# GLM-5.1 vs Mistral Large 3

> GLM-5.1 is the stronger model overall, scoring 47.8 to 39.1 on the Noometry Index. Mistral Large 3 costs 5.7× 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-mistral-large-3
- Last updated: 2026-10-11
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-5.1 scores higher in 8 categories and Mistral Large 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-5.1 leads 39.1 to 15.2.
- The biggest single-benchmark swing is NYT Connections (extended): 77.7% for GLM-5.1 and 7.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $1.40 / $4.40 for GLM-5.1.
- Mistral Large 3 accepts more context: 262K tokens versus 200K.

## Snapshot

| | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 47.8 | 39.1 |
| Rank | 59 | 176 |
| Context | 200K | 262K |
| Input $/M | $1.40 | $0.25 |
| Output $/M | $4.40 | $0.75 |
| Weights | Open | Open |

## Coding

- GLM-5.1: 48.7 (#55)
- Mistral Large 3: 34.4 (#237)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1508 | 1230 |
| LMArena Coding | 1485 | 1448 |
| SWE-bench Verified | 74.2% | — |
| SciCode | 43.8% | — |
| WeirdML | 57.1% | — |
| ALE-Bench | 887.1 | — |

## Agentic & Tool Use

- GLM-5.1: 24.9 (#113)
- Mistral Large 3: —

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| APEX-Agents | 40.9% | — |
| ExploitBench | 18.1% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | 5,634 | — |

## Reasoning

- GLM-5.1: 39.1 (#60)
- Mistral Large 3: 15.2 (#319)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| NYT Connections (extended) | 77.7% | 7.5% |
| Thematic Generalization | 69.8% | 23% |
| LMArena Hard Prompts | 1472 | 1429 |
| SimpleBench | 55.1% | — |
| Kagi LLM Benchmark | — | 50.9% |
| CritPt | 4.6% | — |
| Chess Puzzles | 19% | — |
| Epoch Capabilities Index | 149.84 | — |

## Math

- GLM-5.1: 49.7 (#60)
- Mistral Large 3: 38.7 (#129)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1473 | 1414 |
| FrontierMath (Tiers 1-3) | 36.8% | — |
| MathArena Final-Answer Competitions | 67.1% | — |
| OTIS Mock AIME 2024-2025 | 93.3% | — |
| ProofBench | 22.2% | — |
| FrontierMath (Feb 2025 set) | 33.4% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |

## Knowledge

- GLM-5.1: 54.9 (#50)
- Mistral Large 3: 36.0 (#177)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1476 | 1421 |
| GPQA Diamond | 89.9% | — |
| SimpleQA Verified | 34% | — |
| Vectara Hallucination Rate | — | 14.5% |

## Multimodal

- GLM-5.1: —
- Mistral Large 3: 38.2 (#66)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |

## Multilingual

- GLM-5.1: 55.0 (#36)
- Mistral Large 3: 52.5 (#84)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1447 | 1413 |
| LMArena Chinese | 1515 | 1447 |
| LMArena French | 1474 | 1455 |
| LMArena German | 1465 | 1437 |
| LMArena Japanese | 1434 | 1394 |
| LMArena Korean | 1418 | 1384 |
| LMArena Russian | 1454 | 1411 |
| LMArena Spanish | 1469 | 1440 |

## Instruction Following

- GLM-5.1: 76.3 (#42)
- Mistral Large 3: 74.0 (#108)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1451 | 1403 |

## Long Context

- GLM-5.1: 44.9 (#53)
- Mistral Large 3: 43.1 (#105)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1466 | 1413 |

## Writing & Preference

- GLM-5.1: 66.9 (#31)
- Mistral Large 3: 60.0 (#101)

| Benchmark | GLM-5.1 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1461 | 1428 |
| LMArena Creative Writing | 1453 | 1386 |
| EQ-Bench Creative Writing | 1592 | 1412 |
| LMArena Multi-Turn | 1472 | 1429 |

## FAQ

### Is GLM-5.1 better than Mistral Large 3?

GLM-5.1 is the stronger model overall, scoring 47.8 to 39.1 on the Noometry Index. Mistral Large 3 costs 5.7× 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 Mistral Large 3?

Mistral Large 3 is cheaper. It lists at $0.25 per million input tokens and $0.75 per million output tokens; GLM-5.1 lists at $1.40 and $4.40.

### Is GLM-5.1 or Mistral Large 3 better for coding?

GLM-5.1 scores higher on coding benchmarks: 48.7 versus 34.4 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 200K.

### How many benchmarks do GLM-5.1 and Mistral Large 3 share?

21 benchmarks have published results for both models. GLM-5.1 has 41 scored results on Noometry and Mistral Large 3 has 24.