Model comparison
Claude Instant vs Gemma 7B
Gemma 7B has enough public results to be ranked (#299); Claude Instant does not yet, so treat this comparison as directional.
Last verified . 6 shared benchmarks.
GoogleSummary
- They share 6 benchmarks with published results for both. Claude Instant scores higher in 0 categories and Gemma 7B in 1 category, but none of those gaps is larger than the uncertainty.
- Gemma 7B has downloadable open weights; the other is API-only.
Side by side
| Claude Instant | Gemma 7B | |
|---|---|---|
| Provider | Anthropic | |
| Noometry Index | 29.5 | 30.0 |
| Released | 2023-08-09 | 2024-02-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Claude Instant: —, Gemma 7B: 30.5 (#294)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| HumanEval+ | 50.6% | 28.7% |
| LMArena Coding | — | 1048 |
| MBPP+ | — | 43.4% |
Reasoning Too close to call
Claude Instant: 19.6, Gemma 7B: 19.9 (#249)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| Epoch Capabilities Index | 120.28 | 111.99 |
| LMArena Hard Prompts | — | 1042 |
| DTBench | 45.8% | — |
| Adversarial NLI | — | 48.7% |
| BIG-Bench Hard | — | 55.1% |
| HellaSwag | — | 82.2% |
| PIQA | — | 81.2% |
| WinoGrande | — | 79% |
Math Not comparable
Claude Instant: —, Gemma 7B: 31.2 (#228)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| GSM8K | 86.7% | 46.4% |
| LMArena Math | — | 1066 |
Knowledge Not comparable
Claude Instant: —, Gemma 7B: 27.3 (#252)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| ARC (AI2) Challenge | 86.3% | 78.3% |
| MMLU | 73.4% | 66.1% |
| TriviaQA | 78.9% | 72.3% |
| LMArena Expert | — | 1001 |
| BoolQ | — | 83.2% |
| OpenBookQA | — | 78.6% |
Multilingual Not comparable
Claude Instant: —, Gemma 7B: 25.1 (#287)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| LMArena Non-English | — | 999 |
| LMArena Chinese | — | 1035 |
| LMArena French | — | 1025 |
| LMArena Russian | — | 993 |
Instruction Following Not comparable
Claude Instant: —, Gemma 7B: 51.5 (#295)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| LMArena Instruction Following | — | 1017 |
Long Context Not comparable
Claude Instant: —, Gemma 7B: 31.1 (#282)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| LMArena Longer Query | — | 1022 |
Writing & Preference Not comparable
Claude Instant: —, Gemma 7B: 27.1 (#302)
| Benchmark | Claude Instant | Gemma 7B |
|---|---|---|
| LMArena Text | — | 1056 |
| LMArena Creative Writing | — | 1024 |
| LMArena Multi-Turn | — | 963 |
Frequently asked questions
Is Claude Instant better than Gemma 7B?
Gemma 7B has enough public results to be ranked (#299); Claude Instant does not yet, so treat this comparison as directional.
How many benchmarks do Claude Instant and Gemma 7B share?
6 benchmarks have published results for both models. Claude Instant has 7 scored results on Noometry and Gemma 7B has 27.