Google, open weights
Gemma 4 31B IT
Gemma 4 31B IT by Google ranks 90th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is multimodal, where it ranks 34th. API pricing starts at $0.09 per million input tokens and $0.34 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #90 of 354
- Index score
- 43.5
- Evidence
- Confirmed 35 results
- Provider
Google- Released
- April 2, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 33K
- Input price
- $0.09 / M
- Output price
- $0.34 / M
- Blended price
- $0.15 / M
- Output speed
- 3 tokens/s Kagi
- Value
- #22 of 219
- Knowledge cutoff
- Unknown
- Input
- text, image
- Hugging Face
- google/gemma-4-31B-it
Category scores
Each category score combines every public result we have in that category.
- Coding 42.3
- Reasoning 27.2
- Math 43.2
- Knowledge 37.9
- Multimodal 41.6
- Multilingual 53.8
- Instruction Following 75.5
- Long Context 44.2
- Writing & Preference 60.5
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 42.3 | #108 | 4 |
| Reasoning | 27.2 | #122 | 9 |
| Math | 43.2 | #81 | 2 |
| Knowledge | 37.9 | #151 | 4 |
| Multimodal | 41.6 | #34 | 1 |
| Multilingual | 53.8 | #57 | 1 |
| Instruction Following | 75.5 | #61 | 1 |
| Long Context | 44.2 | #71 | 1 |
| Writing & Preference | 60.5 | #96 | 5 |
Strengths and weaknesses
Categories where Gemma 4 31B IT 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 |
|---|---|---|---|
| Multilingual | 53.8 | +6.4 | #57 of 297, top 20% |
| Instruction Following | 75.5 | +4.2 | #61 of 305, top 20% |
| Long Context | 44.2 | +3.3 | #71 of 296, top 24% |
Closest competitors
The models ranked just above and below Gemma 4 31B IT. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Grok 4.3 | #86 | 43.8 | $1.56 | — | Compare |
| Qwen3 Max | #87 | 43.7 | $2.40 | 48 | Compare |
| MiMo-V2-Omni | #88 | 43.6 | $0.18 | — | Compare |
| Kimi K2.5 Instant | #89 | 43.6 | — | — | Compare |
| Qwen3 235B-A22B | #91 | 43.5 | $1.22 | 85 | Compare |
| Gemma 4 26B A4B IT | #92 | 43.5 | $0.11 | — | Compare |
| MiMo-V2.5 | #93 | 43.4 | $0.18 | — | Compare |
| Kimi K2.7 Code | #94 | 43.3 | $1.71 | — | 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 WebDev | 1366 | #82 of 113, top 73% | LMArena | 2026-10-08 | |
| SciCode | 43.4% | #63 of 121, top 53% | Epoch AI | ||
| WeirdML | 52.3% | #45 of 119, top 38% | Epoch AI | ||
| LMArena Coding | 1459 | #72 of 294, top 25% | LMArena | 2026-10-08 | |
| ALE-Bench | 925.5 | #48 of 105, top 46% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 63.5% | #35 of 99, top 36% | Kagi LLM Benchmark | ||
| NYT Connections (extended) | 15.7% | Lech Mazur benchmarks | |||
| NYT Connections (extended) | 70.6% | #48 of 91, top 53% | Lech Mazur benchmarks | ||
| CritPt | 1.4% | #75 of 134, top 56% | Epoch AI | ||
| Chess Puzzles | 5% | #93 of 129, top 73% | minimal | Epoch AI | 2026-08-06 |
| Thematic Generalization | 53% | #15 of 23, top 66% | Lech Mazur benchmarks | ||
| LMArena Hard Prompts | 1448 | #67 of 297, top 23% | LMArena | 2026-10-08 | |
| DTBench | 82.7% | #62 of 151, top 42% | Epoch AI | ||
| LMCA | 39.3% | #47 of 125, top 38% | Epoch AI | ||
| Surface Evolver Bench | 30.6% | #21 of 25, top 84% | Epoch AI | ||
| Epoch Capabilities Index | 142.74 | #94 of 213, top 45% | Epoch AI | 2026-04-02 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | #85 of 173, top 50% | minimal | Epoch AI | 2026-08-06 |
