# GLM-4.5 vs Mistral Small 3

> GLM-4.5 is the stronger model overall, scoring 42.0 to 31.2 on the Noometry Index. Mistral Small 3 costs 17× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/glm-4-5-vs-mistral-small-3
- Last updated: 2026-10-10
- Shared benchmarks: 18

## Summary

- They share 18 benchmarks with published results for both. GLM-4.5 scores higher in 8 categories and Mistral Small 3 in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GLM-4.5 leads 57.5 to 32.2.
- The biggest single-benchmark swing is Confabulations: 11.3% for GLM-4.5 and 25.2% for Mistral Small 3.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.60 / $2.20 for GLM-4.5.
- GLM-4.5 accepts more context: 131K tokens versus 33K.

## Snapshot

| | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| Provider | Z.ai (Zhipu) | Mistral AI |
| Noometry Index | 42.0 | 31.2 |
| Rank | 122 | 278 |
| Context | 131K | 33K |
| Input $/M | $0.60 | $0.05 |
| Output $/M | $2.20 | $0.08 |
| Weights | Open | Open |

## Coding

- GLM-4.5: 41.4 (#125)
- Mistral Small 3: 36.5 (#207)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1434 | 1246 |
| SWE-bench Verified (bash only) | 54.2% | — |
| WeirdML | 40.6% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 344.82 | — |
| AlgoTune | 1.52 | — |

## Reasoning

- GLM-4.5: 28.6 (#100)
- Mistral Small 3: 18.9 (#273)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1429 | 1233 |
| Kagi LLM Benchmark | 57.9% | — |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |

## Math

- GLM-4.5: 39.0 (#116)
- Mistral Small 3: 16.3 (#295)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1427 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |

## Knowledge

- GLM-4.5: 35.9 (#179)
- Mistral Small 3: 25.1 (#263)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| Confabulations | 11.3% | 25.2% |
| LMArena Expert | 1433 | 1202 |
| GPQA Diamond | — | 47.3% |
| Humanity's Last Exam | 8.3% | — |

## Multilingual

- GLM-4.5: 52.8 (#77)
- Mistral Small 3: 37.3 (#236)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1417 | 1198 |
| LMArena Chinese | 1465 | 1204 |
| LMArena French | 1418 | 1203 |
| LMArena German | 1407 | 1211 |
| LMArena Japanese | 1415 | 1111 |
| LMArena Korean | 1380 | 1188 |
| LMArena Russian | 1414 | 1216 |
| LMArena Spanish | 1454 | — |

## Instruction Following

- GLM-4.5: 74.1 (#104)
- Mistral Small 3: 63.7 (#229)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1214 |

## Long Context

- GLM-4.5: 38.2 (#201)
- Mistral Small 3: 37.8 (#211)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1412 | 1246 |
| Fiction.LiveBench | 58.3% | — |

## Writing & Preference

- GLM-4.5: 57.5 (#127)
- Mistral Small 3: 32.2 (#280)

| Benchmark | GLM-4.5 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1430 | 1234 |
| LMArena Creative Writing | 1395 | 1195 |
| EQ-Bench Creative Writing | 1343 | 707 |
| LMArena Multi-Turn | 1415 | 1217 |
| Short-Story Creative Writing | 73.4% | — |

## FAQ

### Is GLM-4.5 better than Mistral Small 3?

GLM-4.5 is the stronger model overall, scoring 42.0 to 31.2 on the Noometry Index. Mistral Small 3 costs 17× less per token, which makes it the better buy when GLM-4.5's lead doesn't matter for your workload.

### Which is cheaper, GLM-4.5 or Mistral Small 3?

Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; GLM-4.5 lists at $0.60 and $2.20.

### Is GLM-4.5 or Mistral Small 3 better for coding?

GLM-4.5 scores higher on coding benchmarks: 41.4 versus 36.5 in the Noometry coding category.

### Which has the bigger context window?

GLM-4.5 does, with 131K tokens against 33K.

### How many benchmarks do GLM-4.5 and Mistral Small 3 share?

18 benchmarks have published results for both models. GLM-4.5 has 27 scored results on Noometry and Mistral Small 3 has 24.