# GLM-5 vs GLM-5.1

> GLM-5.1 is the stronger model overall, scoring 47.8 to 46.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/glm-5-vs-glm-5-1
- Last updated: 2026-10-10
- Shared benchmarks: 32

## Summary

- They share 32 benchmarks with published results for both. GLM-5 scores higher in 2 categories and GLM-5.1 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 27.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 80% for GLM-5 and 93.3% for GLM-5.1.
- GLM-5 is cheaper at $1 / $3.20 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5 accepts more context: 205K tokens versus 200K.

## Snapshot

| | GLM-5 | GLM-5.1 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Z.ai (Zhipu) |
| Noometry Index | 46.1 | 47.8 |
| Rank | 66 | 59 |
| Context | 205K | 200K |
| Input $/M | $1 | $1.40 |
| Output $/M | $3.20 | $4.40 |
| Weights | Open | Open |

## Coding

- GLM-5: 49.0 (#52)
- GLM-5.1: 48.7 (#55)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| SWE-bench Verified | 72.1% | 74.2% |
| LMArena WebDev | 1434 | 1508 |
| WeirdML | 48.2% | 57.1% |
| LMArena Coding | 1461 | 1485 |
| ALE-Bench | 765.62 | 887.1 |
| SWE-bench Verified (bash only) | 72.8% | — |
| SWE-bench Multilingual | 69.7% | — |
| SciCode | — | 43.8% |

## Agentic & Tool Use

- GLM-5: 31.1 (#71)
- GLM-5.1: 24.9 (#113)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| Vending-Bench 2 | 4,432 | 5,634 |
| Terminal-Bench | 52.4% | — |
| APEX-Agents | — | 40.9% |
| τ²-bench Airline | 82.5% | — |
| τ²-bench Banking | 9.8% | — |
| τ²-bench Retail | 73.7% | — |
| τ²-bench Telecom | 86.8% | — |
| ExploitBench | — | 18.1% |
| GBAEval | — | 0% |

## Reasoning

- GLM-5: 27.6 (#116)
- GLM-5.1: 39.1 (#60)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| SimpleBench | 53.2% | 55.1% |
| NYT Connections (extended) | 74.8% | 77.7% |
| Chess Puzzles | 10% | 19% |
| LMArena Hard Prompts | 1452 | 1472 |
| Epoch Capabilities Index | 145.83 | 149.84 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 44.7% | — |
| CritPt | — | 4.6% |
| Thematic Generalization | — | 69.8% |
| ForecastBench | 61 | — |

## Math

- GLM-5: 46.4 (#71)
- GLM-5.1: 49.7 (#60)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| MathArena Final-Answer Competitions | 65.7% | 67.1% |
| OTIS Mock AIME 2024-2025 | 80% | 93.3% |
| LMArena Math | 1440 | 1473 |
| FrontierMath (Feb 2025 set) | 16.4% | 33.4% |
| FrontierMath Tier 4 (v1) | 2.1% | 12.5% |
| FrontierMath (Tiers 1-3) | — | 36.8% |
| ProofBench | — | 22.2% |

## Knowledge

- GLM-5: 52.3 (#64)
- GLM-5.1: 54.9 (#50)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| GPQA Diamond | 87.8% | 89.9% |
| LMArena Expert | 1454 | 1476 |
| SimpleQA Verified | — | 34% |
| Vectara Hallucination Rate | 10.1% | — |

## Multilingual

- GLM-5: 53.7 (#58)
- GLM-5.1: 55.0 (#36)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| LMArena Non-English | 1430 | 1447 |
| LMArena Chinese | 1511 | 1515 |
| LMArena French | 1455 | 1474 |
| LMArena German | 1445 | 1465 |
| LMArena Japanese | 1416 | 1434 |
| LMArena Korean | 1423 | 1418 |
| LMArena Russian | 1436 | 1454 |
| LMArena Spanish | 1454 | 1469 |

## Instruction Following

- GLM-5: 75.2 (#67)
- GLM-5.1: 76.3 (#42)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| LMArena Instruction Following | 1428 | 1451 |

## Long Context

- GLM-5: 44.7 (#60)
- GLM-5.1: 44.9 (#53)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| LMArena Longer Query | 1446 | 1466 |
| CL-bench | 18.7% | — |

## Writing & Preference

- GLM-5: 66.0 (#38)
- GLM-5.1: 66.9 (#31)

| Benchmark | GLM-5 | GLM-5.1 |
|---|---|---|
| LMArena Text | 1446 | 1461 |
| LMArena Creative Writing | 1439 | 1453 |
| EQ-Bench Creative Writing | 1601 | 1592 |
| LMArena Multi-Turn | 1456 | 1472 |

## FAQ

### Is GLM-5 better than GLM-5.1?

GLM-5.1 is the stronger model overall, scoring 47.8 to 46.1 on the Noometry Index.

### Which is cheaper, GLM-5 or GLM-5.1?

GLM-5 is cheaper. It lists at $1 per million input tokens and $3.20 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5 or GLM-5.1 better for coding?

They score almost the same on coding (49.0 vs 48.7); test both on your own repository before choosing.

### Which has the bigger context window?

GLM-5 does, with 205K tokens against 200K.

### How many benchmarks do GLM-5 and GLM-5.1 share?

32 benchmarks have published results for both models. GLM-5 has 45 scored results on Noometry and GLM-5.1 has 41.