# GPT-4 vs Llama 2-13B

> GPT-4 and Llama 2-13B score almost the same on the Noometry Index (28.9 vs 29.1), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-4-vs-llama-2-13b
- Last updated: 2026-10-10
- Shared benchmarks: 26

## Summary

- They share 26 benchmarks with published results for both. GPT-4 scores higher in 6 categories and Llama 2-13B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Llama 2-13B leads 28.7 to 10.1.
- The biggest single-benchmark swing is DTBench: 62.7% for GPT-4 and 42.2% for Llama 2-13B.
- Llama 2-13B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 | Llama 2-13B |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 28.9 | 29.1 |
| Rank | 308 | 304 |
| Context | 8K | — |
| Input $/M | $30 | — |
| Output $/M | $60 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4: 31.2 (#277)
- Llama 2-13B: 30.4 (#287)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1254 | 1062 |
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |

## Agentic & Tool Use

- GPT-4: —
- Llama 2-13B: —

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| METR Time Horizons | 36.1% | — |

## Reasoning

- GPT-4: 17.3 (#285)
- Llama 2-13B: 12.3 (#333)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| Chess Puzzles | 4% | 0% |
| LMArena Hard Prompts | 1241 | 1051 |
| DTBench | 62.7% | 42.2% |
| BIG-Bench Hard | 75.1% | 58.2% |
| Epoch Capabilities Index | 125.88 | 105.8 |
| HellaSwag | 95.3% | 80.7% |
| WinoGrande | 87.5% | 72.8% |
| Mystery Game Puzzles | 12% | — |
| LMCA | 17.1% | — |
| ForecastBench | 57.8 | — |
| LAMBADA | — | 76.5% |
| PIQA | — | 80.8% |

## Math

- GPT-4: 10.1 (#304)
- Llama 2-13B: 28.7 (#226)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| LMArena Math | 1269 | 1065 |
| GSM8K | 92% | 36.9% |
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| MATH Level 5 | 23% | — |

## Knowledge

- GPT-4: 18.4 (#277)
- Llama 2-13B: 27.5 (#244)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1211 | 1030 |
| MMLU | 86.4% | 55.6% |
| TriviaQA | 84.8% | 79.6% |
| GPQA Diamond | 35.7% | — |
| ARC (AI2) Challenge | — | 60.3% |
| BoolQ | — | 82.4% |
| OpenBookQA | — | 57% |

## Multimodal

- GPT-4: —
- Llama 2-13B: —

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| ScienceQA | — | 55.8% |

## Multilingual

- GPT-4: 40.8 (#210)
- Llama 2-13B: 26.7 (#274)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1246 | 1024 |
| LMArena Chinese | 1242 | 1001 |
| LMArena French | 1282 | 1043 |
| LMArena German | 1251 | 1009 |
| LMArena Japanese | 1209 | 894 |
| LMArena Korean | 1184 | 953 |
| LMArena Russian | 1251 | 1055 |
| LMArena Spanish | 1261 | 1086 |

## Instruction Following

- GPT-4: 65.5 (#217)
- Llama 2-13B: 53.5 (#282)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1241 | 1046 |

## Long Context

- GPT-4: 37.7 (#207)
- Llama 2-13B: 32.3 (#264)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1244 | 1064 |

## Writing & Preference

- GPT-4: 35.0 (#263)
- Llama 2-13B: 30.0 (#284)

| Benchmark | GPT-4 | Llama 2-13B |
|---|---|---|
| LMArena Text | 1263 | 1085 |
| LMArena Creative Writing | 1244 | 1047 |
| LMArena Multi-Turn | 1257 | 1050 |
| EQ-Bench Creative Writing | 752 | — |

## FAQ

### Is GPT-4 better than Llama 2-13B?

GPT-4 and Llama 2-13B score almost the same on the Noometry Index (28.9 vs 29.1), so choose on price, context window or the category you care about most.

### Is GPT-4 or Llama 2-13B better for coding?

They score almost the same on coding (31.2 vs 30.4); test both on your own repository before choosing.

### How many benchmarks do GPT-4 and Llama 2-13B share?

26 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and Llama 2-13B has 32.