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 · Proprietary · rank 29 · bench-align-v5
Gemini 3.8 Flash is built for coding. It ranks in the top quarter for multimodal tasks (top 6% of 136 scored models) and coding (top 9% of 210 scored models), by BenchLM's published scores. It accepts text, images, PDFs, audio and video and produces text.
Gemini 3.8 Flash by Google scores 67.7 overall, costs $0.75 per 1M input tokens and $3.75 per 1M output tokens, and carries a context window of 1M tokens — observed 2026-11-21.
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.
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.
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 | 19.76 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 115 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 |
|---|---|---|---|---|---|
| BioMysteryBench (human-solvable) BioMysteryBench Human Solvable | 88.8 | #4 | Human-solvable computational biology investigations | Expert computational biology | Claude Opus 5 System Card |
| BioMysteryBench (human-difficult) BioMysteryBench Human Difficult | 56.5 | #1 | Human-difficult computational biology investigations | Frontier computational biology | Claude Opus 5 System Card |
| HLE-Verified HLE-Verified | 54.9 | #1 | 1,811 verified or revised expert questions | Frontier multidisciplinary expert reasoning | HLE-Verified: A Systematic Verification and Structured Revision of Humanity's Last Exam |
| LABBench2 LABBench2: An Improved Benchmark for AI Systems Performing Biology Research | 86.2 | #2 | Nearly 1,900 biology-research tasks | Real-world biology research | LABBench2: An Improved Benchmark for AI Systems Performing Biology Research |
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 30.9 | #57 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 95.3 | #2 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 47.8 | #20 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 23.3 | #33 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 50.5 | #23 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 55.1 | #137 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 94.4 | #4 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 90.2 | #5 | Academic multiple-choice questions | Broad academic knowledge | Vals AI MMLU-Pro, Vals AI run leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 89.4 | #5 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| FrontierSWE v2 FrontierSWE v2 | 19.6 | #20 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE v2 |
| Bug Hunt Bench Bug Hunt Bench | 18.0 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 68.421 | #30 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 21.951 | #42 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| ARC-AGI-1 ARC-AGI-1 Semi-Private Evaluation | 98.50 | #1 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | ARC Prize leaderboard |
| ARC-AGI-2 Abstraction and Reasoning Corpus for AGI v2 | 89.166667 | #11 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | ARC-AGI-2: A Harder General Intelligence Benchmark |
| ARC-AGI-3 Abstraction and Reasoning Corpus for AGI v3 | 10.366279 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 19.10 | #28 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.0 |
| AA Briefcase Artificial Analysis Briefcase | 1203 | #42 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 59.9 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 85.6 | #5 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1288 | #22 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| LVBench LVBench | 87.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Gray Swan IPI (15 attempts) Gray Swan Indirect Prompt Injection, attack success at 15 attempts | 5.5 | #9 | Indirect prompt-injection attacks | Adversarial prompt injection | Gemini 4 Argon evaluation methodology |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| MaxxBench MaxxBench (mutated DeepSWE tasks) | 53.4 | #10 | 89 mutated DeepSWE feature-implementation tasks, two attempts per model | Long-horizon software engineering under changed requirements | Why MaxxBench (unLAP research post) |
| Chess Puzzles Chess Puzzles (Epoch AI) | 58.0 | #15 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | Chess Puzzles (Epoch AI) |
| Mystery Game Puzzles Mystery Game Puzzles (Epoch AI) | 47.0 |
A second, independent score source. Epoch’s own figures in Epoch’s units, one line per model version Epoch evaluated (effort setting as Epoch labels it). They are not part of this site’s capability scores or rank.
