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 47 · bench-align-v5
Claude Sonnet 5 is built for agent work and reasoning. It ranks in the top quarter for knowledge (top 10% of 283 scored models) and reasoning (top 13% of 216 scored models), by BenchLM's published scores.
Every published price component, including cache reads and writes.
Lifecycle events the source associates with this model, plus what this profile does not claim.
Claude Sonnet 5 by Anthropic scores 61.6 overall, costs $2.00 per 1M input tokens and $10.00 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 | 147.1 s | 2026-11-21 | 2026-11-21 | |
| Throughput | 75 tok/s | 2026-11-21 | 2026-11-21 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
| $5.00 |
| Batch cache read / 1M tokens (OpenRouter batch) | $0.10 |
| Batch cache write / 1M tokens (OpenRouter batch) | $1.25 |
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 |
|---|---|---|---|---|---|
| HLE Humanity's Last Exam | 57.4 | #11 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| HLE-Verified HLE-Verified | 31.0 | #6 | 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 | 80.1 | #7 | 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 | 38.2 | #43 | Cross-benchmark intelligence index | Display-only external reference | Artificial Analysis |
| AA-GPQA Diamond Artificial Analysis GPQA Diamond | 91.1 | #30 | Graduate-level science questions | Graduate-level science reasoning | Artificial Analysis GPQA Diamond Benchmark Leaderboard |
| AA-HLE Artificial Analysis Humanity's Last Exam | 41.3 | #42 | Expert-level questions | Frontier expert reasoning | Artificial Analysis Humanity's Last Exam Benchmark Leaderboard |
| AA-Omniscience Index Artificial Analysis Omniscience Index | 16.5 | #40 | Knowledge questions | Broad factual knowledge | AA-Omniscience: Knowledge and Hallucination Benchmark |
| AA-Omniscience Accuracy Artificial Analysis Omniscience Accuracy | 40.1 | #59 | Knowledge questions | Broad knowledge | Artificial Analysis model benchmarks |
| AA-Omniscience Hallucination Rate Artificial Analysis Omniscience Hallucination Rate | 39.4 | #166 | Knowledge questions | Factuality | Artificial Analysis model benchmarks |
| HLE w/o tools Humanity's Last Exam without tools | 43.2 | #25 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
| GPQA Diamond (Vals) GPQA Diamond, Vals AI run | 88.9 | #32 | Graduate-level science questions | Expert reasoning | Vals AI GPQA Diamond, Vals AI run leaderboard |
| MMLU-Pro (Vals) MMLU-Pro, Vals AI run | 87.5 | #25 | 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 | 80.4 | #34 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 80.4 | #11 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| SWE-bench Verified Software Engineering Benchmark Verified | 85.2 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 65.614 | #35 | 285 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 29.268 | #32 | 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 |
|---|---|---|---|---|---|
| AA-LCR Artificial Analysis Long Context Reasoning | 82.0 | #29 | Long-context reasoning tasks | Long-context reasoning | Artificial Analysis model benchmarks |
| MLCR-AA Medical Long Context Reasoning (MLCR-AA) | 55.0 | #3 | Long, fragmented medical-record reasoning | Long-context medical reasoning | Medical Long Context Reasoning (MLCR-AA) |
| CritPt Critical Physics Tasks | 16.9 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Terminal-Bench 3.0 Terminal-Bench 3.0 | 14.6 | #9 | 74 professional computer-work tasks across 7 domains | Frontier autonomous knowledge work | Terminal-Bench 3.0 |
| AA EnterpriseOps-Gym Artificial Analysis EnterpriseOps-Gym | 44.7 | #14 | Enterprise operations workflows | Enterprise agent operations | Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard |
| AA Tau3 Banking Artificial Analysis Tau3-Banking | 37.3 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| AA-MMMU-Pro Artificial Analysis MMMU-Pro | 77.3 | #42 | Multimodal academic reasoning | Frontier multimodal | Artificial Analysis MMMU-Pro Benchmark Leaderboard |
| Design Arena Website Design Arena Website Elo | 1265 | #31 | Website generation comparisons | Design and website generation | OpenRouter Grok 4.3 benchmarks |
| CharXiv CharXiv Reasoning | 88.3 |
| Benchmark | Value | Rank | Tasks | Difficulty | Provenance |
|---|---|---|---|---|---|
| Chess Puzzles Chess Puzzles (Epoch AI) | 45.0 | #28 | 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) | 35.0 | #26 | 100 single-best-move positions from an undisclosed game | Unfamiliar game positions, single best move | Mystery Game Puzzles (Epoch AI) |
| MirrorCode MirrorCode (Epoch AI and METR) | 63.3 |
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 | 0.803 ± 0.0283 | 2026-08-06 | |
| xhigh | 0.9053 ± 0.0178 | 2026-07-01 | ||
| FrontierMath Tiers 1-3 (v2) Share of private research-level math problems solved, tiers 1-3. Unit: fraction (0–1); higher is better. | max | 0.6561 ± 0.0282 | 2026-06-30 | |
| FrontierMath Tier 4 (v2) Share of private research-level math problems solved, tier 4. Unit: fraction (0–1); higher is better. | max | 0.2927 ± 0.0719 | 2026-06-30 | |
| SimpleQA Verified Short factual questions answered correctly. Unit: fraction (0–1); higher is better. | max | 0.337 ± 0.015 | 2026-08-27 | |
| xhigh | 0.329 ± 0.0149 | 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 | 1,261 ± 7 | 14,701 | 47 | 2026-11-19 |
Source: LMArena, CC BY 4.0 (licence), leaderboard data read once a day.
