Model comparison
Falcon-180B vs GPT-4 Turbo
Falcon-180B is the stronger model overall, scoring 32.2 to 30.5 on the Noometry Index.
Last verified . 8 shared benchmarks.
Technology Innovation InstituteSummary
- They share 8 benchmarks with published results for both. Falcon-180B scores higher in 1 category and GPT-4 Turbo in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-4 Turbo leads 47.7 to 29.1.
- Falcon-180B has downloadable open weights; the other is API-only.
Side by side
| Falcon-180B | GPT-4 Turbo | |
|---|---|---|
| Provider | Technology Innovation Institute | OpenAI |
| Noometry Index | 32.2 | 30.5 |
| Released | 2023-09-06 | 2023-11-06 |
| Weights | Open | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $10 |
| Output $ / M tokens | — | $30 |
| Results tracked | 16 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, GPT-4 Turbo: 33.8 (#249)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| WeirdML | — | 18% |
| BigCodeBench Instruct | — | 48.2% |
| LMArena Coding | — | 1268 |
| BigCodeBench Complete | — | 58.2% |
| HumanEval+ | — | 86.6% |
| MBPP+ | — | 73.3% |
Agentic & Tool Use Not comparable
Falcon-180B: —, GPT-4 Turbo: —
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| METR Time Horizons | — | 36.7% |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), GPT-4 Turbo: 15.3 (#317)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1251 |
| Epoch Capabilities Index | 112.13 | 127.25 |
| SimpleBench | — | 25.1% |
| Chess Puzzles | — | 6% |
| DTBench | — | 61.6% |
| LMCA | — | 9.8% |
| ForecastBench | — | 59.4 |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
| WinoGrande | 87.1% | — |
Math Not comparable
Falcon-180B: —, GPT-4 Turbo: 9.0 (#322)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 0.7% |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| LMArena Math | — | 1272 |
| MATH Level 5 | — | 46.7% |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, GPT-4 Turbo: 24.3 (#268)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| MMLU | 70.6% | 81.3% |
| GPQA Diamond | — | 46.6% |
| Confabulations | — | 28.4% |
| LMArena Expert | — | 1223 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multimodal Not comparable
Falcon-180B: —, GPT-4 Turbo: 30.6 (#110)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| LMArena Vision | — | 1090 |
Multilingual GPT-4 Turbo leads
Falcon-180B: 25.2 (#286), GPT-4 Turbo: 40.5 (#216)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| LMArena Non-English | 1000 | 1245 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1276 |
| LMArena German | — | 1259 |
| LMArena Japanese | — | 1194 |
| LMArena Korean | — | 1187 |
| LMArena Russian | — | 1259 |
| LMArena Spanish | — | 1260 |
Instruction Following GPT-4 Turbo leads
Falcon-180B: 53.4 (#286), GPT-4 Turbo: 65.8 (#216)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| LMArena Instruction Following | 1047 | 1249 |
Long Context Not comparable
Falcon-180B: —, GPT-4 Turbo: 38.0 (#206)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| LMArena Longer Query | — | 1254 |
Writing & Preference GPT-4 Turbo leads
Falcon-180B: 29.1 (#295), GPT-4 Turbo: 47.7 (#206)
| Benchmark | Falcon-180B | GPT-4 Turbo |
|---|---|---|
| LMArena Text | 1054 | 1272 |
| LMArena Creative Writing | 1089 | 1269 |
| LMArena Multi-Turn | 1013 | 1267 |
Frequently asked questions
Is Falcon-180B better than GPT-4 Turbo?
Falcon-180B is the stronger model overall, scoring 32.2 to 30.5 on the Noometry Index.
How many benchmarks do Falcon-180B and GPT-4 Turbo share?
8 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and GPT-4 Turbo has 36.