Model comparison
Falcon-180B vs Gemma 7B
Falcon-180B is the stronger model overall, scoring 32.2 to 30.0 on the Noometry Index.
Last verified . 15 shared benchmarks.
Technology Innovation Institute
GoogleSummary
- They share 15 benchmarks with published results for both. Falcon-180B scores higher in 3 categories and Gemma 7B in 1 category; 2 gaps are clear of the uncertainty.
Side by side
| Falcon-180B | Gemma 7B | |
|---|---|---|
| Provider | Technology Innovation Institute | |
| Noometry Index | 32.2 | 30.0 |
| Released | 2023-09-06 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 16 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-180B: —, Gemma 7B: 30.5 (#294)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| LMArena Coding | — | 1048 |
| HumanEval+ | — | 28.7% |
| MBPP+ | — | 43.4% |
Reasoning Too close to call
Falcon-180B: 19.1 (#269), Gemma 7B: 19.9 (#249)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| LMArena Hard Prompts | 1007 | 1042 |
| Epoch Capabilities Index | 112.13 | 111.99 |
| HellaSwag | 89% | 82.2% |
| PIQA | 84.9% | 81.2% |
| WinoGrande | 87.1% | 79% |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| LAMBADA | 79.8% | — |
Math Not comparable
Falcon-180B: —, Gemma 7B: 31.2 (#228)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| GSM8K | 54.4% | 46.4% |
| LMArena Math | — | 1066 |
Knowledge Not comparable
Falcon-180B: —, Gemma 7B: 27.3 (#252)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| ARC (AI2) Challenge | 67.8% | 78.3% |
| BoolQ | 89% | 83.2% |
| MMLU | 70.6% | 66.1% |
| OpenBookQA | 64.2% | 78.6% |
| LMArena Expert | — | 1001 |
| TriviaQA | — | 72.3% |
Multilingual Too close to call
Falcon-180B: 25.2 (#286), Gemma 7B: 25.1 (#287)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| LMArena Non-English | 1000 | 999 |
| LMArena Chinese | — | 1035 |
| LMArena French | — | 1025 |
| LMArena Russian | — | 993 |
Instruction Following Falcon-180B leads
Falcon-180B: 53.4 (#286), Gemma 7B: 51.5 (#295)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | 1047 | 1017 |
Long Context Not comparable
Falcon-180B: —, Gemma 7B: 31.1 (#282)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| LMArena Longer Query | — | 1022 |
Writing & Preference Falcon-180B leads
Falcon-180B: 29.1 (#295), Gemma 7B: 27.1 (#302)
| Benchmark | Falcon-180B | Gemma 7B |
|---|---|---|
| LMArena Text | 1054 | 1056 |
| LMArena Creative Writing | 1089 | 1024 |
| LMArena Multi-Turn | 1013 | 963 |
Frequently asked questions
Is Falcon-180B better than Gemma 7B?
Falcon-180B is the stronger model overall, scoring 32.2 to 30.0 on the Noometry Index.
How many benchmarks do Falcon-180B and Gemma 7B share?
15 benchmarks have published results for both models. Falcon-180B has 16 scored results on Noometry and Gemma 7B has 27.