Model comparison
Falcon-40B vs Gemma 2B
Gemma 2B has enough public results to be ranked (#305); Falcon-40B does not yet, so treat this comparison as directional.
Last verified . 10 shared benchmarks.
Technology Innovation Institute
GoogleSummary
- They share 10 benchmarks with published results for both.
Side by side
| Falcon-40B | Gemma 2B | |
|---|---|---|
| Provider | Technology Innovation Institute | |
| Noometry Index | — | 29.1 |
| Released | 2023-03-15 | 2024-02-21 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Falcon-40B: —, Gemma 2B: 28.9 (#300)
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| LMArena Coding | — | 1010 |
| HumanEval+ | — | 20.7% |
| MBPP+ | — | 34.1% |
Reasoning Not comparable
Falcon-40B: —, Gemma 2B: 17.9 (#275)
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| BIG-Bench Hard | 37.1% | 35.2% |
| Epoch Capabilities Index | 104.04 | 93.57 |
| HellaSwag | 85.3% | 71.4% |
| PIQA | 83% | 77.3% |
| WinoGrande | 76.9% | 65.4% |
| LMArena Hard Prompts | — | 989 |
| LAMBADA | 77.3% | — |
Math Not comparable
Falcon-40B: —, Gemma 2B: 27.6 (#237)
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| GSM8K | 33.8% | 17.7% |
| LMArena Math | — | 1009 |
Knowledge Not comparable
Falcon-40B: —, Gemma 2B: —
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| ARC (AI2) Challenge | 61.9% | 42.1% |
| BoolQ | 83.1% | 69.4% |
| MMLU | 56.9% | 42.3% |
| TriviaQA | 79.9% | 53.2% |
| OpenBookQA | 56.6% | — |
Multilingual Not comparable
Falcon-40B: —, Gemma 2B: 23.1 (#289)
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| LMArena Non-English | — | 958 |
| LMArena Chinese | — | 986 |
| LMArena Russian | — | 937 |
Instruction Following Not comparable
Falcon-40B: —, Gemma 2B: 48.8 (#297)
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| LMArena Instruction Following | — | 971 |
Long Context Not comparable
Falcon-40B: —, Gemma 2B: 29.9 (#286)
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| LMArena Longer Query | — | 981 |
Writing & Preference Not comparable
Falcon-40B: —, Gemma 2B: 24.1 (#303)
| Benchmark | Falcon-40B | Gemma 2B |
|---|---|---|
| LMArena Text | — | 1002 |
| LMArena Creative Writing | — | 986 |
| LMArena Multi-Turn | — | 945 |
Frequently asked questions
Is Falcon-40B better than Gemma 2B?
Gemma 2B has enough public results to be ranked (#305); Falcon-40B does not yet, so treat this comparison as directional.
How many benchmarks do Falcon-40B and Gemma 2B share?
10 benchmarks have published results for both models. Falcon-40B has 12 scored results on Noometry and Gemma 2B has 23.