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.
Anthropic · Proprietary · rank 39 · bench-align-v5
Claude Haiku 5.5 is built for agent work. It ranks in the top quarter for agent work (top 19% of 127 scored models), by BenchLM's published scores. It accepts text, images and PDFs and produces text.
Claude Haiku 5.5 by Anthropic scores 63.7 overall, costs $0.10 per 1M input tokens and $0.50 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.
Lifecycle events the source associates with this model, plus what this profile does not claim.
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 | 180.09 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 253 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| Batch output / 1M tokens (OpenRouter batch) (base rate) | $0.25 |
| Batch cache read / 1M tokens (OpenRouter batch) (base rate) | $0.005 |
| Batch cache write / 1M tokens (OpenRouter batch) (base rate) | $0.0625 |
Batch API rate (asynchronous jobs), from OpenRouter's batch listing.
The standard input, output and cache rates above are the base rate. models.dev publishes higher rates for requests whose prompt exceeds the thresholds below. The batch rates have their own long-context tiers, from OpenRouter's batch listing, shown separately. The cost simulator prices a standard-rate request whose whole prompt is above a threshold entirely at the highest of these tiers it exceeds, and a batch request only at a batch tier; it never applies these tiers to batch rates. The cost example on this page uses the base rate: its 1,200-token prompt is below every threshold.
The batch rates above are the base batch rate. OpenRouter's batch listing, the same listing as those rates, publishes higher batch rates for requests whose total prompt is above the thresholds below. The cost simulator prices a batch request whose whole prompt is above a threshold entirely at the highest batch tier it exceeds.
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 ModelChoice; each provider sets its own prices and limits.
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Artificial Analysis Intelligence Index Artificial Analysis Intelligence Index | 36.5 | #45 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-HLE Artificial Analysis Humanity's Last Exam | 44.4 | #28 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 12.3 | #47 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 34.7 | #79 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 34.2 | #179 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HLE w/o tools Humanity's Last Exam without tools | 45.9 | #17 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| HealthBench (raw, Artificial Analysis) Artificial Analysis HealthBench raw score | 61.2 | #4 | 5,000 conversations | Health conversation evaluation | HealthBench independent evaluation |
| HealthBench (length-adjusted, Artificial Analysis) Artificial Analysis HealthBench length-adjusted score | 58.5 | #3 | 5,000 conversations | Health conversation evaluation | HealthBench independent evaluation |
| HealthBench Professional (length-adjusted, Artificial Analysis) Artificial Analysis HealthBench Professional length-adjusted score | 58.4 | #5 | 525 conversations | Health conversation evaluation | HealthBench Professional independent evaluation |
| HealthBench Professional (raw, Artificial Analysis) Artificial Analysis HealthBench Professional raw score | 64.8 | #6 | 525 conversations | Health conversation evaluation | HealthBench Professional independent evaluation |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierCode 1.1 Main FrontierCode 1.1 Main | 46.4 | #7 | 100 private Main tasks (150 in Extended) | Frontier coding-agent quality | FrontierCode leaderboard |
| FrontierSWE v2 FrontierSWE v2 | 43.8 | #12 | 34 ultra-long-horizon engineering and research tasks | Ultra-long-horizon frontier software engineering | FrontierSWE v2 |
| Bug Hunt Bench Bug Hunt Bench | 21.5 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 75.088 | #25 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 46.341 | #25 | 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 | 89.00 | #29 | Semi-private ARC-AGI-1 evaluation set | Abstract visual reasoning | ARC Prize leaderboard |
| ARC-AGI-2 Abstraction and Reasoning Corpus for AGI v2 | 61.25 | #31 | 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 | 0.451371 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 4.0 Terminal-Bench 4.0 | 39.20 | #18 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.0 |
| AA Briefcase Artificial Analysis Briefcase | 1578 | #17 | Professional knowledge-work tasks | Professional work | Artificial Analysis Briefcase Benchmark Leaderboard |
| AA AutomationBench Artificial Analysis AutomationBench | 35.4 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chartography (no tools) Chartography without tools | 46.4 | #8 | 100 specialized chart types | Professional chart reasoning | Chartography |
| Design Arena Website Design Arena Website Elo | 1248 | #45 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| ParseBench-1 ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release) |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chess Puzzles Chess Puzzles (Epoch AI) | 55.0 | #18 | 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) | 30.0 | #35 | 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) | 47.5 |
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. | max | 0.8965 ± 0.0198 | 2026-10-09 | |
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | max | 0.7509 ± 0.0257 | 2026-10-07 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | max | 0.4634 ± 0.0788 | 2026-10-07 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | max | 0.238 ± 0.0135 | 2026-10-09 |
Source: Epoch AI, CC BY 4.0 (licence), benchmark data read once a day.
