# Falcon-180B vs GPT-4

> Falcon-180B is the stronger model overall, scoring 31.8 to 28.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/falcon-180b-vs-gpt-4
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Falcon-180B scores higher in 1 category and GPT-4 in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-4 leads 40.8 to 25.3.
- Falcon-180B has downloadable open weights; the other is API-only.

## Snapshot

| | Falcon-180B | GPT-4 |
|---|---|---|
| Provider | Technology Innovation Institute | OpenAI |
| Noometry Index | 31.8 | 28.9 |
| Rank | 254 | 308 |
| Context | — | 8K |
| Input $/M | — | $30 |
| Output $/M | — | $60 |
| Weights | Open | Proprietary |

## Coding

- Falcon-180B: —
- GPT-4: 31.2 (#277)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| WeirdML | — | 12.4% |
| BigCodeBench Instruct | — | 46% |
| LMArena Coding | — | 1254 |
| BigCodeBench Complete | — | 57.2% |
| HumanEval+ | — | 79.3% |

## Agentic & Tool Use

- Falcon-180B: —
- GPT-4: —

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| METR Time Horizons | — | 36.1% |

## Reasoning

- Falcon-180B: 18.3 (#266)
- GPT-4: 17.3 (#285)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1241 |
| Epoch Capabilities Index | 111.89 | 125.88 |
| HellaSwag | 89% | 95.3% |
| WinoGrande | 87.1% | 87.5% |
| Chess Puzzles | — | 4% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 62.7% |
| LMCA | — | 17.1% |
| BIG-Bench Hard | — | 75.1% |
| ForecastBench | — | 57.8 |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |

## Math

- Falcon-180B: —
- GPT-4: 10.1 (#304)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| GSM8K | 54.4% | 92% |
| OTIS Mock AIME 2024-2025 | — | 1.1% |
| LMArena Math | — | 1269 |
| MATH Level 5 | — | 23% |

## Knowledge

- Falcon-180B: —
- GPT-4: 18.4 (#277)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| MMLU | 70.6% | 86.4% |
| GPQA Diamond | — | 35.7% |
| LMArena Expert | — | 1211 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
| TriviaQA | — | 84.8% |

## Multilingual

- Falcon-180B: 25.3 (#281)
- GPT-4: 40.8 (#210)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| LMArena Non-English | 1000 | 1246 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1282 |
| LMArena German | — | 1251 |
| LMArena Japanese | — | 1209 |
| LMArena Korean | — | 1184 |
| LMArena Russian | — | 1251 |
| LMArena Spanish | — | 1261 |

## Instruction Following

- Falcon-180B: 53.6 (#281)
- GPT-4: 65.5 (#217)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| LMArena Instruction Following | 1047 | 1241 |

## Long Context

- Falcon-180B: —
- GPT-4: 37.7 (#207)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| LMArena Longer Query | — | 1244 |

## Writing & Preference

- Falcon-180B: 29.3 (#290)
- GPT-4: 35.0 (#263)

| Benchmark | Falcon-180B | GPT-4 |
|---|---|---|
| LMArena Text | 1054 | 1263 |
| LMArena Creative Writing | 1089 | 1244 |
| LMArena Multi-Turn | 1013 | 1257 |
| EQ-Bench Creative Writing | — | 752 |

## FAQ

### Is Falcon-180B better than GPT-4?

Falcon-180B is the stronger model overall, scoring 31.8 to 28.9 on the Noometry Index.

### How many benchmarks do Falcon-180B and GPT-4 share?

11 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and GPT-4 has 38.