| LMArena Math | 1465 | #48 of 285, top 17% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 75.8% | #91 of 186, top 49% | minimal | Epoch AI | 2026-08-06 |
| SimpleQA Verified | 10.4% | #75 of 77, top 98% | Epoch AI | 2026-08-27 | |
| Vectara Hallucination Rate (lower is better) | 7.4% | #32 of 96, top 34% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1465 | #56 of 273, top 21% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1277 | #31 of 122, top 26% | LMArena | 2026-10-09 | |
| LMArena Document | 1425 | #30 of 38, top 79% | LMArena | 2026-09-13 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1431 | #57 of 297, top 20% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1476 | #70 of 285, top 25% | LMArena | 2026-10-08 | |
| LMArena French | 1435 | #86 of 223, top 39% | LMArena | 2026-10-08 | |
| LMArena Russian | 1460 | #33 of 283, top 12% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1444 | #61 of 226, top 27% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1433 | #57 of 298, top 20% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1446 | #56 of 291, top 20% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1443 | #55 of 297, top 19% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1415 | #59 of 295, top 20% | LMArena | 2026-10-08 | |
| EQ-Bench Creative Writing | 1368 | #72 of 115, top 63% | EQ-Bench | ||
| EQ-Bench 4 | 1120 | #22 of 28, top 79% | EQ-Bench | ||
| LMArena Multi-Turn | 1452 | #51 of 295, top 18% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.14 | $0.40 | — | 2026-10-10 |
| deepinfra | $0.20 | $0.40 | — | 2026-10-10 |
| openrouter | $0.09 | $0.34 | $0.05 | 2026-10-10 |
Compare Gemma 4 31B IT
- Gemma 4 31B IT vs Kimi K2.5 Instant
- Gemma 4 31B IT vs Qwen3 235B-A22B
- Gemma 4 31B IT vs MiMo-V2-Omni
- Gemma 4 31B IT vs Gemma 4 26B A4B IT
- Gemma 4 31B IT vs Qwen3 Max
- Gemma 4 31B IT vs MiMo-V2.5
- Gemma 4 31B IT vs GPT-6 Astra
- Gemma 4 31B IT vs Claude Fable 5.1
- Gemma 4 31B IT vs Kimi K3
- Gemma 4 31B IT vs Grok 4.6
- Gemma 4 31B IT vs Qwen3.8 Max
- Gemma 4 31B IT vs GLM-5.3
- Gemma 4 31B IT vs Muse Spark 1.3
- Gemma 4 31B IT vs DeepSeek V4 Pro
Other Google models
Frequently asked questions
How good is Gemma 4 31B IT?
Gemma 4 31B IT by Google ranks 90th of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.5. Its strongest category is multimodal, where it ranks 34th. API pricing starts at $0.09 per million input tokens and $0.34 per million output tokens, with a 262K-token context window.
How much does Gemma 4 31B IT cost?
Gemma 4 31B IT costs $0.09 per million input tokens and $0.34 per million output tokens on openrouter, with cached input at $0.05.
What is Gemma 4 31B IT's context window?
Gemma 4 31B IT accepts up to 262K tokens of input and can write up to 33K tokens in one response.
Is Gemma 4 31B IT open source?
Yes. Gemma 4 31B IT's weights are downloadable from Hugging Face (google/gemma-4-31B-it); check the license for commercial terms.
How fast is Gemma 4 31B IT?
Gemma 4 31B IT generated about 3 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Gemma 4 31B IT's strengths and weaknesses?
Relative to other ranked models, Gemma 4 31B IT places best in multilingual, instruction following, long context and lowest in knowledge, reasoning, coding.
What is Gemma 4 31B IT best at?
Its best category is multimodal, where it ranks 34th on Noometry.