# GPT-5.4 mini vs Llama-3.3-70B-Instruct

> GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct 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-llama-3-3-70b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. GPT-5.4 mini scores higher in 9 categories and Llama-3.3-70B-Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 15.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for GPT-5.4 mini and 5.1% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 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 128K.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 45.0 | 30.6 |
| Rank | 76 | 291 |
| Context | 400K | 128K |
| Input $/M | $0.75 | $0.10 |
| Output $/M | $4.50 | $0.32 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 mini: 45.2 (#72)
- Llama-3.3-70B-Instruct: 31.0 (#290)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| SciCode | 49.9% | 26% |
| WeirdML | 60.3% | 14.4% |
| LMArena Coding | 1438 | 1268 |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| BigCodeBench Instruct | — | 46.9% |
| LiveBench Coding | — | 36.6% |
| BigCodeBench Complete | — | 57.5% |
| ALE-Bench | 1,189 | — |

## Agentic & Tool Use

- GPT-5.4 mini: 29.9 (#81)
- Llama-3.3-70B-Instruct: 25.8 (#105)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 31.9% |
| DeepResearch Bench | 36.3% | — |
| BALROG | — | 23% |

## Reasoning

- GPT-5.4 mini: 30.4 (#85)
- Llama-3.3-70B-Instruct: 14.1 (#327)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| CritPt | 10% | 0% |
| LMArena Hard Prompts | 1424 | 1257 |
| DTBench | 80% | 59.5% |
| LMCA | 40.8% | 17.5% |
| Epoch Capabilities Index | 148.84 | 127.33 |
| ForecastBench | 57 | 58.6 |
| ARC-AGI-2 | 18.9% | — |
| SimpleBench | — | 19.9% |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 61.7% | — |
| LiveBench Reasoning | — | 50.8% |
| Mystery Game Puzzles | 11% | — |
| LiveBench Data Analysis | — | 49.5% |
| LiveBench | — | 50.2% |

## Math

- GPT-5.4 mini: 45.5 (#75)
- Llama-3.3-70B-Instruct: 15.3 (#298)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 5.1% |
| LMArena Math | 1419 | 1267 |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| ProofBench | 21% | — |
| LiveBench Math | — | 42.2% |
| MATH Level 5 | — | 41.6% |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |

## Knowledge

- GPT-5.4 mini: 51.5 (#67)
- Llama-3.3-70B-Instruct: 30.6 (#226)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| GPQA Diamond | 86.9% | 47.4% |
| Vectara Hallucination Rate | 5.5% | 4.1% |
| LMArena Expert | 1435 | 1225 |
| SimpleQA Verified | 29.4% | — |
| Confabulations | — | 22.8% |
| MMLU | — | 86.3% |

## Multimodal

- GPT-5.4 mini: 39.7 (#56)
- Llama-3.3-70B-Instruct: —

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 51.9 (#96)
- Llama-3.3-70B-Instruct: 39.9 (#220)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1405 | 1236 |
| LMArena Chinese | 1446 | 1217 |
| LMArena French | 1440 | 1281 |
| LMArena German | 1409 | 1251 |
| LMArena Japanese | 1374 | 1150 |
| LMArena Korean | 1368 | 1143 |
| LMArena Russian | 1417 | 1252 |
| LMArena Spanish | 1405 | 1270 |

## Instruction Following

- GPT-5.4 mini: 74.1 (#102)
- Llama-3.3-70B-Instruct: 71.1 (#157)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | 1242 |
| LiveBench Instruction Following | — | 82.7% |

## Long Context

- GPT-5.4 mini: 43.0 (#112)
- Llama-3.3-70B-Instruct: 26.4 (#295)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1407 | 1256 |
| Fiction.LiveBench | — | 33.3% |

## Writing & Preference

- GPT-5.4 mini: 64.0 (#58)
- Llama-3.3-70B-Instruct: 47.6 (#207)

| Benchmark | GPT-5.4 mini | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1412 | 1274 |
| LMArena Creative Writing | 1370 | 1250 |
| LMArena Multi-Turn | 1429 | 1280 |
| EQ-Bench Creative Writing | 1665 | — |
| LiveBench Language | — | 39.2% |

## FAQ

### Is GPT-5.4 mini better than Llama-3.3-70B-Instruct?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.6 on the Noometry Index. Llama-3.3-70B-Instruct 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 Llama-3.3-70B-Instruct?

Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.

### Is GPT-5.4 mini or Llama-3.3-70B-Instruct better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 31.0 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 128K.

### How many benchmarks do GPT-5.4 mini and Llama-3.3-70B-Instruct share?

27 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Llama-3.3-70B-Instruct has 43.