# GLM-5.1 vs Llama 4 Maverick

> GLM-5.1 is the stronger model overall, scoring 47.6 to 30.6 on the Noometry Index. Llama 4 Maverick costs 7.1× less per token, which makes it the better buy when GLM-5.1's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-5-1-vs-llama-4-maverick
- Last updated: 2026-10-10
- Shared benchmarks: 28

## Summary

- They share 28 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Llama 4 Maverick in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 38.2 to 10.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 93.3% for GLM-5.1 and 20.6% for Llama 4 Maverick.
- Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- GLM-5.1 accepts more context: 200K tokens versus 128K.

## Snapshot

| | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| Provider | Z.ai (Zhipu) | Meta |
| Noometry Index | 47.6 | 30.6 |
| Rank | 51 | 276 |
| Context | 200K | 128K |
| Input $/M | $1.40 | $0.19 |
| Output $/M | $4.40 | $0.65 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.5 (#52)
- Llama 4 Maverick: 26.3 (#318)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| SciCode | 43.8% | 33.1% |
| WeirdML | 57.1% | 24.5% |
| LMArena Coding | 1486 | 1302 |
| ALE-Bench | 887.1 | 172.97 |
| SWE-bench Verified | 74.2% | — |
| SWE-bench Verified (bash only) | — | 21% |
| Aider Polyglot | — | 15.6% |
| LMArena WebDev | 1509 | — |
| BigCodeBench Instruct | — | 49.7% |
| BigCodeBench Complete | — | 61.4% |

## Agentic & Tool Use

- GLM-5.1: 24.8 (#106)
- Llama 4 Maverick: 27.9 (#86)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| APEX-Agents | 40.9% | — |
| Berkeley Function Calling Leaderboard | — | 37.3% |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 38.2 (#57)
- Llama 4 Maverick: 10.1 (#337)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| SimpleBench | 55.1% | 27.7% |
| NYT Connections (extended) | 77.7% | 8% |
| CritPt | 4.6% | 0% |
| LMArena Hard Prompts | 1472 | 1281 |
| Epoch Capabilities Index | 149.86 | 132.2 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 55.9% |
| ARC-AGI-1 | — | 4.4% |
| Chess Puzzles | 19% | — |
| EnigmaEval | — | 0.6% |
| Thematic Generalization | 69.8% | — |
| DTBench | — | 61.9% |
| LMCA | — | 15.9% |
| ForecastBench | — | 57.5 |

## Math

- GLM-5.1: 49.0 (#48)
- Llama 4 Maverick: 24.6 (#256)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 93.3% | 20.6% |
| LMArena Math | 1472 | 1299 |
| FrontierMath (Feb 2025 set) | 33.4% | 0.7% |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| ProofBench | 22.2% | — |
| Omni-MATH | — | 42.2% |
| MATH Level 5 | — | 73% |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 55.0 (#45)
- Llama 4 Maverick: 33.3 (#196)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| GPQA Diamond | 89.9% | 67% |
| LMArena Expert | 1477 | 1259 |
| Humanity's Last Exam | — | 5.7% |
| SimpleQA Verified | 34% | — |
| MMLU-Pro | — | 81% |
| Confabulations | — | 22.6% |
| Vectara Hallucination Rate | — | 8.2% |
| GPQA (HELM) | — | 65% |

## Multimodal

- GLM-5.1: —
- Llama 4 Maverick: 30.9 (#100)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Vision | — | 1141 |
| GeoBench | — | 52% |
| SpatialViz-Bench | — | 31.8% |

## Multilingual

- GLM-5.1: 55.2 (#34)
- Llama 4 Maverick: 42.4 (#190)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Non-English | 1448 | 1269 |
| LMArena Chinese | 1516 | 1277 |
| LMArena French | 1478 | 1258 |
| LMArena German | 1466 | 1291 |
| LMArena Japanese | 1436 | 1207 |
| LMArena Korean | 1423 | 1203 |
| LMArena Russian | 1453 | 1286 |
| LMArena Spanish | 1467 | 1293 |

## Instruction Following

- GLM-5.1: 76.5 (#41)
- Llama 4 Maverick: 71.9 (#140)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Instruction Following | 1451 | 1267 |
| IFEval | — | 90.8% |

## Long Context

- GLM-5.1: 44.9 (#51)
- Llama 4 Maverick: 31.4 (#274)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Longer Query | 1467 | 1280 |
| Fiction.LiveBench | — | 46.2% |

## Writing & Preference

- GLM-5.1: 67.2 (#29)
- Llama 4 Maverick: 39.0 (#247)

| Benchmark | GLM-5.1 | Llama 4 Maverick |
|---|---|---|
| LMArena Text | 1462 | 1287 |
| LMArena Creative Writing | 1454 | 1266 |
| EQ-Bench Creative Writing | 1592 | 860 |
| LMArena Multi-Turn | 1473 | 1289 |
| Short-Story Creative Writing | — | 62% |
| WildBench | — | 80% |

## FAQ

### Is GLM-5.1 better than Llama 4 Maverick?

GLM-5.1 is the stronger model overall, scoring 47.6 to 30.6 on the Noometry Index. Llama 4 Maverick costs 7.1× 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-5.1 or Llama 4 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Llama 4 Maverick better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.5 versus 26.3 in the Noometry coding category.

### Which has the bigger context window?

GLM-5.1 does, with 200K tokens against 128K.

### How many benchmarks do GLM-5.1 and Llama 4 Maverick share?

28 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Llama 4 Maverick has 54.