# GLM-4.6 vs Mistral Large 3

> GLM-4.6 is the stronger model overall, scoring 40.9 to 38.6 on the Noometry Index. Mistral Large 3 costs 2.7× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-6-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GLM-4.6 scores higher in 8 categories and Mistral Large 3 in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GLM-4.6 leads 23.1 to 14.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 9.5% for GLM-4.6 and 14.5% for Mistral Large 3.
- Mistral Large 3 is cheaper at $0.25 / $0.75 per million input/output tokens, against $0.60 / $2.20 for GLM-4.6.
- Mistral Large 3 accepts more context: 262K tokens versus 205K.

## Snapshot

| | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 40.9 | 38.6 |
| Rank | 132 | 172 |
| Context | 205K | 262K |
| Input $/M | $0.60 | $0.25 |
| Output $/M | $2.20 | $0.75 |
| Weights | Open | Open |

## Coding

- GLM-4.6: 39.9 (#137)
- Mistral Large 3: 34.1 (#230)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena WebDev | 1339 | 1230 |
| LMArena Coding | 1449 | 1447 |
| SWE-bench Verified (bash only) | 55.4% | — |
| SciCode | 38.4% | — |
| ALE-Bench | 340.82 | — |

## Agentic & Tool Use

- GLM-4.6: 32.1 (#60)
- Mistral Large 3: —

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| Terminal-Bench | 24.5% | — |
| Berkeley Function Calling Leaderboard | 72.4% | — |

## Reasoning

- GLM-4.6: 23.1 (#168)
- Mistral Large 3: 14.6 (#314)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| Kagi LLM Benchmark | 47.4% | 50.9% |
| LMArena Hard Prompts | 1440 | 1429 |
| NYT Connections (extended) | — | 7.5% |
| CritPt | 1.1% | — |
| Thematic Generalization | — | 23% |

## Math

- GLM-4.6: 36.4 (#115)
- Mistral Large 3: 36.0 (#131)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1431 | 1415 |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GLM-4.6: 39.6 (#118)
- Mistral Large 3: 35.5 (#173)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| Vectara Hallucination Rate | 9.5% | 14.5% |
| LMArena Expert | 1432 | 1421 |

## Multimodal

- GLM-4.6: —
- Mistral Large 3: 37.6 (#65)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- GLM-4.6: 53.6 (#62)
- Mistral Large 3: 52.6 (#79)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1426 | 1412 |
| LMArena Chinese | 1500 | 1448 |
| LMArena French | 1459 | 1456 |
| LMArena German | 1447 | 1438 |
| LMArena Japanese | 1394 | 1399 |
| LMArena Korean | 1401 | 1384 |
| LMArena Russian | 1418 | 1412 |
| LMArena Spanish | 1436 | 1437 |

## Instruction Following

- GLM-4.6: 74.5 (#93)
- Mistral Large 3: 74.1 (#104)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1410 | 1402 |

## Long Context

- GLM-4.6: 43.4 (#91)
- Mistral Large 3: 43.1 (#102)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1423 | 1413 |

## Writing & Preference

- GLM-4.6: 61.3 (#86)
- Mistral Large 3: 60.2 (#100)

| Benchmark | GLM-4.6 | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1440 | 1427 |
| LMArena Creative Writing | 1411 | 1385 |
| EQ-Bench Creative Writing | 1411 | 1412 |
| LMArena Multi-Turn | 1427 | 1429 |

## FAQ

### Is GLM-4.6 better than Mistral Large 3?

GLM-4.6 is the stronger model overall, scoring 40.9 to 38.6 on the Noometry Index. Mistral Large 3 costs 2.7× less per token, which makes it the better buy when GLM-4.6's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.6 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-4.6 lists at $0.60 and $2.20.

### Is GLM-4.6 or Mistral Large 3 better for coding?

GLM-4.6 scores higher on coding benchmarks: 39.9 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 205K.

### How many benchmarks do GLM-4.6 and Mistral Large 3 share?

21 benchmarks have published results for both models. GLM-4.6 has 29 scored results on Noometry and Mistral Large 3 has 24.