Model comparison
Falcon-40B vs GPT-3.5-turbo
GPT-3.5-turbo has enough public results to be ranked (#345); Falcon-40B does not yet, so treat this comparison as directional.
Last verified . 9 shared benchmarks.
Technology Innovation InstituteSummary
- They share 9 benchmarks with published results for both.
- Falcon-40B has downloadable open weights; the other is API-only.
Side by side
| Falcon-40B | GPT-3.5-turbo | |
|---|---|---|
| Provider | Technology Innovation Institute | OpenAI |
| Noometry Index | — | 23.1 |
| Released | 2023-03-15 | 2023-03-01 |
| Weights | Open | Proprietary |
| Context window | — | 16K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $1.50 |
| Results tracked | 12 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-40B: —, GPT-3.5-turbo: 23.5 (#326)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| WeirdML | — | 3.5% |
| BigCodeBench Instruct | — | 39.1% |
| LMArena Coding | — | 1137 |
| BigCodeBench Complete | — | 50.6% |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
Falcon-40B: —, GPT-3.5-turbo: —
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| METR Time Horizons | — | 21.5% |
Reasoning Not comparable
Falcon-40B: —, GPT-3.5-turbo: 13.3 (#328)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| BIG-Bench Hard | 37.1% | 61.6% |
| Epoch Capabilities Index | 104.04 | 118.48 |
| WinoGrande | 76.9% | 81.6% |
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | — | 1108 |
| Mystery Game Puzzles | — | 3% |
| DTBench | — | 48.5% |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| HellaSwag | 85.3% | — |
| LAMBADA | 77.3% | — |
| PIQA | 83% | — |
Math Not comparable
Falcon-40B: —, GPT-3.5-turbo: 6.0 (#321)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| GSM8K | 33.8% | 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-40B: —, GPT-3.5-turbo: 10.0 (#298)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| ARC (AI2) Challenge | 61.9% | 87.4% |
| BoolQ | 83.1% | 87% |
| MMLU | 56.9% | 71.4% |
| OpenBookQA | 56.6% | 86% |
| TriviaQA | 79.9% | 85.8% |
| GPQA Diamond | — | 28% |
| LMArena Expert | — | 1070 |
Multilingual Not comparable
Falcon-40B: —, GPT-3.5-turbo: 31.6 (#253)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | — | 1108 |
| LMArena Chinese | — | 1075 |
| LMArena French | — | 1117 |
| LMArena German | — | 1090 |
| LMArena Japanese | — | 1043 |
| LMArena Korean | — | 1019 |
| LMArena Russian | — | 1123 |
| LMArena Spanish | — | 1120 |
Instruction Following Not comparable
Falcon-40B: —, GPT-3.5-turbo: 58.1 (#257)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | — | 1119 |
Long Context Not comparable
Falcon-40B: —, GPT-3.5-turbo: 34.0 (#249)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | — | 1121 |
Writing & Preference Not comparable
Falcon-40B: —, GPT-3.5-turbo: 25.4 (#300)
| Benchmark | Falcon-40B | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | — | 1125 |
| LMArena Creative Writing | — | 1092 |
| EQ-Bench Creative Writing | — | 451 |
| LMArena Multi-Turn | — | 1117 |
Frequently asked questions
Is Falcon-40B better than GPT-3.5-turbo?
GPT-3.5-turbo has enough public results to be ranked (#345); Falcon-40B does not yet, so treat this comparison as directional.
How many benchmarks do Falcon-40B and GPT-3.5-turbo share?
9 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and GPT-3.5-turbo has 44.