Model comparison
Falcon-180B vs Llama 3.1-70B
Falcon-180B is the stronger model overall, scoring 32.2 to 29.6 on the Noometry Index.
Last verified . 8 shared benchmarks.
Technology Innovation Institute
MetaSummary
- They share 8 benchmarks with published results for both. Falcon-180B scores higher in 0 categories and Llama 3.1-70B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama 3.1-70B leads 38.8 to 25.2.
Side by side
| Falcon-180B | Llama 3.1-70B | |
|---|---|---|
| Provider | Technology Innovation Institute | Meta |
| Noometry Index | 32.2 | 29.6 |
| Released | 2023-09-06 | 2024-07-23 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $0.40 |
| Results tracked | 16 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Llama 3.1-70B: 30.3 (#296)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| WeirdML | — | 9% |
| BigCodeBench Instruct | — | 46.1% |
| LMArena Coding | — | 1260 |
| BigCodeBench Complete | — | 54.8% |
Agentic & Tool Use Not comparable
Falcon-180B: —, Llama 3.1-70B: 25.1 (#112)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| TheAgentCompany | — | 6.9% |
| BALROG | — | 27.9% |
Reasoning Llama 3.1-70B leads
Falcon-180B: 19.1 (#269), Llama 3.1-70B: 21.6 (#220)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1241 |
| Epoch Capabilities Index | 112.13 | 125.92 |
| DTBench | — | 60% |
| LMCA | — | 14.8% |
| HellaSwag | 89% | — |
| LAMBADA | 79.8% | — |
| PIQA | 84.9% | — |
| WinoGrande | 87.1% | — |
Math Not comparable
Falcon-180B: —, Llama 3.1-70B: 13.5 (#304)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 3.6% |
| Omni-MATH | — | 21% |
| LMArena Math | — | 1252 |
| MATH Level 5 | — | 36.7% |
| GSM8K | 54.4% | — |
Knowledge Not comparable
Falcon-180B: —, Llama 3.1-70B: 24.2 (#269)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| MMLU | 70.6% | 80.1% |
| GPQA Diamond | — | 44.2% |
| MMLU-Pro | — | 65.3% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1209 |
| ARC (AI2) Challenge | 67.8% | — |
| BoolQ | 89% | — |
| OpenBookQA | 64.2% | — |
Multilingual Llama 3.1-70B leads
Falcon-180B: 25.2 (#286), Llama 3.1-70B: 38.8 (#225)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| LMArena Non-English | 1000 | 1219 |
| LMArena Chinese | — | 1215 |
| LMArena French | — | 1261 |
| LMArena German | — | 1222 |
| LMArena Japanese | — | 1132 |
| LMArena Korean | — | 1140 |
| LMArena Russian | — | 1234 |
| LMArena Spanish | — | 1253 |
Instruction Following Llama 3.1-70B leads
Falcon-180B: 53.4 (#286), Llama 3.1-70B: 65.3 (#223)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1231 |
| IFEval | — | 82.1% |
Long Context Not comparable
Falcon-180B: —, Llama 3.1-70B: 37.6 (#214)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| LMArena Longer Query | — | 1241 |
Writing & Preference Llama 3.1-70B leads
Falcon-180B: 29.1 (#295), Llama 3.1-70B: 35.4 (#267)
| Benchmark | Falcon-180B | Llama 3.1-70B |
|---|---|---|
| LMArena Text | 1054 | 1261 |
| LMArena Creative Writing | 1089 | 1232 |
| LMArena Multi-Turn | 1013 | 1256 |
| EQ-Bench Creative Writing | — | 784 |
| WildBench | — | 75.8% |
Frequently asked questions
Is Falcon-180B better than Llama 3.1-70B?
Falcon-180B is the stronger model overall, scoring 32.2 to 29.6 on the Noometry Index.
How many benchmarks do Falcon-180B and Llama 3.1-70B share?
8 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Llama 3.1-70B has 35.