# Claude Sonnet 4.5

Anthropic · Proprietary · rank 109 · bench-align-v5

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/models/claude-sonnet-4-5  
JSON: https://modelchoice.dev/api/model/claude-sonnet-4-5

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `claude-sonnet-4-5` | — |
| Overall score | 46.6 | Observed 2026-11-21 · source benchlm:models |
| Verified score (BenchLM): a separate BenchLM figure, not the overall score | 50 | Observed 2026-11-21 · source benchlm:models |
| Context window | 200K tokens | Observed 2026-11-21 · source benchlm:models |
| Max output (models.dev) | 64,000 tokens | Observed 2026-11-21 · source modelsdev:catalog |
| Modalities (models.dev) | Input: text, image, PDF · Output: text | Observed 2026-11-21 · source modelsdev:catalog |
| Release date | 2025-09-29 | Observed 2026-11-21 · source benchlm:models |
| Access type | Proprietary | — |
| Blended $/1M (75% input / 25% output) | $6.00 | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero. Beside each score is BenchLM's separate verified score for that axis; the two are published side by side and are not interchangeable.

| Axis | Score | Evidence | Verified (BenchLM) | Verified evidence |
| --- | --- | --- | --- | --- |
| Agentic | 36.5 | Observed 2026-11-21 · source benchlm:models | 35.4 | Observed 2026-11-21 · source benchlm:models |
| Coding | 65.8 | Observed 2026-11-21 · source benchlm:models | 65.8 | Observed 2026-11-21 · source benchlm:models |
| Knowledge | 73.4 | Observed 2026-11-21 · source benchlm:models | 73.5 | Observed 2026-11-21 · source benchlm:models |
| Reasoning | 21.4 | Observed 2026-11-21 · source benchlm:models | 21.4 | Observed 2026-11-21 · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | Unavailable | Unavailable · source benchlm:models | Unavailable | Unavailable · source benchlm:models |
| Math | 32.4 | Observed 2026-11-21 · source benchlm:models | 32.4 | Observed 2026-11-21 · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |
| Throughput | 41 tok/s | 2026-11-21 | 2026-11-21 | Observed 2026-11-21 · source openrouter:endpoints |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | $3.00 | Observed 2026-11-21 · source benchlm:pricing |
| Output / 1M tokens | $15.00 | Observed 2026-11-21 · source benchlm:pricing |
| Cache read / 1M tokens | $0.30 | Observed 2026-11-21 · source openrouter:pricing |
| Cache write / 1M tokens | $3.75 | Observed 2026-11-21 · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | $6.00 | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Unavailable · source livebench:table |
| Batch input / 1M tokens (OpenRouter batch) (base rate) | $1.50 | Observed 2026-11-21 · source openrouter:pricing |
| Batch output / 1M tokens (OpenRouter batch) (base rate) | $7.50 | Observed 2026-11-21 · source openrouter:pricing |
| Batch cache read / 1M tokens (OpenRouter batch) (base rate) | $0.15 | Observed 2026-11-21 · source openrouter:pricing |
| Batch cache write / 1M tokens (OpenRouter batch) (base rate) | $1.88 | Observed 2026-11-21 · source openrouter:pricing |

Batch API rate (asynchronous jobs), from OpenRouter's batch listing.

### Long-context batch price tiers (OpenRouter batch)

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.

| Prompt size | Batch USD per 1M tokens | Evidence |
| --- | --- | --- |
| Above 200K prompt tokens | $3.00 input / $11.25 output per 1M · cache read $0.30 · cache write $3.75 | Observed 2026-11-21 · source openrouter:pricing |

**Pricing note.** Anthropic's Claude Sonnet 4.6 announcement says pricing remains the same as Sonnet 4.5 at $3 input / $15 output per million tokens.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | $16.90 |
| Modelled tokens | 2.82M |

## Benchmark record

23 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| GPQA (Graduate-Level Google-Proof Q&A) | 83.4 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.0 | 50.0 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 77.2 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |

### Mathematics

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AIME 2025 (American Invitational Mathematics Examination 2025) | 87 | 15 problems | High school olympiad level | [American Invitational Mathematics Examination](https://www.maa.org/math-competitions/aime) |
| FrontierMath v2 (Tiers 1-3) (FrontierMath v2 Tiers 1-3) | 23.860 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | [FrontierMath v2 benchmark hub](https://epoch.ai/benchmarks/frontiermath-tiers-1-3-v2) |
| FrontierMath v2 (Tier 4) (FrontierMath v2 Tier 4) | 2.439 | 41 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | [FrontierMath Tier 4 v2 leaderboard](https://epoch.ai/benchmarks/frontiermath-tier-4-v2?view=graph&tab=leaderboard) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| ARC-AGI-2 (Abstraction and Reasoning Corpus for AGI v2) | 13.6 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | [ARC-AGI-2: A Harder General Intelligence Benchmark](https://arcprize.org/arc-agi/2/) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.0 | 50 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| Gert Labs (Gert Labs Composite Game Benchmark) | 48.51 | Novel game environments | Agentic coding and decision-making | [Gert Labs rankings](https://gertlabs.com/rankings) |
| OSWorld-Verified | 61.4 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | [OSWorld](https://os-world.github.io/) |
| JobBench | 27.7 | 130 tasks across 35 occupations | Professional multi-source workflows | [JobBench: Aligning Agent Work With Human Will](https://arxiv.org/abs/2605.26329) |
| VITA-Bench | 17.0 | Interactive consumer-service agent tasks | Long-horizon real-world workflows | [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://vitabench.github.io/) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Design Arena Website (Design Arena Website Elo) | 1177 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |

### external

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Chess Puzzles (Chess Puzzles (Epoch AI)) | 10.0 | 100 programmatically generated chess positions with a single best move | Novel chess positions, single best move | [Chess Puzzles (Epoch AI)](https://epoch.ai/benchmarks/chess-puzzles) |
| Mystery Game Puzzles (Mystery Game Puzzles (Epoch AI)) | 17.0 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | [Mystery Game Puzzles (Epoch AI)](https://epoch.ai/benchmarks/mystery-game-puzzles) |
| EBR-bench (Earthborne Rangers (EBR-bench)) | 2.4 | 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](https://epoch.ai/benchmarks/ebr-bench) |
| FailureSensorIQ | 64.2 | Multiple-choice questions on sensors and failure modes for 10 industrial assets | Industrial maintenance and reliability knowledge | [BenchLM](https://benchlm.ai/benchmarks/failuresensoriq) |
| Game Arena Go | 325 | Head-to-head Go games on a 13 x 13 board | Strategic planning and rule-following | [BenchLM](https://benchlm.ai/benchmarks/game-arena-go) |
| BinaryAudit (BinaryAudit (backdoor detection in compiled binaries)) | 26.3 | 19 backdoor and timebomb detection tasks on stripped binaries, three runs each (57 runs); 6 tooling and 8 clean-binary tasks reported alongside | Reverse engineering without source code or symbols | [We hid backdoors in ~40 MB binaries and asked AI + Ghidra to find them (Quesma)](https://quesma.com/blog/introducing-binaryaudit/) |
| OTelBench (OTelBench (OpenTelemetry instrumentation tasks)) | 21.7 | 23 OpenTelemetry instrumentation tasks in 11 languages, three attempts each (69 runs) | Distributed tracing and context propagation across services | [Benchmarking OpenTelemetry: can AI trace your failed login? (Quesma)](https://quesma.com/blog/introducing-otel-bench/) |
| CompileBench (CompileBench (building real projects from source, pass@1)) | 86.7 | 15 build tasks on cowsay, jq, GNU coreutils and curl, three attempts each (45 attempts) | Dependency resolution, legacy toolchains, static linking and cross-compilation | [CompileBench: can AI compile 22-year-old code? (Quesma)](https://quesma.com/blog/introducing-compilebench/) |
| NYT Connections (NYT Connections LLM Benchmark (extended version)) | 35.8 | 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)](https://github.com/lechmazur/nyt-connections) |
| SkillsBench official leaderboard (BenchFlow) (SkillsBench v1.1 official leaderboard (BenchFlow)) | 36.2 | 87 tasks in 8 domains (SkillsBench v1.1) | Multi-step agent tasks | [SkillsBench leaderboard](https://www.skillsbench.ai/leaderboard) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

**Retirement scheduled.** Scheduled to retire on 2026-11-30 (tentative), according to Anthropic model deprecations.

| Event | Type | Confirmation | Announced | Effective | Replacement | Source |
| --- | --- | --- | --- | --- | --- | --- |
| claude-sonnet-4-5-20250929 retirement | Retirement | confirmed | 2026-09-30 | 2026-11-30 (tentative) | [claude-sonnet-5-5](https://modelchoice.dev/models/claude-sonnet-5-5) | [Anthropic model deprecations](https://platform.claude.com/docs/en/about-claude/model-deprecations) |

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-11-21 05:17 UTC.
