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 33 · bench-align-v5
Gemini 3.7 Flash is built for coding and reasoning. It ranks in the top quarter for coding (top 5% of 210 scored models) and knowledge (top 7% of 283 scored models), by BenchLM's published scores. It accepts text, images, PDFs, audio and video and produces text.
Every published price component, including cache reads and writes.
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.
Gemini 3.7 Flash by Google scores 66.4 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.
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 | 8.52 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 285 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
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.
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 | 87.1 | #5 | Human-solvable computational biology investigations | Expert computational biology | Claude Opus 5 System Card |
| BioMysteryBench (human-difficult) BioMysteryBench Human Difficult | 43.5 | #5 | Human-difficult computational biology investigations | Frontier computational biology | Claude Opus 5 System Card |
| HLE-Verified HLE-Verified | 53.6 | #4 | 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 | 82.1 | #4 | 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 | 39.1 | #39 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 94.5 | #4 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 47.9 | #18 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 26.5 | #28 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 55.3 | #14 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 64.5 | #120 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 93.9 | #5 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 90.1 | #6 | 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 | 85.8 | #17 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| FrontierCode 1.1 Main FrontierCode 1.1 Main | 43.6 | #10 | 100 private Main tasks (150 in Extended) | Frontier coding-agent quality | FrontierCode leaderboard |
| FrontierSWE v2 FrontierSWE v2 | 20.3 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 71.579 | #27 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 36.585 | #27 | 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 | 95.50 | #15 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | ARC Prize leaderboard |
| MRCR v2 64K-128K OpenAI MRCR v2 8-needle 64K-128K | 97 | #1 | 8-needle retrieval tasks | Long-context reasoning | Introducing GPT-5.4 mini and nano |
| ARC-AGI-2 Abstraction and Reasoning Corpus for AGI v2 | 84.583333 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 3.0 Terminal-Bench 3.0 | 14.9 | #8 | 74 professional computer-work tasks across 7 domains | Frontier autonomous knowledge work | Terminal-Bench 3.0 |
| AA Harvey LAB v1.0 Artificial Analysis Harvey LAB-AA v1.0 | 90.7 | #9 | Legal agent tasks | Professional legal work | Artificial Analysis Harvey LAB-AA Benchmark Leaderboard |
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 85.8 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 85.5 | #6 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1292 | #18 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| LVBench LVBench | 85.4 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chess Puzzles Chess Puzzles (Epoch AI) | 66.0 | #7 | 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) | 37.0 | #23 | 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) | 26.7 |
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 | 0.9482 ± 0.0135 | 2026-08-14 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | high | 0.7158 ± 0.0268 | 2026-08-14 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | high | 0.3659 ± 0.0762 | 2026-08-14 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | high | 0.692 ± 0.0146 | 2026-08-27 |
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 | 1,294 ± 9 | 6,776 | 6 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #19 |
| 34 ultra-long-horizon engineering and research tasks |
| Ultra-long-horizon frontier software engineering |
| FrontierSWE v2 |
| AA Coding Index Artificial Analysis Coding Index | 76.1 | #10 | Cross-benchmark coding index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 57.2 | #21 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| LiveCodeBench (Vals) LiveCodeBench, Vals AI run | 88.7 | #5 | Competitive programming problems (easy, medium, hard) | Frontier coding | Vals AI LiveCodeBench, Vals AI run leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 80.8 | #23 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| DeepSWE DeepSWE | 65.3 | #38 | 113 software engineering tasks across 91 repositories and 5 languages | Long-horizon software engineering | DeepSWE benchmark blog |
| #15 |
| Visual pattern completion and abstract reasoning |
| Expert-level — hardest public reasoning benchmark |
| ARC-AGI-2: A Harder General Intelligence Benchmark |
| AA-LCR Artificial Analysis Long Context Reasoning | 81.7 | #33 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| CritPt Critical Physics Tasks | 14.3 | #54 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
| #18 |
| Terminal-based software-agent tasks |
| Professional software engineering |
| Terminal-Bench |
| GDPval-AA GDPval-AA | 1525 | #38 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 44.6 | #41 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 36.4 | #26 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 60.0 | #2 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| OSWorld 2.0 OSWorld 2.0 | 47.9 | #12 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks |
| AutomationBench AutomationBench | 30.4 | #30 | 600 public automation tasks | Long-horizon automation | Kimi K3: Open Frontier Intelligence |
| Agents' Last Exam Agents' Last Exam | 26.3 | #17 | Agent tasks | Advanced agentic work | DeepSeek V4 Flash 0731 update |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 77.5 | #13 | 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 | 16 | #10 | 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 |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 1 | #21 | 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 | 12.40 | #38 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| #3 |
| Long-form video question answering |
| Extended temporal reasoning |
| Qwen3.8-Max: A New Bar for Coding and Cowork |
| CharXiv CharXiv Reasoning | 88.7 | #14 | Scientific chart reasoning | Scientific visualization reasoning | CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| CharXiv w/o tools CharXiv Reasoning without tools | 84.5 | #8 | 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) | 70.37 | #10 | 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 |
| ParseBench-2 ParseBench-2: severity-aware document parsing (LlamaIndex leaderboard) | 76.55 | #5 | 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 |
| #33 |
| 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) | 41.1 | #22 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | MirrorCode (Epoch AI) |
| Code2Video Code2Video | 1477 | #12 | Creative briefs rendered as motion-graphics video | Code-driven motion design | BenchLM |
| Game Arena Go Game Arena Go | 1006 | #17 | 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) | 94.0 | #11 | 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) |