Model profile
Gemma 4 31B
Evidence coverage
29 of 323 tracked benchmarks are published. 7 are verified and 22 provisional. 6 of 8 categories are measured.
- Published / tracked
- 29 / 323
- Verified
- 7
- Provisional
- 22
- Categories with evidence
- 6 / 8
Evidence by category
- Agentic9 benchmarksMixed evidence
- Coding4 benchmarksMixed evidence
- Reasoning2 benchmarksReported
- Knowledge11 benchmarksMixed evidence
- Math0 benchmarksNot measured
- Multilingual0 benchmarksNot measured
- Multimodal2 benchmarksMixed evidence
- Inst. Following1 benchmarkReported
Gemma 4 31B ranks #43 out of 200 models on the public leaderboard with an overall score of 61.08/100. It also ranks #33 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.
Gemma 4 31B is a open weight model with a 256K token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.
Gemma 4 31B sits inside the Gemma 4 family alongside Gemma 4 26B A4B, Gemma 4 12B, Gemma 4 E2B, Gemma 4 E4B. This profile currently has 29 of 323 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.
Its strongest category is Coding (#71), while its weakest is Agentic (#114). This performance profile makes it particularly well-suited for software development and code generation tasks.
Peer position
Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.
Range 60.56–61.31
- Gemini 3 Pro Deep ThinkGoogleCompare#4161.31Gemini 3 Pro Deep Think is #41 with a score of 61.31.
- GLM-4.7Z.AICompare#4261.16GLM-4.7 is #42 with a score of 61.16.
- Gemma 4 31BCurrent modelGoogle#4361.08Gemma 4 31B is #43 with a score of 61.08.
- GPT-5.4 ProOpenAICompare#4460.89GPT-5.4 Pro is #44 with a score of 60.89.
- Qwen3.5-27BAlibabaCompare#4560.7Qwen3.5-27B is #45 with a score of 60.7.
- DeepSeek V4 ProDeepSeekCompare#4660.66DeepSeek V4 Pro is #46 with a score of 60.66.
- Qwen3.5-122B-A10BAlibabaCompare#4760.56Qwen3.5-122B-A10B is #47 with a score of 60.56.
Category percentile
More
Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.
- Coding42%Eligible cohort rank #71 of 122Category score 49.1
- Agentic4%Eligible cohort rank #114 of 119Category score 27.0
Category evidence
Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #114 of 119Percentile 4thWeight 22%9 benchmarksMixed sources | 27.0 | #114 of 119 | 4th | 22% | 9 benchmarks | Mixed sources |
| CodingRank #71 of 122Percentile 42ndWeight 20%4 benchmarksMixed sources | 49.1 | #71 of 122 | 42nd | 20% | 4 benchmarks | Mixed sources |
| ReasoningRank Not rankedWeight 17%2 benchmarksReported | 66.4 | Not ranked | Not available | 17% | 2 benchmarks | Reported |
| KnowledgeRank Not rankedWeight 12%11 benchmarksMixed sources | 51.5 | Not ranked | Not available | 12% | 11 benchmarks | Mixed sources |
| MathWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalRank Not rankedWeight 12%2 benchmarksMixed sources | 59.4 | Not ranked | Not available | 12% | 2 benchmarks | Mixed sources |
| Inst. FollowingWeight 5%1 benchmarkReported | Score pending | Not ranked | Not available | 5% | 1 benchmark | Reported |
Self-host vs API cost
Estimates at 50,000 req/day · 1000 tokens/req average.
Chatbot Arena performance
Scroll horizontally to inspect confidence intervals and vote counts.
| View | Elo | Confidence interval | Votes |
|---|---|---|---|
| Text Overall | 1451 | ±7.6 | 5,879 |
| Coding | 1498 | ±15.4 | 1,362 |
| Math | 1470 | ±27.5 | 399 |
| Instruction Following | 1452 | ±14.1 | 1,663 |
| Creative Writing | 1421 | ±19.3 | 937 |
| Multi-turn | 1464 | ±17.8 | 1,069 |
| Hard Prompts | 1473 | ±9.9 | 3,368 |
| Hard Prompts (English) | 1483 | ±14.7 | 1,530 |
| Longer Query | 1467 | ±13.9 | 1,656 |
Benchmark Details
Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.
Agentic9 benchmarks
Artificial Analysis Agentic Index
τ²-Bench Tool-Agent-User Evaluation
GDPval-AA normalized
Gert Labs Composite Game Benchmark
Artificial Analysis EnterpriseOps-Gym
Artificial Analysis ITBench-AA
Artificial Analysis Tau3-Banking
Coding4 benchmarks
Artificial Analysis Coding Index
Artificial Analysis SciCode
Reasoning2 benchmarks
Artificial Analysis Long Context Reasoning
Critical Physics Tasks
Knowledge11 benchmarks
Humanity's Last Exam
Massive Multitask Language Understanding Professional
Graduate-Level Google-Proof Q&A
Humanity's Last Exam without tools
Artificial Analysis GPQA Diamond
Artificial Analysis Humanity's Last Exam
Artificial Analysis Omniscience Index
Artificial Analysis Omniscience Accuracy
Artificial Analysis Omniscience Hallucination Rate
Artificial Analysis Openness Index
Multimodal2 benchmarks
Massive Multi-discipline Multimodal Understanding Pro
Artificial Analysis MMMU-Pro
Inst. Following1 benchmark
Artificial Analysis IFBench
Frequently Asked Questions
How does Gemma 4 31B perform overall in AI benchmarks?
Gemma 4 31B has 29 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.
Is Gemma 4 31B good for knowledge and understanding?
Gemma 4 31B has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.
Is Gemma 4 31B good for coding and programming?
Gemma 4 31B ranks #71 out of 122 models in coding and programming benchmarks with an average score of 49.1. There are stronger options in this category.
Is Gemma 4 31B good for reasoning and logic?
Gemma 4 31B has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.
Is Gemma 4 31B good for agentic tool use and computer tasks?
Gemma 4 31B ranks #114 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 27. There are stronger options in this category.
Is Gemma 4 31B good for multimodal and grounded tasks?
Gemma 4 31B has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.
Is Gemma 4 31B good for instruction following?
Gemma 4 31B has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.
Is Gemma 4 31B open source?
Yes, Gemma 4 31B is an open weight model created by Google, meaning it can be downloaded and run locally or fine-tuned for specific use cases.
Which sibling models are related to Gemma 4 31B?
Gemma 4 31B belongs to the Gemma 4 family. Related variants on BenchLM include Gemma 4 26B A4B, Gemma 4 12B, Gemma 4 E2B, Gemma 4 E4B.
Does Gemma 4 31B have full benchmark coverage on BenchLM?
Not yet. Gemma 4 31B currently has 29 published benchmark scores out of the 323 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.
What is the context window size of Gemma 4 31B?
Gemma 4 31B has a published context window of 256K, which determines how much text it can process in a single interaction.
Related Resources
Choose with this week’s evidence
Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.
Free. One email per week.