# Claude Sonnet 4.5 > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-sonnet-4-5. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-sonnet-4-5. Anthropic Canonical URL: https://benchize.com/models/claude-sonnet-4-5 Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Anthropic ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [τ-bench telecom (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Atelecom.md) | 98% | — | 2 / 10 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-sonnet-4-5_anthropic_2025-10-02/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 98 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-09-29","notes":"Scores were achieved using extended thinking with tool use and a prompt addendum to the Airline and Telecom Agent Policy instructing Claude to better target its known failure modes when using the vanilla prompt. A prompt addendum was also added to the Telecom User prompt to avoid failure modes from the user ending the interaction incorrectly.","tau2_bench_version":"0.1.3","user_simulator":null,"verification":{"details":"Unverified submission - no trajectory data available, unknown evaluation methodology, telecom domain omitted, incomplete evaluation (Pass^1 only)","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission claude-sonnet-4-5_anthropic_2025-10-02 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-sonnet-4-5_anthropic_2025-10-02/submission.json) Source sierra Original model label Claude-Sonnet-4.5 Evaluated 2025-09-29 Observed 2026-10-21T16:55:01.251Z Evidence SHA-256 `20e3ef4c1c495dbf3ec155ffa4899d6478b75deccf16862d886def20a79dda11` Source locator `/results/telecom` | | | | | | | | [τ-bench retail (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aretail.md) | 86.2% | — | 1 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-sonnet-4-5_anthropic_2025-10-02/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 86.2 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-09-29","notes":"Scores were achieved using extended thinking with tool use and a prompt addendum to the Airline and Telecom Agent Policy instructing Claude to better target its known failure modes when using the vanilla prompt. A prompt addendum was also added to the Telecom User prompt to avoid failure modes from the user ending the interaction incorrectly.","tau2_bench_version":"0.1.3","user_simulator":null,"verification":{"details":"Unverified submission - no trajectory data available, unknown evaluation methodology, telecom domain omitted, incomplete evaluation (Pass^1 only)","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission claude-sonnet-4-5_anthropic_2025-10-02 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-sonnet-4-5_anthropic_2025-10-02/submission.json) Source sierra Original model label Claude-Sonnet-4.5 Evaluated 2025-09-29 Observed 2026-10-21T16:55:01.251Z Evidence SHA-256 `20e3ef4c1c495dbf3ec155ffa4899d6478b75deccf16862d886def20a79dda11` Source locator `/results/retail` | | | | | | | | [DesignArena Browser game generation](https://benchize.com/benchmarks/designarena%3Agame-dev.md) | 1,166elo | — | 60 / 117 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=game-dev) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1166 \| elo \| game-dev \| Higher is better \| ### Configuration arenaType models category gamedev inputModality Not reported sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics averageGenerationTimeMs 96559 battles 6024 losses 2947 standardError Not reported winRate 51.1 wins 3077 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=game-dev) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:38:01.100Z Evidence SHA-256 `53db6a89112ce8cdf644568c666d4b8309aece764cfcedb291ffd52ae3934e30` Source locator `/data/92` | | | | | | | | [DesignArena Full-stack application development](https://benchize.com/benchmarks/designarena%3Afullstack.md) | 1,050elo | SE ±14.33 | 27 / 31 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=fullstack) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1050 \| elo \| fullstack \| Higher is better \| ### Configuration arenaType agents category fullstack inputModality Not reported sourceModelVersion claude-sonnet-4-5-20250929 variationName public ### Reported statistics Uncertainty Standard error: ±14.33 averageGenerationTimeMs Not reported battles 629 losses 354 standardError 14.3337 winRate 43.7 wins 275 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=fullstack) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:38:00.857Z Evidence SHA-256 `aa171459dd44cfad57fba8da746c40b27832b57dc731b1198bdb71c73ddd0f97` Source locator `/data/40` | | | | | | | | [Spiral-Bench v1.0](https://benchize.com/benchmarks/eq-bench%3Aspiral-bench-v1.0.md) | 76.4% | CI 76.4–76.4% | 3 / 11 | — | [eq bench · spiral-bench-v1.0](https://eqbench.com/spiral-bench_v1.0.