens | $2.20 | $4.40 |
| Results tracked | 29 | 50 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.2 leads
GLM-4.6: 39.9 (#137), GLM-5.2: 50.9 (#37)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| LMArena WebDev | 1339 | 1604 |
| SciCode | 38.4% | 50.5% |
| LMArena Coding | 1449 | 1484 |
| ALE-Bench | 340.82 | 1,047 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| FrontierCode | — | 24.5% |
| SWE-bench Verified (bash only) | 55.4% | — |
| WeirdML | — | 70.1% |
Agentic & Tool Use Too close to call
GLM-4.6: 32.1 (#60), GLM-5.2: 31.6 (#63)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 8,314 |
Reasoning GLM-5.2 leads
GLM-4.6: 23.1 (#168), GLM-5.2: 42.1 (#46)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 62.6% |
| CritPt | 1.1% | 20.9% |
| LMArena Hard Prompts | 1440 | 1480 |
| ARC-AGI-2 | — | 22.8% |
| SimpleBench | — | 58.8% |
| NYT Connections (extended) | — | 74.3% |
| ARC-AGI-1 | — | 77% |
| 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-4.6: 36.4 (#115), GLM-5.2: 55.4 (#35)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| LMArena Math | 1431 | 1482 |
| 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% |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GLM-5.2 leads
GLM-4.6: 39.6 (#118), GLM-5.2: 57.1 (#36)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| LMArena Expert | 1432 | 1484 |
| GPQA Diamond | — | 91.9% |
| SimpleQA Verified | — | 34.2% |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual GLM-5.2 leads
GLM-4.6: 53.6 (#62), GLM-5.2: 56.0 (#25)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1426 | 1459 |
| LMArena Chinese | 1500 | 1518 |
| LMArena French | 1459 | 1476 |
| LMArena German | 1447 | 1470 |
| LMArena Japanese | 1394 | 1451 |
| LMArena Korean | 1401 | 1445 |
| LMArena Russian | 1418 | 1467 |
| LMArena Spanish | 1436 | 1477 |
Instruction Following GLM-5.2 leads
GLM-4.6: 74.5 (#93), GLM-5.2: 77.1 (#32)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1465 |
Long Context GLM-5.2 leads
GLM-4.6: 43.4 (#91), GLM-5.2: 45.3 (#43)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1423 | 1479 |
Writing & Preference GLM-5.2 leads
GLM-4.6: 61.3 (#86), GLM-5.2: 70.7 (#20)
| Benchmark | GLM-4.6 | GLM-5.2 |
|---|---|---|
| LMArena Text | 1440 | 1470 |
| LMArena Creative Writing | 1411 | 1465 |
| EQ-Bench Creative Writing | 1411 | 1757 |
| LMArena Multi-Turn | 1427 | 1468 |
| EQ-Bench 4 | — | 1222 |
Frequently asked questions
Is GLM-4.6 better than GLM-5.2?
GLM-5.2 is the stronger model overall, scoring 50.9 to 40.9 on the Noometry Index. GLM-4.6 costs 2.1× 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-4.6 or GLM-5.2?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GLM-5.2 lists at $1.40 and $4.40.
Is GLM-4.6 or GLM-5.2 better for coding?
GLM-5.2 scores higher on coding benchmarks: 50.9 versus 39.9 in the Noometry coding category.
Which has the bigger context window?
GLM-5.2 does, with 1M tokens against 205K.
How many benchmarks do GLM-4.6 and GLM-5.2 share?
23 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GLM-5.2 has 50.