# GPT-5.4 mini vs Ministral 8B

> GPT-5.4 mini is the stronger model overall, scoring 45.0 to 28.2 on the Noometry Index. Ministral 8B costs 11× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-4-mini-vs-ministral-8b
- Last updated: 2026-10-12
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and Ministral 8B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 12.6.
- The biggest single-benchmark swing is GPQA Diamond: 86.9% for GPT-5.4 mini and 27.1% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 262K.
- Ministral 8B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| Provider | OpenAI | Mistral AI |
| Noometry Index | 45.0 | 28.2 |
| Rank | 76 | 325 |
| Context | 400K | 262K |
| Input $/M | $0.75 | $0.15 |
| Output $/M | $4.50 | $0.15 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Ministral 8B: 35.0 (#230)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Coding | 1438 | 1202 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Ministral 8B: 16.4 (#148)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 11.1% |
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Ministral 8B: 18.4 (#281)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1191 |
| DTBench | 80% | 45.7% |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| Mystery Game Puzzles | 11% | — |
| LMCA | 40.8% | — |
| Epoch Capabilities Index | 148.84 | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Ministral 8B: 25.7 (#267)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Math | 1419 | 1188 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| MATH Level 5 | — | 14.9% |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Ministral 8B: 12.6 (#297)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| GPQA Diamond | 86.9% | 27.1% |
| Vectara Hallucination Rate | 5.5% | 7.4% |
| LMArena Expert | 1435 | 1170 |
| SimpleQA Verified | 29.4% | — |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Ministral 8B: —

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Ministral 8B: 35.1 (#247)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1405 | 1165 |
| LMArena Chinese | 1446 | 1193 |
| LMArena Russian | 1417 | 1195 |
| LMArena French | 1440 | — |
| LMArena German | 1409 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1368 | — |
| LMArena Spanish | 1405 | — |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Ministral 8B: 60.5 (#250)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1161 |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Ministral 8B: 36.7 (#227)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1407 | 1212 |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Ministral 8B: 39.6 (#246)

| Benchmark | GPT-5.4 mini | Ministral 8B |
|---|---|---|
| LMArena Text | 1412 | 1191 |
| LMArena Creative Writing | 1370 | 1175 |
| LMArena Multi-Turn | 1429 | 1166 |
| EQ-Bench Creative Writing | 1665 | — |

## FAQ

### Is GPT-5.4 mini better than Ministral 8B?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 28.2 on the Noometry Index. Ministral 8B costs 11× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.4 mini or Ministral 8B?

Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

### Is GPT-5.4 mini or Ministral 8B better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 35.0 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 Ministral 8B share?

15 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Ministral 8B has 17.