Model comparison
GLM-4.6 vs GLM-5.1
GLM-5.1 is the stronger model overall, scoring 47.8 to 41.4 on the Noometry Index. GLM-4.6 costs 2.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Summary
- They share 24 benchmarks with published results for both. GLM-4.6 scores higher in 1 category and GLM-5.1 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 23.7.
- The biggest single-benchmark swing is SciCode: 38.4% for GLM-4.6 and 43.8% for GLM-5.1.
- GLM-4.6 is cheaper at $0.60 / $2.20 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-4.6 accepts more context: 205K tokens versus 200K.
Side by side
| GLM-4.6 | GLM-5.1 | |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 41.4 | 47.8 |
| Released | 2025-09-30 | 2026-04-07 |
| Weights | Open | Open |
| Context window | 205K | 200K |
| Max output | 131K | 131K |
| Input $ / M tokens | $0.60 | $1.40 |
| Output $ / M tokens | $2.20 | $4.40 |
| Results tracked | 29 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GLM-5.1 leads
GLM-4.6: 40.1 (#148), GLM-5.1: 48.7 (#55)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| LMArena WebDev | 1340 | 1508 |
| SciCode | 38.4% | 43.8% |
| LMArena Coding | 1449 | 1485 |
| ALE-Bench | 340.82 | 887.1 |
| SWE-bench Verified | — | 74.2% |
| SWE-bench Verified (bash only) | 55.4% | — |
| WeirdML | — | 57.1% |
Agentic & Tool Use GLM-4.6 leads
GLM-4.6: 32.3 (#66), GLM-5.1: 24.9 (#113)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| APEX-Agents | — | 40.9% |
| Berkeley Function Calling Leaderboard | 72.4% | — |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |
| Vending-Bench 2 | — | 5,634 |
Reasoning GLM-5.1 leads
GLM-4.6: 23.7 (#172), GLM-5.1: 39.1 (#60)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| CritPt | 1.1% | 4.6% |
| LMArena Hard Prompts | 1440 | 1472 |
| SimpleBench | — | 55.1% |
| Kagi LLM Benchmark | 47.4% | — |
| NYT Connections (extended) | — | 77.7% |
| Chess Puzzles | — | 19% |
| Thematic Generalization | — | 69.8% |
| Epoch Capabilities Index | — | 149.84 |
Math GLM-5.1 leads
GLM-4.6: 39.1 (#111), GLM-5.1: 49.7 (#60)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| LMArena Math | 1432 | 1473 |
| FrontierMath (Feb 2025 set) | 3.8% | 33.4% |
| FrontierMath Tier 4 (v1) | 2.1% | 12.5% |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| MathArena Final-Answer Competitions | — | 67.1% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| ProofBench | — | 22.2% |
Knowledge GLM-5.1 leads
GLM-4.6: 40.2 (#124), GLM-5.1: 54.9 (#50)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| LMArena Expert | 1431 | 1476 |
| GPQA Diamond | — | 89.9% |
| SimpleQA Verified | — | 34% |
| Vectara Hallucination Rate | 9.5% | — |
Multilingual GLM-5.1 leads
GLM-4.6: 53.5 (#66), GLM-5.1: 55.0 (#36)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1426 | 1447 |
| LMArena Chinese | 1499 | 1515 |
| LMArena French | 1459 | 1474 |
| LMArena German | 1447 | 1465 |
| LMArena Japanese | 1393 | 1434 |
| LMArena Korean | 1400 | 1418 |
| LMArena Russian | 1419 | 1454 |
| LMArena Spanish | 1436 | 1469 |
Instruction Following GLM-5.1 leads
GLM-4.6: 74.3 (#98), GLM-5.1: 76.3 (#42)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1451 |
Long Context GLM-5.1 leads
GLM-4.6: 43.4 (#94), GLM-5.1: 44.9 (#53)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1422 | 1466 |
Writing & Preference GLM-5.1 leads
GLM-4.6: 61.1 (#90), GLM-5.1: 66.9 (#31)
| Benchmark | GLM-4.6 | GLM-5.1 |
|---|---|---|
| LMArena Text | 1440 | 1461 |
| LMArena Creative Writing | 1411 | 1453 |
| EQ-Bench Creative Writing | 1411 | 1592 |
| LMArena Multi-Turn | 1427 | 1472 |
Frequently asked questions
Is GLM-4.6 better than GLM-5.1?
GLM-5.1 is the stronger model overall, scoring 47.8 to 41.4 on the Noometry Index. GLM-4.6 costs 2.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.
Which is cheaper, GLM-4.6 or GLM-5.1?
GLM-4.6 is cheaper. It lists at $0.60 per million input tokens and $2.20 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.
Is GLM-4.6 or GLM-5.1 better for coding?
GLM-5.1 scores higher on coding benchmarks: 48.7 versus 40.1 in the Noometry coding category.
Which has the bigger context window?
GLM-4.6 does, with 205K tokens against 200K.
How many benchmarks do GLM-4.6 and GLM-5.1 share?
24 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and GLM-5.1 has 41.