Google, open weights
Gemma 2B
Gemma 2B by Google ranks 307th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.6. Its strongest category is math, where it ranks 239th.
Last verified
Specifications
- Noometry rank
- #307 of 354
- Index score
- 29.6
- Evidence
- Confirmed 23 results
- Provider
Google- Released
- February 21, 2024
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- —
- Max output
- —
- Input price
- Not listed
- Output price
- Not listed
- Blended price
- Not listed
- Output speed
- Not measured
- Value
- Not ranked
- Knowledge cutoff
- Unknown
Category scores
Each category score combines every public result we have in that category.
- Coding 29.4
- Reasoning 18.8
- Math 30.0
- Multilingual 23.0
- Instruction Following 48.5
- Long Context 29.9
- Writing & Preference 24.0
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 29.4 | #305 | 1 |
| Reasoning | 18.8 | #275 | 1 |
| Math | 30.0 | #239 | 1 |
| Multilingual | 23.0 | #294 | 1 |
| Instruction Following | 48.5 | #302 | 1 |
| Long Context | 29.9 | #291 | 1 |
| Writing & Preference | 24.0 | #308 | 3 |
Strengths and weaknesses
Categories where Gemma 2B places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Instruction Following | 48.5 | −22.8 | #302 of 305, top 100% |
| Multilingual | 23.0 | −24.4 | #294 of 297, top 99% |
| Writing & Preference | 24.0 | −29.8 | #308 of 312, top 99% |
Closest competitors
The models ranked just above and below Gemma 2B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Mistral | #303 | 29.9 | — | — | Compare |
| OLMo 2 Furious 13B | #304 | 29.7 | — | — | Compare |
| Phi 3 Mini 128k Instruct | #305 | 29.7 | — | — | Compare |
| phi-3-medium 14B | #306 | 29.7 | — | — | Compare |
| Llama 3.1-70B | #308 | 29.6 | $0.40 | — | Compare |
| Llama 2-13B | #309 | 29.6 | — | — | Compare |
| Claude 3 Opus | #310 | 29.5 | — | — | Compare |
| DBRX | #311 | 29.4 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 1010 | #289 of 294, top 99% | LMArena | 2026-10-08 | |
| HumanEval+ | 20.7% | #44 of 45, top 98% | EvalPlus | ||
| HumanEval+ | 15.2% | EvalPlus | |||
| MBPP+ | 34.1% | #37 of 38, top 98% | EvalPlus |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 989 | #294 of 297, top 99% | LMArena | 2026-10-08 | |
| BIG-Bench Hard | 35.2% | #25 of 27, top 93% | Epoch AI | ||
| Epoch Capabilities Index | 94.2 | #207 of 213, top 98% | Epoch AI | 2024-02-21 | |
| HellaSwag | 71.4% | #26 of 29, top 90% | Epoch AI | ||
| PIQA | 77.3% | #26 of 27, top 97% | Epoch AI | ||
| WinoGrande | 65.4% | #35 of 43, top 82% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1009 | #283 of 285, top 100% | LMArena | 2026-10-08 | |
| GSM8K | 17.7% | #35 of 38, top 93% | Epoch AI |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ARC (AI2) Challenge | 42.1% | #34 of 39, top 88% | Epoch AI | ||
| BoolQ | 69.4% | #22 of 23, top 96% | Epoch AI | ||
| MMLU | 42.3% | #73 of 81, top 91% | Epoch AI | ||
| TriviaQA | 53.2% | #24 of 25, top 96% | Epoch AI |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 958 | #294 of 297, top 99% | LMArena | 2026-10-08 | |
| LMArena Chinese | 986 | #280 of 285, top 99% | LMArena | 2026-10-08 | |
| LMArena Russian | 937 | #283 of 283, top 100% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 970 | #296 of 298, top 100% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 981 | #291 of 291, top 100% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1002 | #294 of 297, top 99% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 987 | #292 of 295, top 99% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 945 | #293 of 295, top 100% | LMArena | 2026-10-08 |
Compare Gemma 2B
- Gemma 2B vs phi-3-medium 14B
- Gemma 2B vs Llama 3.1-70B
- Gemma 2B vs Phi 3 Mini 128k Instruct
- Gemma 2B vs Llama 2-13B
- Gemma 2B vs OLMo 2 Furious 13B
- Gemma 2B vs Claude 3 Opus
- Gemma 2B vs GPT-6 Astra
- Gemma 2B vs Claude Fable 5.1
- Gemma 2B vs Kimi K3
- Gemma 2B vs Grok 4.6
- Gemma 2B vs Qwen3.8 Max
- Gemma 2B vs GLM-5.3
- Gemma 2B vs Muse Spark 1.3
- Gemma 2B vs DeepSeek V4 Pro
Other Google models
Frequently asked questions
How good is Gemma 2B?
Gemma 2B by Google ranks 307th of 354 ranked models on the Noometry Index as of October 2026, with a score of 29.6. Its strongest category is math, where it ranks 239th.
Is Gemma 2B open source?
Yes. Gemma 2B's weights are downloadable; check the license for commercial terms.
What are Gemma 2B's strengths and weaknesses?
Relative to other ranked models, Gemma 2B places best in math, reasoning, coding and lowest in instruction following, multilingual, writing & preference.
What is Gemma 2B best at?
Its best category is math, where it ranks 239th on Noometry.