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score_norm` \| 76.4 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol spiral-bench-v1.0 sourceModelVersion claude-sonnet-4.5 ### Reported statistics Uncertainty Confidence interval: 76.4–76.4% confidenceIntervalHigh 76.4 confidenceIntervalLow 76.4 ### Source [Original source](https://eqbench.com/spiral-bench_v1.0.js) Source eq bench Original model label claude-sonnet-4.5 Source version spiral-bench-v1.0 Observed 2026-10-21T16:35:04.619Z Evidence SHA-256 `d939ed9ba6d42226765fb4acf3e440127472566e1b5c2894d4ca25baa5ae75d2` Source locator `/leaderboardDataDelusion/13` | | | | | | | | [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,511elo | CI 1,481.9–1,540.1 | 16 / 50 | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1511.0 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 72.2 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion claude-sonnet-4.5 ### Reported statistics Uncertainty Confidence interval: 1,481.9–1,540.1 confidenceIntervalHigh 1540.1 confidenceIntervalLow 1481.9 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label claude-sonnet-4.5 Source version eqbench3 Observed 2026-10-21T16:35:00.608Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/22` | | | | | | | | [Judgemark v2.1](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v2.md) | 84.56% | — | 7 / 39 | — | [eq bench · judgemark-v2](https://eqbench.com/judgemark-v2.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `judgemark_score` \| 84.56 \| percent \| overall \| Higher is better \| \| `stability` \| 0.817 \| score_fraction \| overall \| Higher is better \| \| `separability` \| 0.867 \| score_fraction \| overall \| Higher is better \| \| `human_corr` \| 0.79 \| correlation \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v2 sourceModelVersion claude-sonnet-4.5 ### Source [Original source](https://eqbench.com/judgemark-v2.js) Source eq bench Original model label claude-sonnet-4.5 Source version judgemark-v2 Observed 2026-10-21T16:35:03.564Z Evidence SHA-256 `070cc3fbd6f0333dde2b52bec4329ea3fba7eccbf016bbbbef95e0f8b2197781` Source locator `/leaderboardDataV2/22` | | | | | | | | [Spiral-Bench v1.2](https://benchize.com/benchmarks/eq-bench%3Aspiral-bench-v1.2.md) | 70.3% | CI 70.3–70.3% | 1 / 16 | — | [eq bench · spiral-bench-v1.2](https://eqbench.com/spiral-bench.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score_norm` \| 70.3 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol spiral-bench-v1.2 sourceModelVersion claude-sonnet-4.5 ### Reported statistics Uncertainty Confidence interval: 70.3–70.3% confidenceIntervalHigh 70.3 confidenceIntervalLow 70.3 ### Source [Original source](https://eqbench.com/spiral-bench.js) Source eq bench Original model label claude-sonnet-4.5 Source version spiral-bench-v1.2 Observed 2026-10-21T16:35:04.308Z Evidence SHA-256 `2f0402654b01e7363c0d02bbc708afd7849e669dc5da63d9f85c995ed8f0a97f` Source locator `/leaderboardDataDelusion/2` | | | | | | | | [DesignArena Data visualization generation](https://benchize.com/benchmarks/designarena%3Adata-viz.md) | 1,167elo | — | 64 / 99 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=data-viz) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1167 \| elo \| data-viz \| Higher is better \| ### Configuration arenaType models category dataviz inputModality Not reported sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics averageGenerationTimeMs 73737 battles 1820 losses 958 standardError Not reported winRate 47.4 wins 862 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=data-viz) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:37:58.264Z Evidence SHA-256 `a895f6f1a25fa8eb01f821c2097ddec4f884de7bd22f1b8a22e82e6679b71849` Source locator `/data/93` | | | | | | | | [DesignArena 3D design generation](https://benchize.com/benchmarks/designarena%3A3d-design.md) | 1,158elo | — | 50 / 110 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=3d-design) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1158 \| elo \| 3d-design \| Higher is better \| ### Configuration arenaType models category 3d inputModality Not reported sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics averageGenerationTimeMs 66440 battles 7375 losses 3614 standardError Not reported winRate 51 wins 3761 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=3d-design) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:37:58.515Z Evidence SHA-256 `bcc0267f7bc7e9ec112306b3a35413cf78bbccbfaa838356232d5d5ed0b83d0f` Source locator `/data/79` | | | | | | | | [DesignArena SVG generation](https://benchize.com/benchmarks/designarena%3Asvgs.md) | 1,108elo | — | 55 / 77 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=svgs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1108 \| elo \| svgs \| Higher is better \| ### Configuration arenaType models category svg inputModality Not reported sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics averageGenerationTimeMs 27618 battles 4915 losses 2507 standardError Not reported winRate 49 wins 2408 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=svgs) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:38:03.249Z Evidence SHA-256 `8cbc34a474a66ef5c64f3ffe557df9b55bf7e13368c07c0214223e3ed8f3f21e` Source locator `/data/87` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 3.75% | — | 151 / 212 | 0.13usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.0375 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.1295 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup claude-sonnet-4-5-20250929 modelType Base LLM sourceModelVersion claude-sonnet-4-5-20250929 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Sonnet 4.5 Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/77` | | | | | | | | [DesignArena Mobile application development](https://benchize.com/benchmarks/designarena%3Amobileapps.md) | 1,137elo | SE ±17.46 | 24 / 33 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=mobileapps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1137 \| elo \| mobileapps \| Higher is better \| ### Configuration arenaType agents category mobileapps inputModality Not reported sourceModelVersion claude-sonnet-4-5-20250929 variationName public ### Reported statistics Uncertainty Standard error: ±17.46 averageGenerationTimeMs Not reported battles 414 losses 195 standardError 17.4621 winRate 52.9 wins 219 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=mobileapps) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:38:02.538Z Evidence SHA-256 `40af33d0e93e729486da375cbe954633e2458af0dd6ca6d9fbdcda90da650f7d` Source locator `/data/35` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 25.5% | — | 176 / 213 | 0.08usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.255 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.0808 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup claude-sonnet-4-5-20250929 modelType Base LLM sourceModelVersion claude-sonnet-4-5-20250929 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Sonnet 4.5 Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/74` | | | | | | | | [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 71.4% | — | 33 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 71.4 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 15.63 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 14.88 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 15.16 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 14.66 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 14.67 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 14.23 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 13.85 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 13.09 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 13.77 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion claude-sonnet-4.5 ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label claude-sonnet-4.5 Source version longform-writing Observed 2026-10-21T16:35:02.575Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/7` | | | | | | | | [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,677.6elo | — | 32 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1677.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.14 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion claude-sonnet-4.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label claude-sonnet-4.5 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/36` | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,569 | — | 44 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1569 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_anthropic_claude_sonnet_4_5 ### Reported statistics coverageCount 27 draws 5 judged 90 losses 37 rank 54 ratingDeviation 28 wins 48 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Claude Sonnet 4.5 Observed 2026-10-21T16:32:23.388Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/52` | | | | | | | | [DesignArena ASCII art generation](https://benchize.com/benchmarks/designarena%3Aascii.md) | 1,175elo | — | 30 / 65 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ascii) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1175 \| elo \| ascii \| Higher is better \| ### Configuration arenaType models category ascii inputModality Not reported sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics averageGenerationTimeMs 56892 battles 420 losses 203 standardError Not reported winRate 51.7 wins 217 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ascii) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:38:03.513Z Evidence SHA-256 `0603b8c65b44ee887f5b566feb469465f59635137a6ac5c6d94c23bcf3776311` Source locator `/data/40` | | | | | | | | [Slop Score](https://benchize.com/benchmarks/eq-bench%3Aslop-score.md) | 19.49% | — | 2 / 16 | — | [eq bench · slop-score](https://eqbench.com/data/leaderboard_results.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 19.488948709359388 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 9.72238118855951 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.22891152569531875 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.17102987605114325 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 150 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label claude-sonnet-4-5 Source version slop-score Evaluated 2025-11-01T09:06:17.484557+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/2` | | | | | | | | [DesignArena Agentic web applications](https://benchize.com/benchmarks/designarena%3Awebapps.md) | 1,059elo | SE ±9.42 | 35 / 39 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=webapps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1059 \| elo \| webapps \| Higher is better \| ### Configuration arenaType