Model comparison
Falcon-180B vs GPT-3.5-turbo
Falcon-180B is the stronger model overall, scoring 32.2 to 23.2 on the Noometry Index.
Last verified . 13 shared benchmarks.
Technology Innovation InstituteSummary
- They share 13 benchmarks with published results for both. Falcon-180B scores higher in 2 categories and GPT-3.5-turbo in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where GPT-3.5-turbo leads 31.5 to 25.2.
- Falcon-180B has downloadable open weights; the other is API-only.
Side by side
| Falcon-180B | GPT-3.5-turbo | |
|---|---|---|
| Provider | Technology Innovation Institute | OpenAI |
| Noometry Index | 32.2 | 23.2 |
| Released | 2023-09-06 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | — | 16K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $1.50 |
| Results tracked | 16 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, GPT-3.5-turbo: 23.9 (#331)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| WeirdML | — | 3.5% |
| BigCodeBench Instruct | — | 39.1% |
| LMArena Coding | — | 1136 |
| BigCodeBench Complete | — | 50.6% |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
Falcon-180B: —, GPT-3.5-turbo: —
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| METR Time Horizons | — | 21.5% |
Reasoning Falcon-180B leads
Falcon-180B: 19.1 (#269), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1108 |
| Epoch Capabilities Index | 112.13 | 118.55 |
| WinoGrande | 87.1% | 81.6% |
| Chess Puzzles | — | 0% |
| Mystery Game Puzzles | — | 3% |
| DTBench | — | 48.5% |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
Math Not comparable
Falcon-180B: —, GPT-3.5-turbo: 6.3 (#327)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| GSM8K | 54.4% | 57.8% |
| FrontierMath (Tiers 1-3) | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 2.2% |
| LMArena Math | — | 1142 |
| MATH Level 5 | — | 15.9% |
Knowledge Not comparable
Falcon-180B: —, GPT-3.5-turbo: 10.0 (#303)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 87.4% |
| BoolQ | 89% | 87% |
| MMLU | 70.6% | 71.4% |
| OpenBookQA | 64.2% | 86% |
| GPQA Diamond | — | 28% |
| LMArena Expert | — | 1070 |
| TriviaQA | — | 85.8% |
Multilingual GPT-3.5-turbo leads
Falcon-180B: 25.2 (#286), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1000 | 1108 |
| LMArena Chinese | — | 1075 |
| LMArena French | — | 1118 |
| LMArena German | — | 1090 |
| LMArena Japanese | — | 1043 |
| LMArena Korean | — | 1019 |
| LMArena Russian | — | 1123 |
| LMArena Spanish | — | 1121 |
Instruction Following GPT-3.5-turbo leads
Falcon-180B: 53.4 (#286), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1047 | 1119 |
Long Context Not comparable
Falcon-180B: —, GPT-3.5-turbo: 34.0 (#254)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | — | 1121 |
Writing & Preference Falcon-180B leads
Falcon-180B: 29.1 (#295), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | Falcon-180B | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1054 | 1125 |
| LMArena Creative Writing | 1089 | 1092 |
| LMArena Multi-Turn | 1013 | 1117 |
| EQ-Bench Creative Writing | — | 451 |
Frequently asked questions
Is Falcon-180B better than GPT-3.5-turbo?
Falcon-180B is the stronger model overall, scoring 32.2 to 23.2 on the Noometry Index.
How many benchmarks do Falcon-180B and GPT-3.5-turbo share?
13 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and GPT-3.5-turbo has 44.