| Benchmark | Variant | Score | Epoch date | Evidence |
|---|---|---|---|---|
| GPQA Diamond Accuracy on graduate-level science multiple-choice questions (best score across scorers). Unit: fraction (0–1); higher is better. | high | 0.9539 ± 0.014 | 2026-09-02 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | high | 0.6842 ± 0.0276 | 2026-09-02 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | high | 0.2195 ± 0.0654 | 2026-09-02 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | high | 0.697 ± 0.0145 | 2026-09-02 |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
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. | High | 1,293 ± 8 | 9,782 | 12 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #27 |
| 105 planted bugs across two production TypeScript repositories |
| Blind production-repository bug finding and repair |
| Bug Hunt Bench method, caveats, and definitions |
| AA Coding Index Artificial Analysis Coding Index | 76.3 | #8 | Cross-benchmark coding index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 56.6 | #23 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| LiveCodeBench (Vals) LiveCodeBench, Vals AI run | 89.5 | #3 | Competitive programming problems (easy, medium, hard) | Frontier coding | Vals AI LiveCodeBench, Vals AI run leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 80.0 | #24 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| DeepSWE DeepSWE | 73.8 | #14 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| ScarfBench ScarfBench: Cross-Framework Application Migration in Enterprise Java | 66.0 | #6 | 204 framework migration tasks across 34 enterprise Java applications | Whole-application framework migration | ScarfBench: A Benchmark for Cross-Framework Application Migration in Enterprise Java |
| #9 |
| Interactive game-like tasks with hidden rules |
| Frontier agentic reasoning |
| ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence |
| AA-LCR Artificial Analysis Long Context Reasoning | 81.3 | #34 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 21.7 | #24 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 18.3 | #34 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
| ARC-AGI-3 Provider Adapter ARC-AGI-3 Semi-Private: Provider Adapter harness | 35.00 | #8 | — | — | ARC Prize verified ARC-AGI-3 results |
| #24 |
| Business-process automation tasks |
| Agentic automation |
| Artificial Analysis AutomationBench Benchmark Leaderboard |
| AA ITBench Artificial Analysis ITBench-AA | 52.5 | #3 | IT incident-response tasks | Enterprise IT operations | Artificial Analysis ITBench-AA Benchmark Leaderboard |
| AA Tau3 Banking Artificial Analysis Tau3-Banking | 44.9 | #9 | Banking tool-use workflows | Agentic banking workflows | Artificial Analysis Tau3-Banking Benchmark Leaderboard |
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 89.4 | #5 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| GDPval-AA GDPval-AA | 1545 | #37 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 46.8 | #35 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 41.1 | #21 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 19.7 | #35 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 21.0 | #29 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 46.3 | #17 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| OSWorld 2.0 OSWorld 2.0 | 59.0 | #9 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks |
| Finance Agent v2 Finance Agent v2 | 61.4 | #2 | Financial analyst task categories | Professional expert-task agent workflow | Finance Agent v2 |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 81.3 | #8 | Difficult terminal tasks | Frontier agentic | Vals AI Terminal-Bench 2.1, Vals AI run leaderboard |
| ApprenticeBench ApprenticeBench: end-to-end computer use, continual learning, and long-horizon agency on a real accounts-payable job | 24 | #6 | 100 vendor bills processed in sequence inside a simulated construction company | Long-horizon computer use with offline and online continual learning | ApprenticeBench: a step change in AI's job readiness |
| Hermes Index Hermes Index: agentic capability and cost per task inside Hermes Agent | 38.1 | #10 | Four suites: Hermes Bench (150 tasks), TerminalBench 4 without its 4 GPU tasks, TerminalBench Science and SkillsBench | Frontier agentic | Hermes Index: an agentic model leaderboard |
| Hermes Bench Hermes Bench: 150 agent tasks graded on the files and state the agent leaves behind | 62.2 | #16 | 150 tasks across 25 categories | Frontier agentic | Hermes Bench (Hermes Index) |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 4 | #18 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | MazeBench Results |
| Terminal-Bench 4.1 Terminal-Bench 4.1 | 18.20 | #33 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| AA Cyber Index Artificial Analysis Cyber Index | 25.1 | #17 | Three defensive cybersecurity evaluations | Real-world vulnerability discovery and patching | Artificial Analysis Cyber Index |
| CWE-Bench-AA Artificial Analysis CWE-Bench-AA | 52.5 | #15 | Real-world vulnerability patching tasks | Automated vulnerability remediation | CWE-Bench-AA Benchmark Leaderboard |
