# Falcon-180B vs Llama 2-7B

> Falcon-180B is the stronger model overall, scoring 31.8 to 28.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/falcon-180b-vs-llama-2-7b
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Falcon-180B scores higher in 4 categories and Llama 2-7B in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Falcon-180B leads 18.3 to 15.1.

## Snapshot

| | Falcon-180B | Llama 2-7B |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | 31.8 | 28.6 |
| Rank | 254 | 315 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Falcon-180B: —
- Llama 2-7B: 28.7 (#302)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| LMArena Coding | — | 1002 |

## Reasoning

- Falcon-180B: 18.3 (#266)
- Llama 2-7B: 15.1 (#309)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1009 |
| Epoch Capabilities Index | 111.89 | 98.54 |
| HellaSwag | 89% | 77.2% |
| LAMBADA | 79.8% | 73.3% |
| PIQA | 84.9% | 78.8% |
| WinoGrande | 87.1% | 69.2% |
| Chess Puzzles | — | 0% |
| BIG-Bench Hard | — | 39.2% |

## Math

- Falcon-180B: —
- Llama 2-7B: 28.2 (#231)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| GSM8K | 54.4% | 16.7% |
| LMArena Math | — | 1042 |

## Knowledge

- Falcon-180B: —
- Llama 2-7B: 27.7 (#243)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 45.9% |
| BoolQ | 89% | 77.9% |
| MMLU | 70.6% | 45.8% |
| OpenBookQA | 64.2% | 58.6% |
| LMArena Expert | — | 1036 |
| TriviaQA | — | 73.7% |

## Multimodal

- Falcon-180B: —
- Llama 2-7B: —

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| ScienceQA | — | 43.1% |

## Multilingual

- Falcon-180B: 25.3 (#281)
- Llama 2-7B: 23.9 (#288)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1000 | 973 |
| LMArena Chinese | — | 973 |
| LMArena French | — | 969 |
| LMArena German | — | 978 |
| LMArena Russian | — | 995 |
| LMArena Spanish | — | 1007 |

## Instruction Following

- Falcon-180B: 53.6 (#281)
- Llama 2-7B: 51.0 (#293)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1006 |

## Long Context

- Falcon-180B: —
- Llama 2-7B: 30.4 (#282)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | — | 999 |

## Writing & Preference

- Falcon-180B: 29.3 (#290)
- Llama 2-7B: 28.1 (#293)

| Benchmark | Falcon-180B | Llama 2-7B |
|---|---|---|
| LMArena Text | 1054 | 1053 |
| LMArena Creative Writing | 1089 | 1033 |
| LMArena Multi-Turn | 1013 | 1029 |

## FAQ

### Is Falcon-180B better than Llama 2-7B?

Falcon-180B is the stronger model overall, scoring 31.8 to 28.6 on the Noometry Index.

### How many benchmarks do Falcon-180B and Llama 2-7B share?

16 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Llama 2-7B has 29.