# GPT-4o vs Llama 3.2 3B

> GPT-4o and Llama 3.2 3B score almost the same on the Noometry Index (28.6 vs 28.9), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-4o-vs-llama-3-2-3b
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. GPT-4o scores higher in 5 categories and Llama 3.2 3B in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4o leads 52.6 to 24.7.
- The biggest single-benchmark swing is BigCodeBench Complete: 61.1% for GPT-4o and 28.3% for Llama 3.2 3B.
- Llama 3.2 3B is cheaper at $0.05 / $0.33 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- Llama 3.2 3B accepts more context: 131K tokens versus 128K.
- Llama 3.2 3B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4o | Llama 3.2 3B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 28.6 | 28.9 |
| Rank | 324 | 321 |
| Context | 128K | 131K |
| Input $/M | $2.50 | $0.05 |
| Output $/M | $10 | $0.33 |
| Weights | Proprietary | Open |

## Coding

- GPT-4o: 24.8 (#328)
- Llama 3.2 3B: 27.6 (#319)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| BigCodeBench Instruct | 51.1% | 23.4% |
| LMArena Coding | 1297 | 1098 |
| BigCodeBench Complete | 61.1% | 28.3% |
| SWE-bench Verified | 31% | — |
| SWE-bench Verified (bash only) | 21.6% | — |
| Aider Polyglot | 45.3% | — |
| GSO | 0% | — |
| WeirdML | 25.1% | — |
| LiveBench Coding | 51.4% | — |
| CadEval | 26% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o: 21.0 (#141)
- Llama 3.2 3B: 20.1 (#143)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| BALROG | 32.3% | 10.1% |
| Berkeley Function Calling Leaderboard | — | 21.9% |
| GDPval | 9.9% | — |
| TheAgentCompany | 8.6% | — |
| Cybench | 12.5% | — |
| LMArena Search | 1006 | — |
| METR Time Horizons | 40.8% | — |

## Reasoning

- GPT-4o: 9.4 (#343)
- Llama 3.2 3B: 21.0 (#228)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Hard Prompts | 1281 | 1095 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 17.8% | — |
| ARC-AGI-1 | 4.5% | — |
| CritPt | 0% | — |
| Chess Puzzles | 13% | — |
| EnigmaEval | 0.8% | — |
| LiveBench Reasoning | 55.8% | — |
| DTBench | 64.5% | — |
| LiveBench Data Analysis | 60.9% | — |
| LMCA | 16.6% | — |
| Epoch Capabilities Index | 128.97 | — |
| ForecastBench | 57.7 | — |
| LiveBench | 55.3% | — |

## Math

- GPT-4o: 10.6 (#312)
- Llama 3.2 3B: 32.4 (#214)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Math | 1285 | 1126 |
| FrontierMath (Tiers 1-3) | 0.4% | — |
| OTIS Mock AIME 2024-2025 | 6.4% | — |
| Omni-MATH | 29.3% | — |
| LiveBench Math | 49.5% | — |
| MATH Level 5 | 53.3% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |

## Knowledge

- GPT-4o: 28.8 (#242)
- Llama 3.2 3B: 29.7 (#235)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Expert | 1250 | 1090 |
| GPQA Diamond | 49.2% | — |
| Humanity's Last Exam | 2.7% | — |
| SimpleQA Verified | 26% | — |
| MMLU-Pro | 71.3% | — |
| Confabulations | 15.3% | — |
| Vectara Hallucination Rate | 9.6% | — |
| GPQA (HELM) | 52% | — |
| MMLU | 88.1% | — |

## Multimodal

- GPT-4o: 34.5 (#91)
- Llama 3.2 3B: —

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Vision | 1137 | — |
| Video-MME | 71.9% | — |
| GeoBench | 71% | — |
| VPCT | 40% | — |
| ScienceQA | 88.5% | — |

## Multilingual

- GPT-4o: 43.2 (#186)
- Llama 3.2 3B: 26.2 (#281)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Non-English | 1283 | 1019 |
| LMArena Chinese | 1277 | 1017 |
| LMArena German | 1282 | 1056 |
| LMArena Russian | 1286 | 949 |
| LMArena French | 1304 | — |
| LMArena Japanese | 1257 | — |
| LMArena Korean | 1234 | — |
| LMArena Spanish | 1292 | — |

## Instruction Following

- GPT-4o: 66.6 (#207)
- Llama 3.2 3B: 56.0 (#275)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Instruction Following | 1278 | 1089 |
| LiveBench Instruction Following | 68.6% | — |
| IFEval | 81.7% | — |

## Long Context

- GPT-4o: 39.4 (#179)
- Llama 3.2 3B: 33.4 (#261)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Longer Query | 1289 | 1100 |
| Fiction.LiveBench | 66.7% | — |

## Writing & Preference

- GPT-4o: 52.6 (#166)
- Llama 3.2 3B: 24.7 (#307)

| Benchmark | GPT-4o | Llama 3.2 3B |
|---|---|---|
| LMArena Text | 1300 | 1110 |
| LMArena Creative Writing | 1292 | 1094 |
| LMArena Multi-Turn | 1302 | 1105 |
| Short-Story Creative Writing | 81.8% | — |
| EQ-Bench Creative Writing | — | 595 |
| WildBench | 82.8% | — |
| LiveBench Language | 47.6% | — |

## FAQ

### Is GPT-4o better than Llama 3.2 3B?

GPT-4o and Llama 3.2 3B score almost the same on the Noometry Index (28.6 vs 28.9), so choose on price, context window or the category you care about most.

### Which is cheaper, GPT-4o or Llama 3.2 3B?

Llama 3.2 3B is cheaper. It lists at $0.05 per million input tokens and $0.33 per million output tokens; GPT-4o lists at $2.50 and $10.

### Is GPT-4o or Llama 3.2 3B better for coding?

Llama 3.2 3B scores higher on coding benchmarks: 27.6 versus 24.8 in the Noometry coding category.

### Which has the bigger context window?

Llama 3.2 3B does, with 131K tokens against 128K.

### How many benchmarks do GPT-4o and Llama 3.2 3B share?

16 benchmarks have published results for both models. GPT-4o has 72 scored results on Noometry and Llama 3.2 3B has 18.