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 11 · bench-align-v5
Gemini 4 Hydrogen is a general-purpose language model. It ranks in the top quarter for math (top 10% of 110 scored models) and knowledge (top 25% of 283 scored models), by BenchLM's published scores. It accepts text, images, PDFs, audio and video and produces text.
Gemini 4 Hydrogen by Google scores 78.8 overall, costs $1.50 per 1M input tokens and $7.50 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.
Every published price component, including cache reads and writes.
Lifecycle events the source associates with this model, plus what this profile does not claim.
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 | 47.15 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 168 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| $3.75 |
| Batch cache read / 1M tokens (OpenRouter batch) | $0.0375 |
| Batch cache write / 1M tokens (OpenRouter batch) | $0.0833 |
Batch API rate (asynchronous jobs), from OpenRouter's batch listing.
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 |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 53.9 | #12 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 46.3 | #6 | 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 | 8.5 | #217 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierSWE v2 FrontierSWE v2 | 53.1 | #8 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE v2 |
| Bug Hunt Bench Bug Hunt Bench | 32.7 | #15 | 105 planted bugs across two production TypeScript repositories | Blind production-repository bug finding and repair | Bug Hunt Bench method, caveats, and definitions |
| FrontierCode 2.0 FrontierCode 2.0 | 38.9 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 88.070 | #12 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 87.805 | #10 | 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 |
|---|---|---|---|---|---|
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 21.1 | #25 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench-Science 0.1 Terminal-Bench-Science 0.1 | 51.4 | #11 | 70 expert-curated scientific research workflows | Frontier scientific research workflows | Terminal-Bench-Science 0.1 |
| AA Briefcase Artificial Analysis Briefcase | 1568 | #19 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 76.1 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chartography (no tools) Chartography without tools | 66.6 | #4 | 100 specialized chart types | Professional chart reasoning | Chartography |
| Design Arena Website Design Arena Website Elo | 1331 | #5 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| ExtractBench (LlamaIndex) ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard) |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| SpireClimb SpireClimb (Slay the Spire 1 and 2) | 7.7 | #7 | 60 Slay the Spire 1 runs (Ascension 20, Heart kill) and 75 Slay the Spire 2 runs (Ascension 10) per model | Maximum game difficulty, long-horizon computer use | SpireClimb (Epoch AI) |
| Chess Puzzles Chess Puzzles (Epoch AI) | 60.0 | #10 | 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) | 65.0 |
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. | xhigh | 0.9678 ± 0.0117 | 2026-11-13 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | xhigh | 0.8807 ± 0.0192 | 2026-11-13 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | xhigh | 0.878 ± 0.0517 | 2026-11-13 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | xhigh | 0.709 ± 0.0144 | 2026-11-13 |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
| #10 |
| 132 private software-engineering tasks |
| Frontier coding-agent quality |
| FrontierCode 2.0 |
| #6 |
| Business-process automation tasks |
| Agentic automation |
| Artificial Analysis AutomationBench Benchmark Leaderboard |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 53.5 | #14 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 27.6 | #11 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 2 | #19 | 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 |
| CWE-bench CWE-bench v2 | 68.1 | #2 | Audit and patch C/C++, Go, Java, TypeScript/JavaScript, Python, and Rust repositories; 100 public and 150 held-out tasks | Frontier agent evaluation | CWE-bench v2 leaderboard and methodology |
| Terminal-Bench 4.1 Terminal-Bench 4.1 | 56.40 | #11 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| OSWorld 2.1 Offline OSWorld 2.1 offline subset (82 tasks) | 77.6 | #6 | 82 offline computer-use workflows | Long-horizon professional workflows | OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) |
| MKA Multimodal Knowledge Agent Benchmark | 53.4 | #4 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | MKA Benchmark Leaderboard |
| #7 |
| 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 |
| ExtractBench Pro ExtractBench Pro: long-tail document extraction challenges (LlamaIndex) | 42 | #3 | 100 synthetic documents, 2,622 pages, 86 document types, six challenge groups | The best system completes 58 of 100 documents perfectly; several complete none | ExtractBench Pro leaderboard and challenge descriptions |
| #8 |
| 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) | 57.5 | #13 | 60 photos of three IKEA builds, some with deliberate assembly mistakes | Spatial reasoning from technical diagrams to real photos | Furniture Assembly Benchmark (Epoch AI) |
| EBR-bench Earthborne Rangers (EBR-bench) | 70.5 | #7 | Ten playthroughs of an Earthborne Rangers campaign segment per sample (eight learning, two scored) | Learning an unfamiliar game over multi-hour playthroughs | Earthborne Rangers (EBR-bench), Epoch AI |