| #24 |
| 105 planted bugs across two production TypeScript repositories |
| Blind production-repository bug finding and repair |
| Bug Hunt Bench method, caveats, and definitions |
| AA-SciCode Artificial Analysis SciCode | 55.0 | #29 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| VulcanBench Frontier v4 VulcanBench Frontier v4 | 92.2 | #3 | 23 behavioural-reconstruction coding tasks | Professional multi-file software engineering | VulcanBench Frontier v4 leaderboard |
| FrontierCode 2.0 (AA) FrontierCode 2.0, Artificial Analysis evaluation | 34.9 | #1 | 132 private software-engineering tasks | Frontier coding-agent quality | Artificial Analysis Intelligence Index |
| FrontierCode 2.0 FrontierCode 2.0 | 28.9 | #14 | 132 private software-engineering tasks | Frontier coding-agent quality | FrontierCode 2.0 |
| #17 |
| 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 | 82.7 | #23 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 35.0 | #14 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 18.9 | #33 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
| ARC-AGI-3 Provider Adapter ARC-AGI-3 Semi-Private: Provider Adapter harness | 2.82 | #11 | — | — | ARC Prize verified ARC-AGI-3 results |
| #43 |
| Business-process automation tasks |
| Agentic automation |
| Artificial Analysis AutomationBench Benchmark Leaderboard |
| AA Harvey LAB v1.0 Artificial Analysis Harvey LAB-AA v1.0 | 89.9 | #10 | Legal agent tasks | Professional legal work | Artificial Analysis Harvey LAB-AA Benchmark Leaderboard |
| HLE w/ tools Humanity's Last Exam with tools | 57.4 | #12 | Expert questions with tool use | Frontier tool-augmented reasoning | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA | 1620 | #26 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 56.0 | #15 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Terminal-Bench 4.0 Artificial Analysis Terminal-Bench v4.0 | 32.8 | #28 | Terminal-based agent tasks | Agentic software engineering | Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard |
| GDP.pdf Artificial Analysis GDP.pdf | 20.8 | #30 | Professional document-production tasks | Professional knowledge work | GDP.pdf Benchmark Leaderboard |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 53.8 | #6 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| Hermes Index Hermes Index: agentic capability and cost per task inside Hermes Agent | 37.0 | #11 | 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 | 71.0 | #9 | 150 tasks across 25 categories | Frontier agentic | Hermes Bench (Hermes Index) |
| MazeBench MazeBench: visual spatial reasoning in a 3D open world | 1 | #22 | 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 | 40.00 | #20 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| AA AutomationBench (strict) Artificial Analysis AutomationBench, strict pass@1 | 13.9 | #3 | End-to-end business-workflow automation tasks | Agentic automation | Artificial Analysis AutomationBench Benchmark Leaderboard |
| OSWorld 2.1 Offline OSWorld 2.1 offline subset (82 tasks) | 72.4 | #9 | 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 | 41.0 | #14 | 200 multimodal professional tasks across 10 industry verticals | Expert multimodal knowledge work | MKA Benchmark Leaderboard |
| Agents' Last Exam (Linux) Agents' Last Exam, Linux subset | 57.0 | #3 | Linux agent tasks (subset size not published) | Advanced agentic work | Introducing Muse Ember |
| #32 |
| 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) | 71.24 | #16 | 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 |
| PerceptionBench (tools) PerceptionBench with tools | 78.6 | #2 | Fine-grained visual-perception tasks with tools | Fine-grained visual perception | Introducing Muse Ember |
| #19 |
| 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) | 43.8 | #14 | 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 |
| MirrorCode MirrorCode (Epoch AI and METR) | 78.9 | #5 | 30 reimplementation tasks (15 programs in two languages), three attempts each | Days-long software engineering without source code | MirrorCode (Epoch AI) |
| FACTS Multimodal FACTS Multimodal | 38.9 | #20 | About 1,500 image questions: 711 public and 811 held out | Image-grounded factual answering | BenchLM |
| Pelican Arena Pelican Arena | 1305 | #22 | One prompt: an animated SVG of a pelican riding a bicycle, rated by human votes | Vector drawing and animation in code | BenchLM |
| ASCII Arena ASCII Arena | 1337 | #12 | ASCII drawings of subjects from Google's Quick, Draw! dataset, rated by human votes | Text-character drawing | BenchLM |
| Game Arena Go Game Arena Go | 1076 | #15 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | BenchLM |
| NYT Connections NYT Connections LLM Benchmark (extended version) | 65.7 | #58 | 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) | 49.5 | #17 | 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 | 4.2 | #17 | 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) |