Model comparison
Falcon-40B vs Llama 3.1-405B
Llama 3.1-405B has enough public results to be ranked (#288); Falcon-40B does not yet, so treat this comparison as directional.
Last verified . 8 shared benchmarks.
Technology Innovation Institute
MetaSummary
- They share 8 benchmarks with published results for both.
Side by side
| Falcon-40B | Llama 3.1-405B | |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | — | 30.7 |
| Released | 2023-03-15 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 42 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-40B: —, Llama 3.1-405B: 33.1 (#262)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| WeirdML | — | 21.4% |
| LMArena Coding | — | 1291 |
Agentic & Tool Use Not comparable
Falcon-40B: —, Llama 3.1-405B: 21.0 (#140)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| TheAgentCompany | — | 7.4% |
| Cybench | — | 7.5% |
Reasoning Not comparable
Falcon-40B: —, Llama 3.1-405B: 16.8 (#300)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| BIG-Bench Hard | 37.1% | 82.9% |
| Epoch Capabilities Index | 104.45 | 128.75 |
| HellaSwag | 85.3% | 89.2% |
| PIQA | 83% | 85.9% |
| WinoGrande | 76.9% | 89.2% |
| SimpleBench | — | 23% |
| Kagi LLM Benchmark | — | 45% |
| LMArena Hard Prompts | — | 1269 |
| DTBench | — | 61.4% |
| ForecastBench | — | 59.9 |
| LAMBADA | 77.3% | — |
Math Not comparable
Falcon-40B: —, Llama 3.1-405B: 18.4 (#290)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 9.7% |
| Omni-MATH | — | 24.9% |
| LMArena Math | — | 1281 |
| MATH Level 5 | — | 49.8% |
| GSM8K | 33.8% | — |
Knowledge Not comparable
Falcon-40B: —, Llama 3.1-405B: 30.4 (#227)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| ARC (AI2) Challenge | 61.9% | 95.3% |
| MMLU | 56.9% | 84.5% |
| TriviaQA | 79.9% | 82.7% |
| GPQA Diamond | — | 50.9% |
| MMLU-Pro | — | 72.3% |
| Confabulations | — | 17.6% |
| GPQA (HELM) | — | 52.2% |
| LMArena Expert | — | 1243 |
| BoolQ | 83.1% | — |
| OpenBookQA | 56.6% | — |
Multilingual Not comparable
Falcon-40B: —, Llama 3.1-405B: 40.7 (#214)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| LMArena Non-English | — | 1248 |
| LMArena Chinese | — | 1242 |
| LMArena French | — | 1279 |
| LMArena German | — | 1252 |
| LMArena Japanese | — | 1208 |
| LMArena Korean | — | 1184 |
| LMArena Russian | — | 1265 |
| LMArena Spanish | — | 1260 |
Instruction Following Not comparable
Falcon-40B: —, Llama 3.1-405B: 65.9 (#214)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| IFEval | — | 81.1% |
| LMArena Instruction Following | — | 1259 |
Long Context Not comparable
Falcon-40B: —, Llama 3.1-405B: 38.4 (#197)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| LMArena Longer Query | — | 1266 |
Writing & Preference Not comparable
Falcon-40B: —, Llama 3.1-405B: 38.9 (#251)
| Benchmark | Falcon-40B | Llama 3.1-405B |
|---|---|---|
| LMArena Text | — | 1284 |
| LMArena Creative Writing | — | 1262 |
| EQ-Bench Creative Writing | — | 870 |
| WildBench | — | 78.3% |
| LMArena Multi-Turn | — | 1297 |
Frequently asked questions
Is Falcon-40B better than Llama 3.1-405B?
Llama 3.1-405B has enough public results to be ranked (#288); Falcon-40B does not yet, so treat this comparison as directional.
How many benchmarks do Falcon-40B and Llama 3.1-405B share?
8 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and Llama 3.1-405B has 42.