| DeepsecBench-AA Artificial Analysis DeepsecBench-AA | 14.5 | #18 | Vulnerability discovery in real codebases | Security code review | DeepsecBench-AA Benchmark Leaderboard |
| CyberGym-E2E-AA Artificial Analysis CyberGym-E2E-AA | 8.4 | #14 | 131 end-to-end vulnerability reproduction and patching tasks | Real-world cybersecurity | CyberGym-E2E-AA Benchmark Leaderboard |
| MKA Multimodal Knowledge Agent Benchmark | 35.3 | #19 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | MKA Benchmark Leaderboard |
| #2 |
| Long-form video question answering |
| Extended temporal reasoning |
| Qwen3.8-Max: A New Bar for Coding and Cowork |
| CharXiv w/o tools CharXiv Reasoning without tools | 86.2 | #4 | Scientific chart reasoning (tool-free) | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| ParseBench-1 ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release) | 71.20 | #8 | 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 |
| ExtractBench (LlamaIndex) ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard) | 80.71 | #21 | 370 documents, 4,869 pages, 8 business domains, 67 document types, each with a JSON Schema | Short documents are near solved; long record lists and grounding separate systems | ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction |
| ParseBench-2 ParseBench-2: severity-aware document parsing (LlamaIndex leaderboard) | 76.53 | #6 | 4,317 page-level test cases from 2,645 documents in 13 datasets | Charts and visual grounding separate the field; several systems that lead on text and tables score near zero on charts | ParseBench-2: Severity-Aware Evaluation of Document Parsing |
| #19 |
| 100 single-best-move positions from an undisclosed game |
| Unfamiliar game positions, single best move |
| Mystery Game Puzzles (Epoch AI) |
| Furniture Assembly Furniture Assembly Benchmark (Epoch AI) | 31.7 | #30 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | Furniture Assembly Benchmark (Epoch AI) |
| MirrorCode MirrorCode (Epoch AI and METR) | 38.9 | #26 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | MirrorCode (Epoch AI) |
| Epoch Automation Reports Epoch Automation Reports | 42.3 | #6 | 11 open-ended work tasks in five categories from Epoch AI's own work | Open-ended professional research and design work | Epoch Automation Reports |
| FACTS Multimodal FACTS Multimodal | 57.6 | #2 | About 1,500 image questions: 711 public and 811 held out | Image-grounded factual answering | BenchLM |
| DAYJOB DAYJOB | 2.6 | #11 | 130 long-horizon tasks: 80 finance and 50 healthcare | Long-horizon professional work | BenchLM |
| DAYJOB Healthcare DAYJOB Healthcare | 1.2 | #10 | 50 long-horizon healthcare tasks across five subfields | Long-horizon clinical and healthcare operations work | BenchLM |
| FailureSensorIQ FailureSensorIQ | 69.0 | #3 | Multiple-choice questions on sensors and failure modes for 10 industrial assets | Industrial maintenance and reliability knowledge | BenchLM |
| Code2Video Code2Video | 1440 | #17 | Creative briefs rendered as motion-graphics video | Code-driven motion design | BenchLM |
| Landing Page Arena Landing Page Arena | 1338 | #14 | 12 client briefs for small-business landing pages, rated by human votes | Marketing page design and copy | BenchLM |
| Chart Arena Chart Arena | 1498 | #9 | 13 chart briefs with small datasets, rated by human votes | Data visualisation | BenchLM |
| Joke Arena Joke Arena | 1540 | #3 | 100 joke prompts in 10 categories, rated by human votes | Humour writing | BenchLM |
| Pelican Arena Pelican Arena | 1570 | #13 | One prompt: an animated SVG of a pelican riding a bicycle, rated by human votes | Vector drawing and animation in code | BenchLM |
| Landmark Arena Landmark Arena | 1361 | #11 | 20 famous landmarks built as three.js web pages, rated by human votes | 3D scenes in browser code | BenchLM |
| ASCII Arena ASCII Arena | 1677 | #5 | ASCII drawings of subjects from Google's Quick, Draw! dataset, rated by human votes | Text-character drawing | BenchLM |
| Game Arena Go Game Arena Go | 1170 | #11 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | BenchLM |
| BabaIsBench BabaIsBench (Baba Is You intro levels, pass@1) | 100 | #1 | 8 intro levels of Baba Is You, three attempts per level (Stage 0); 15 further levels run once (Stage 1) | Rule-rewriting puzzles that need planning over many moves | Baba Is Solved by Fable 5 and GPT-5.6 Sol, but at what cost? (Quesma) |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 97.4 | #5 | 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) | 47.9 | #19 | 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) |
| FrontierPhysics End-to-End Physics Research Benchmark for AI Agents | 0.0 | #20 | 56 research projects from 42 physicists across nine fields, three trials each (168 rollouts per setup) | Open-ended research projects that took their authors about 270 days on average | FrontierPhysics: Evaluating Agents for End-to-End Physics Research (arXiv, November 4, 2026) |
| HoneyBench HoneyBench v0.2 (Goodhart Labs) | 80.5 | #6 | 20 private honeypot tasks across 7 domains with exploitable evaluators | Agentic alignment and specification gaming | HoneyBench v0.2 |