# GPT-5.4 mini vs Mistral Medium 3.5

> GPT-5.4 mini is the stronger model overall, scoring 44.8 to 39.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-mistral-medium-3-5
- Last updated: 2026-10-10
- Shared benchmarks: 21

## Summary

- They share 21 benchmarks with published results for both. GPT-5.4 mini scores higher in 6 categories and Mistral Medium 3.5 in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 mini leads 30.3 to 16.6.
- The biggest single-benchmark swing is NYT Connections (extended): 61.8% for GPT-5.4 mini and 12.9% for Mistral Medium 3.5.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
- GPT-5.4 mini accepts more context: 400K tokens versus 262K.
- Mistral Medium 3.5 has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 44.8 | 39.6 |
| Rank | 69 | 151 |
| Context | 400K | 262K |
| Input $/M | $0.75 | $1.50 |
| Output $/M | $4.50 | $7.50 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.0 (#67)
- Mistral Medium 3.5: 35.7 (#208)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena WebDev | 1397 | 1263 |
| LMArena Coding | 1438 | 1461 |
| FrontierCode | 27% | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.6 (#74)
- Mistral Medium 3.5: —

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.3 (#77)
- Mistral Medium 3.5: 16.6 (#290)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| Kagi LLM Benchmark | 37.9% | 41.4% |
| NYT Connections (extended) | 61.8% | 12.9% |
| LMArena Hard Prompts | 1424 | 1436 |
| Epoch Capabilities Index | 148.83 | 141.42 |
| ARC-AGI-2 | 18.9% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.4 (#63)
- Mistral Medium 3.5: 36.4 (#113)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena Math | 1418 | 1432 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.4 (#62)
- Mistral Medium 3.5: 39.3 (#123)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena Expert | 1434 | 1431 |
| GPQA Diamond | 86.9% | — |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |

## Multimodal

- GPT-5.4 mini: 39.0 (#51)
- Mistral Medium 3.5: 37.6 (#64)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena Vision | 1245 | 1222 |

## Multilingual

- GPT-5.4 mini: 52.1 (#94)
- Mistral Medium 3.5: 52.1 (#93)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena Non-English | 1405 | 1405 |
| LMArena Chinese | 1446 | 1443 |
| LMArena French | 1440 | 1448 |
| LMArena German | 1407 | 1453 |
| LMArena Korean | 1369 | 1387 |
| LMArena Russian | 1417 | 1396 |
| LMArena Spanish | 1403 | 1406 |
| LMArena Japanese | 1375 | — |

## Instruction Following

- GPT-5.4 mini: 74.3 (#99)
- Mistral Medium 3.5: 74.7 (#87)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena Instruction Following | 1405 | 1414 |

## Long Context

- GPT-5.4 mini: 42.9 (#107)
- Mistral Medium 3.5: 43.2 (#101)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena Longer Query | 1407 | 1414 |

## Writing & Preference

- GPT-5.4 mini: 64.2 (#56)
- Mistral Medium 3.5: 58.6 (#113)

| Benchmark | GPT-5.4 mini | Mistral Medium 3.5 |
|---|---|---|
| LMArena Text | 1411 | 1421 |
| LMArena Creative Writing | 1370 | 1372 |
| LMArena Multi-Turn | 1429 | 1423 |
| EQ-Bench Creative Writing | 1665 | — |
| EQ-Bench 4 | — | 993 |

## FAQ

### Is GPT-5.4 mini better than Mistral Medium 3.5?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 39.6 on the Noometry Index.

### Which is cheaper, GPT-5.4 mini or Mistral Medium 3.5?

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

### Is GPT-5.4 mini or Mistral Medium 3.5 better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 262K.

### How many benchmarks do GPT-5.4 mini and Mistral Medium 3.5 share?

21 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Mistral Medium 3.5 has 22.