Google, open weights
Gemma 2 9B
Gemma 2 9B by Google ranks 341st of 354 ranked models on the Noometry Index as of October 2026, with a score of 25.9. Its strongest category is long context, where it ranks 233rd.
Last verified
Specifications
- Noometry rank
- #341 of 354
- Index score
- 25.9
- Evidence
- Confirmed 35 results
- Provider
Google- Released
- June 24, 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 15.9
- Math 9.9
- Knowledge 9.7
- Multilingual 36.6
- Instruction Following 57.6
- Long Context 36.3
- Writing & Preference 32.1
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 29.4 | #304 | 4 |
| Reasoning | 15.9 | #309 | 3 |
| Math | 9.9 | #318 | 4 |
| Knowledge | 9.7 | #305 | 2 |
| Multilingual | 36.6 | #238 | 1 |
| Instruction Following | 57.6 | #269 | 2 |
| Long Context | 36.3 | #233 | 1 |
| Writing & Preference | 32.1 | #281 | 5 |
Strengths and weaknesses
Categories where Gemma 2 9B places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Long Context | 36.3 | −4.7 | #233 of 296, top 79% |
| Multilingual | 36.6 | −10.8 | #238 of 297, top 81% |
| Instruction Following | 57.6 | −13.7 | #269 of 305, top 89% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Math | 9.9 | −26.6 | #318 of 327, top 98% |
| Knowledge | 9.7 | −27.6 | #305 of 314, top 98% |
| Writing & Preference | 32.1 | −21.6 | #281 of 312, top 91% |
Closest competitors
The models ranked just above and below Gemma 2 9B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Mistral Nemo | #337 | 26.4 | $0.15 | — | Compare |
| Ministral 3B | #338 | 26.2 | $0.10 | — | Compare |
| DeepSeek-R1-Distill-Qwen-1.5B | #339 | 26.1 | — | — | Compare |
| Claude 3 Haiku | #340 | 25.9 | — | 41 | Compare |
| Dolly 2.0-12b | #342 | 25.5 | — | — | Compare |
| GPT-4o mini | #343 | 25.5 | $0.26 | 120 | Compare |
| Llama 3-8B | #344 | 25.5 | — | — | Compare |
| Claude 2.1 | #345 | 25.2 | — | — | 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 |
|---|---|---|---|---|---|
| BigCodeBench Instruct | 34.7% | #47 of 64, top 74% | BigCodeBench | 2024-06-19 | |
| LiveBench Coding | 22.5% | #33 of 39, top 85% | Epoch AI | ||
| LMArena Coding | 1173 | #249 of 294, top 85% | LMArena | 2026-10-08 | |
| BigCodeBench Complete | 40.6% | #50 of 66, top 76% | BigCodeBench | 2024-06-19 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Reasoning | 15.2% | #39 of 39, top 100% | Epoch AI | ||
| LMArena Hard Prompts | 1171 | #248 of 297, top 84% | LMArena | 2026-10-08 | |
| LiveBench Data Analysis | 36.4% | #34 of 39, top 88% | Epoch AI | ||
| Epoch Capabilities Index | 119.83 | #169 of 213, top 80% | Epoch AI | 2024-06-24 | |
| LiveBench | 28.7% | #35 of 39, top 90% | Epoch AI | ||
| PIQA | 83.7% | #8 of 27, top 30% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.6% | #170 of 173, top 99% | Epoch AI | 2025-03-07 | |
| LiveBench Math | 19.8% | #35 of 39, top 90% | Epoch AI | ||
| LMArena Math | 1183 | #239 of 285, top 84% | LMArena | 2026-10-08 | |
| MATH Level 5 | 21% | #63 of 79, top 80% | Epoch AI | 2025-01-27 | |
| GSM8K | 84.9% | #9 of 38, top 24% | Epoch AI |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 27.5% | #175 of 186, top 95% | Epoch AI | 2025-01-27 | |
| LMArena Expert | 1147 | #237 of 273, top 87% | LMArena | 2026-10-08 | |
| BoolQ | 85.7% | #8 of 23, top 35% | Epoch AI | ||
| MMLU | 72.1% | #40 of 81, top 50% | Epoch AI |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1188 | #238 of 297, top 81% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1185 | #238 of 285, top 84% | LMArena | 2026-10-08 | |
| LMArena French | 1190 | #195 of 223, top 88% | LMArena | 2026-10-08 | |
| LMArena German | 1186 | #196 of 231, top 85% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1144 | #177 of 211, top 84% | LMArena | 2026-10-08 | |
| LMArena Korean | 1137 | #185 of 213, top 87% | LMArena | 2026-10-08 | |
| LMArena Russian | 1200 | #234 of 283, top 83% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1200 | #194 of 226, top 86% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Instruction Following | 52.6% | #36 of 39, top 93% | Epoch AI | ||
| LMArena Instruction Following | 1178 | #244 of 298, top 82% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1197 | #242 of 291, top 84% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1207 | #242 of 297, top 82% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1206 | #229 of 295, top 78% | LMArena | 2026-10-08 | |
| EQ-Bench Creative Writing | 841 | #103 of 115, top 90% | EQ-Bench | ||
| LMArena Multi-Turn | 1193 | #239 of 295, top 82% | LMArena | 2026-10-08 | |
| LiveBench Language | 25.5% | #32 of 39, top 83% | Epoch AI |
Compare Gemma 2 9B
- Gemma 2 9B vs Gemma 7B
- Gemma 2 9B vs Claude 3 Haiku
- Gemma 2 9B vs Dolly 2.0-12b
- Gemma 2 9B vs DeepSeek-R1-Distill-Qwen-1.5B
- Gemma 2 9B vs GPT-4o mini
- Gemma 2 9B vs Ministral 3B
- Gemma 2 9B vs Llama 3-8B
- Gemma 2 9B vs GPT-6 Astra
- Gemma 2 9B vs Claude Fable 5.1
- Gemma 2 9B vs Kimi K3
- Gemma 2 9B vs Grok 4.6
- Gemma 2 9B vs Qwen3.8 Max
- Gemma 2 9B vs GLM-5.3
- Gemma 2 9B vs Muse Spark 1.3
Other Google models
Frequently asked questions
How good is Gemma 2 9B?
Gemma 2 9B by Google ranks 341st of 354 ranked models on the Noometry Index as of October 2026, with a score of 25.9. Its strongest category is long context, where it ranks 233rd.
Is Gemma 2 9B open source?
Yes. Gemma 2 9B's weights are downloadable; check the license for commercial terms.
What are Gemma 2 9B's strengths and weaknesses?
Relative to other ranked models, Gemma 2 9B places best in long context, multilingual, instruction following and lowest in math, knowledge, writing & preference.
What is Gemma 2 9B best at?
Its best category is long context, where it ranks 233rd on Noometry.