| #9 |
| 500 verified issues |
| Professional software engineering |
| SWE-bench: Can Language Models Resolve Real-World GitHub Issues? |
| SWE-bench Pro SWE-bench Pro | 63.2 | #23 | 1,865 repository problems | Long-horizon professional engineering | SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks? |
| VulcanBench CII v1 VulcanBench Coding Intelligence Index v1 | 89.2 | #2 | 38 validated post-cutoff repository tasks | Mid-band frontier software engineering | CII v1 frontier results |
| FrontierCode 1.1 Main FrontierCode 1.1 Main | 42.7 | #12 | 100 private Main tasks (150 in Extended) | Frontier coding-agent quality | FrontierCode leaderboard |
| SWE Multilingual SWE Multilingual | 78.3 | #16 | Multilingual software-engineering tasks | Professional software engineering | MiniMax M2.7: Early Echoes of Self-Evolution |
| SWE Multimodal SWE-bench Multimodal | 28.1 | #7 | Multimodal software engineering tasks | Frontier multimodal coding | SWE-bench Multimodal |
| AA Coding Index Artificial Analysis Coding Index | 71.5 | #21 | Cross-benchmark coding index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-SciCode Artificial Analysis SciCode | 54.3 | #34 | Scientific coding subproblems | Scientific programming | Artificial Analysis SciCode Benchmark Leaderboard |
| LiveCodeBench (Vals) LiveCodeBench, Vals AI run | 82.4 | #50 | Competitive programming problems (easy, medium, hard) | Frontier coding | Vals AI LiveCodeBench, Vals AI run leaderboard |
| SWE-bench (Vals) SWE-bench, Vals AI run | 79.6 | #25 | Real repository issues by human time bucket | Frontier coding agents | Vals AI SWE-bench, Vals AI run leaderboard |
| #44 |
| Research-level physics questions |
| Research-level physics reasoning |
| CritPt Benchmark Leaderboard |
| #23 |
| Banking tool-use workflows |
| Agentic banking workflows |
| Artificial Analysis Tau3-Banking Benchmark Leaderboard |
| Terminal-Bench 2.0 Terminal-Bench 2.0 | 80.4 | #12 | Terminal-based software tasks | Professional software engineering | Terminal-Bench 2.0 |
| Terminal-Bench 2.1 Terminal-Bench 2.1 | 80.4 | #36 | Terminal-based software-agent tasks | Professional software engineering | Terminal-Bench |
| BrowseComp BrowseComp | 84.7 | #17 | Research questions requiring browsing | Hard web research | BrowseComp |
| 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 | 1603 | #28 | Agentic real-world work tasks | Professional agentic workflows | DeepSeek-V4 Technical Report |
| GDPval-AA GDPval-AA normalized | 48.2 | #30 | Economically valuable tasks | Professional agentic workflows | Artificial Analysis model benchmarks |
| AA Agentic Index Artificial Analysis Agentic Index | 44.3 | #14 | Cross-benchmark agentic index | Display-only external reference | Artificial Analysis model leaderboards |
| AA-AnalystAgent Artificial Analysis AnalystAgent | 46.3 | #17 | Spreadsheet and document analysis questions | Business and data analysis | AA-AnalystAgent Benchmark Leaderboard |
| OSWorld-Verified OSWorld-Verified | 81.2 | #9 | 369 real-world computer tasks (361 when eight Google Drive tasks are excluded) | Multi-step desktop and cross-application workflows | OSWorld |
| Terminal-Bench 2.1 (Vals) Terminal-Bench 2.1, Vals AI run | 74.5 | #17 | 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 | 0 | #28 | 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 | 12.10 | #40 | 66 professional computer-work tasks | Frontier autonomous knowledge work | Terminal-Bench 4.1 |
| OSWorld 2.1 OSWorld 2.1 (all 108 tasks) | 57.0 | #12 | 108 long-horizon computer-use workflows | Long-horizon professional workflows | OSWorld 2.1 release (xlang-ai/OSWorld-V2, tag osworld-v2.1) |
| #16 |
| Scientific chart reasoning |
| Scientific visualization reasoning |
| CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs |
| CharXiv w/o tools CharXiv Reasoning without tools | 77 | #18 | 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) | 61.16 | #28 | 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 |
| #11 |
| 30 reimplementation tasks (15 programs in two languages), three attempts each |
| Days-long software engineering without source code |
| MirrorCode (Epoch AI) |
| DAYJOB DAYJOB | 1.7 | #13 | 130 long-horizon tasks: 80 finance and 50 healthcare | Long-horizon professional work | BenchLM |
| DAYJOB Healthcare DAYJOB Healthcare | 0.0 | #15 | 50 long-horizon healthcare tasks across five subfields | Long-horizon clinical and healthcare operations work | BenchLM |
| Landing Page Arena Landing Page Arena | 1412 | #10 | 12 client briefs for small-business landing pages, rated by human votes | Marketing page design and copy | BenchLM |
| Joke Arena Joke Arena | 1458 | #18 | 100 joke prompts in 10 categories, rated by human votes | Humour writing | BenchLM |
| Pelican Arena Pelican Arena | 1221 | #24 | 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 | 1157 | #13 | 20 famous landmarks built as three.js web pages, rated by human votes | 3D scenes in browser code | BenchLM |
| Game Arena Go Game Arena Go | 1118 | #13 | 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) | 67 | #21 | 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) | 75.1 | #47 | 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) |