Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Loading page…
Preferred languages
More languages supported by Google Translate
Open the selector to load the current language catalog.
Translations are provided by Google Translate.
Google · Open Weight · rank 137 · bench-align-v5
Gemma 4 31B is a general-purpose language model. It ranks in the top quarter for instruction following (top 13% of 159 scored models), by BenchLM's published scores.
Gemma 4 31B by Google scores 43 overall and carries a context window of 256K tokens — observed 2026-11-21.
Seven axes from the ranking source. A missing axis is drawn as a gap.
Each axis shows the ranking source’s score and, beside it, BenchLM’s separate verified score for that axis. The two are published side by side and are not interchangeable.
Every published price component, including cache reads and writes.
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 78.95 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 36 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Plans from the model's maker, and the API providers that list this exact model today. Links leave ModelScale; each provider sets its own prices and limits.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| GPQA Graduate-Level Google-Proof Q&A | 84.3 | #59 | 448 questions | Graduate level | GPQA: A Graduate-Level Google-Proof Q&A Benchmark |
| MMLU-Pro Massive Multitask Language Understanding Professional | 85.2 | #19 | Multiple subjects | Professional level | MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark |
| HLE Humanity's Last Exam | 26.5 | #61 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 4.4 | #238 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 85.7 | #74 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 23.6 | #108 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | -48.5 | #185 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 19.9 | #155 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 85.5 | #58 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HLE w/o tools Humanity's Last Exam without tools | 19.5 | #53 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| SWE-Rebench SWE-Rebench | 41.6 | #13 | Fresh GitHub issues (rolling window) | Professional software engineering | SWE-Rebench: Contamination-Free Evaluation of Software Engineering Agents |
| LiveCodeBench v6 LiveCodeBench v6 | 80.0 | #31 | Fresh programming problems | Competitive programming level | LiveCodeBench official repository and release documentation |
| React Native Evals React Native Evals | 75.2 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MRCRv2 MRCRv2 | 66.4 | #9 | Long-context retrieval | Hard long-context | Introducing GPT-5.2 and GPT-5.2 Pro |
| AA-LCR Artificial Analysis Long Context Reasoning | 69.7 | #118 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| CritPt Critical Physics Tasks | 1.4 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-IFBench Artificial Analysis IFBench | 75.6 | #22 | Verifiable instruction constraints | Instruction precision | Artificial Analysis IFBench Benchmark Leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA ITBench Artificial Analysis ITBench-AA | 37.3 | #23 | IT incident-response tasks | Enterprise IT operations | Artificial Analysis ITBench-AA Benchmark Leaderboard |
| GDPval-AA GDPval-AA | 755 | #101 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 5.9 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MMMU-Pro Massive Multi-discipline Multimodal Understanding Pro | 76.9 | #31 | Multimodal academic reasoning | Frontier multimodal | MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark |
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 73.4 | #67 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| ParseBench-1 ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release) | 62.40 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FACTS Multimodal FACTS Multimodal | 42.3 | #15 | About 1,500 image questions: 711 public and 811 held out | Image-grounded factual answering | BenchLM |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 70.6 | #53 | 940 NYT Connections puzzles, each with up to four added trick words | Wordplay, word knowledge and decoys that fit almost-but-not-quite | NYT Connections LLM Benchmark (Lech Mazur, GitHub) |
| StealthMark StealthMark Intelligence Benchmarks (overall score) | 29.5 |
People's votes between two anonymous answers on arena.ai, one board per task. LMArena's own ratings and ranks, one line per model version it rates; not part of this site's capability scores or rank.
| Board | Variant | Rating | Votes | Rank | Published | Evidence |
|---|---|---|---|---|---|---|
| Vision Arena People's votes between two answers about the same image, style-controlled. | — | 1,265 ± 5 | 42,217 | 41 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #10 |
| React Native app implementation tasks |
| Production mobile app engineering |
| React Native Evals |
| AA Coding Index Artificial Analysis Coding Index | 43.4 | #65 | Cross-benchmark coding index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 45.5 | #73 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| #99 |
| Economically valuable tasks |
| Professional agentic workflows |
| Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 6.7 | #56 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| Gert Labs Gert Labs Composite Game Benchmark | 35.26 | #45 | Novel game environments | Agentic coding and decision-making | Gert Labs rankings |
| τ²-bench results τ²-Bench Tool-Agent-User Evaluation | 59.9 | #90 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment |
| b3 Agent Security b3: Backbone Breaker Benchmark | 83.0 | #4 | Threat snapshots of attacks on agent backends | Agent security | The Backbone Breaker Benchmark |
| Cyber Misuse Refusal Refusal of harmful cyber requests (JailbreakBench, StrongREJECT, AgentHarm) | 84.0 | #4 | Cyber-related harmful prompts from three safety benchmarks | Cyber misuse safety | Mistral Large 4 is now open weight |
| #25 |
| 2,078 human-verified enterprise pages from insurance, finance and government documents |
| No method is strong on all five dimensions; charts and visual grounding separate the field |
| ParseBench: A Document Parsing Benchmark for AI Agents |
| #38 |
| 8 original tasks: Newton's Mirror, Ground Truth, Latch, Foresight, Mona Lisa, Selfie, Beach and Raccoon |
| Chained physical reasoning, planning without tools and precise visual construction |
| StealthMark: The AI Benchmark Explained (Stealth Models) |