Gemma 7B
Gemma 7B (Google DeepMind) was released on Feb 21, 2024. In the Epoch AI capability ranking (ECI), it ranks #218 out of 267 models, with 112.05. Against models of the same generation, its best result is on WinoGrande: 79.0%, #9 of 35.
Where Gemma 7B stands out and where it falls behind, by the numbers
Gemma 7B has published results on 11 tests compiled by Epoch AI. The yardstick here is its generation: its position among the models released between May 27, 2023 and May 21, 2024 that took the same test. Against the whole archive, which includes 2023 models, a recent release lands near the top of almost everything, and that says nothing.
Where it stands out
Tests where it sits in the top third of its own generation.
Where it falls behind
Tests where it sits in the bottom half of its own generation.
See all 11 tests, one by one
| Test | Score | In its generation | Overall | Test record |
|---|---|---|---|---|
| MMLU | 66.1% | #26 / 53 | #50 / 92 | 88.1% GPT-4o (May 2024) |
| ARC (AI2) | 78.3% | #13 / 40 (tied with 1) | #16 / 65 | 95.3% DeepSeek-V3 (Mar 2025) |
| WinoGrande | 79.0% | #9 / 35 | #16 / 61 | 89.2% Llama 3.1-405B |
| GSM8K | 46.4% | #15 / 33 | #27 / 54 | 92.0% GPT-4 (Mar 2023) |
| HellaSwag | 82.2% | #9 / 26 | #19 / 51 | 95.3% GPT-4 (Mar 2023) |
| PIQA | 81.2% | #10 / 23 | #20 / 43 | 88.7% GPT-4o mini |
| BoolQ | 83.2% | #10 / 22 | #19 / 42 | 90.9% PaLM 2-L |
| BIG-Bench Hard | 55.1% | #13 / 27 | #19 / 41 | 89.2% Gemini 1.5 Pro (Sept 2024) |
| OpenBookQA | 78.6% | #8 / 18 | #8 / 32 | 88.0% phi-3-mini 3.8B |
| TriviaQA | 72.3% | #13 / 18 | #23 / 32 | 87.6% Llama 2-70B |
| Adversarial Nli | 48.7% | #7 / 9 | #7 / 9 | 58.1% GPT-3.5 Turbo (Nov 2023) |
For each test, the model's best effort level counts, as in the ranking. Source of the scores: Epoch AI, under CC BY 4.0.
What to compare Gemma 7B with
The models from other labs closest in capability and released in the same period, at most two per lab. Click any of them to see its page.
| Model | Lab | ECI | ELO | LiveBench | Release |
|---|---|---|---|---|---|
| Qwen2.5-Coder (7B) | Alibaba | 113.20 | n/a | n/a | Sep 18, 2024 |
| Qwen-14B | Alibaba | 113.09 | n/a | n/a | Sep 24, 2023 |
| Mistral 7B v0.1 | Mistral AI | 112.27 | n/a | n/a | Sep 27, 2023 |
| Falcon-180B | Technology Innovation Institute | 112.19 | n/a | n/a | Sep 6, 2023 |
| internlm-20b | 112.15 | n/a | n/a | Sep 18, 2023 | |
| Gemma 7B | Google DeepMind | 112.05 | n/a | n/a | Feb 21, 2024 |
| Mistral 7B | Mistral AI | 111.99 | n/a | n/a | Sep 27, 2023 |
Gemma 7B or internlm-20b?
internlm-20b is the model from another lab closest to Gemma 7B in capability. Across the 6 tests both took, this is the score:
| Test | Gemma 7B | internlm-20b |
|---|---|---|
| GSM8K | 46.4% | 62.9% |
| HellaSwag | 82.2% | 78.1% |
| BoolQ | 83.2% | 87.5% |
| BIG-Bench Hard | 55.1% | 52.5% |
| ARC (AI2) | 78.3% | 81.7% |
| PIQA | 81.2% | 80.3% |
Unweighted score: each test counts one point, whether math or coding. The dot marks who did better on each row.
Other models from Google DeepMind
The models from the same lab closest in time, newest first.
| Model | Release | ECI | ELO | LiveBench | Access |
|---|---|---|---|---|---|
| Gemini 2.0 Flash Thinking Exp | Jan 21, 2025 | 135.39 | n/a | n/a | API access |
| Gemini 2.0 Flash Thinking (Jan 2025) | Jan 21, 2025 | 135.36 | n/a | n/a | API access |
| Gemini 1.5 Pro (Sept 2024) | Sep 24, 2024 | 131.73 | n/a | n/a | API access |
| Gemini 1.5 Flash (Sep 2024) | Sep 24, 2024 | 129.37 | n/a | n/a | API access |
| Gemma 2 27B | Jun 24, 2024 | 122.10 | n/a | n/a | Open weights (restricted use) |
| Gemma 2 9B | Jun 24, 2024 | 119.85 | n/a | n/a | Open weights (restricted use) |
| Gemma 7B | Feb 21, 2024 | 112.05 | n/a | n/a | Open weights (restricted use) |
| Gemma 2B | Feb 21, 2024 | 94.34 | n/a | n/a | Open weights (restricted use) |
| Gemini 1.0 Pro | Dec 13, 2023 | 117.07 | n/a | n/a | API access |
Have you used Gemma 7B? Rate it
Users' opinion, not measurement: the rating is kept apart from the ranking and does not move anyone's position. One vote per browser, no sign-up, and you can change your rating later.
What people ask about Gemma 7B
Where does Gemma 7B rank among AI models?
In the ROO3 AI Benchmark, ordered by the Epoch AI ECI, Gemma 7B ranks #218 out of 267 models, with an ECI of 112.05. The ECI is a composite index that combines several hard benchmarks into a single scale. The position changes when a new model comes out, and the page is refreshed six times a day.
Is Gemma 7B better than internlm-20b?
Across the 6 tests both models took and Epoch AI compiled, Gemma 7B comes out ahead on 3, behind on 3 and tied on 0. It is a test-by-test count with no weighting: a win in math counts the same as a win in coding. To choose between the two, look at the tests that resemble your own use.
What is Gemma 7B best at?
Against models of the same generation (released up to 9 months before and up to 3 months after it), the best relative results of Gemma 7B are: WinoGrande (#9 of 35); HellaSwag (#9 of 26); ARC (AI2) (#13 of 40). The yardstick is its position among the models of that period that took the same test.
Where do the numbers on this page come from?
From the same three sources as the ranking, all openly licensed: Epoch AI (ECI and individual tests, CC BY 4.0), Arena (human-preference ELO, CC BY 4.0) and LiveBench (overall average, CC BY-SA 4.0). ROO3 does not measure any model. When the page shows a figure published by the maker itself, it appears in the written analysis, labeled as the maker's, and never enters the ranking.
Where each number comes from
Epoch AI, "AI Benchmarking Hub". Published at epoch.ai. Data under the CC BY 4.0 licence, reordered by roo3.co.
The Arena (LMArena) leaderboard, from the public lmarena-ai/leaderboard-dataset on Hugging Face, under the CC BY 4.0 licence. We are not affiliated with the Arena.
LiveBench, by the LiveBench team, published at livebench.ai under the CC BY-SA 4.0 license. The overall average is recomputed by roo3.co with the same formula as the website (average of the categories), and those numbers stay under CC BY-SA 4.0. We are not affiliated with LiveBench.
← See the full ranking