agents category agon_webapps inputModality text sourceModelVersion claude-sonnet-4-5-20250929 variationName public ### Reported statistics Uncertainty Standard error: ±9.42 averageGenerationTimeMs Not reported battles 1503 losses 854 standardError 9.4227 winRate 43.2 wins 649 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=webapps) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:38:00.309Z Evidence SHA-256 `f955787274cf4ac627ada7cd33eaae2e08ef7297db92d3391340fcaa0b44a35f` Source locator `/data/47` | | | | | | | | [DesignArena Website generation](https://benchize.com/benchmarks/designarena%3Awebsite.md) | 1,190elo | — | 58 / 123 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=website) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1190 \| elo \| website \| Higher is better \| ### Configuration arenaType models category website inputModality text sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics averageGenerationTimeMs 108057 battles 29170 losses 14057 standardError Not reported winRate 51.8 wins 15113 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=website) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:37:57.757Z Evidence SHA-256 `51873e97776a3c5ae706b24cc2c60384793dd18398df970e213a8e7c276d8ac0` Source locator `/data/91` | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 87.54% | — | 80 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 87.54 \| percent \| reported \| Higher is better \| \| `tooling` \| 97.75 \| percent \| category \| Higher is better \| \| `creative_writing` \| 84.19 \| percent \| category \| Higher is better \| \| `language` \| 92.39 \| percent \| category \| Higher is better \| \| `utility` \| 83.78 \| percent \| category \| Higher is better \| \| `reasoning` \| 78.61 \| percent \| category \| Higher is better \| \| `text_editing` \| 99.02 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.8 \| percent \| category \| Higher is better \| \| `hallucination` \| 87.78 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 4.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Sonnet 4.5 Observed 2026-10-21T16:31:48.370Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/103` | | | | | | | | [τ-bench airline (legacy)](https://benchize.com/benchmarks/sierra%3Alegacy%3Aairline.md) | 70% | — | 2 / 14 | — | [sierra](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-sonnet-4-5_anthropic_2025-10-02/submission.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 70 \| percent \| consistent_success_across_k_trials \| Higher is better \| ### Configuration benchmarkVersion 0.1.3 harness tau-bench methodology {"evaluation_date":"2025-09-29","notes":"Scores were achieved using extended thinking with tool use and a prompt addendum to the Airline and Telecom Agent Policy instructing Claude to better target its known failure modes when using the vanilla prompt. A prompt addendum was also added to the Telecom User prompt to avoid failure modes from the user ending the interaction incorrectly.","tau2_bench_version":"0.1.3","user_simulator":null,"verification":{"details":"Unverified submission - no trajectory data available, unknown evaluation methodology, telecom domain omitted, incomplete evaluation (Pass^1 only)","modified_prompts":null,"omitted_questions":null}} modality text Reasoning effort unknown retrieval Not reported sourceSubmission claude-sonnet-4-5_anthropic_2025-10-02 ### Source [Original source](https://sierra-tau-bench-public.s3.us-west-2.amazonaws.com/submissions/claude-sonnet-4-5_anthropic_2025-10-02/submission.json) Source sierra Original model label Claude-Sonnet-4.5 Evaluated 2025-09-29 Observed 2026-10-21T16:55:01.251Z Evidence SHA-256 `20e3ef4c1c495dbf3ec155ffa4899d6478b75deccf16862d886def20a79dda11` Source locator `/results/airline` | | | | | | | | [DesignArena Overall frontend coding](https://benchize.com/benchmarks/designarena%3Acode.md) | 1,183elo | SE ±1.79 | 51 / 116 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=code) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1183 \| elo \| code \| Higher is better \| ### Configuration arenaType models category allcategories inputModality text sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics Uncertainty Standard error: ±1.79 averageGenerationTimeMs 98423 battles 45449 losses 22062 standardError 1.7942 winRate 51.5 wins 23387 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=code) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:37:57.301Z Evidence SHA-256 `0c897b58670f5e352bd123db999a40c0d1781a443964c502b90774a76a3a7758` Source locator `/data/82` | | | | | | | | [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $3,838.74 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 3838.7400000000002 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 3006.3255724953715 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Claude Sonnet 4.5 thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 2160.111521250415 positiveBalanceRuns 5 runCount 5 standardDeviation 2464.365408416536 standardError 1102.0977149236812 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label Claude Sonnet 4.5 Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/15` | | | | | | | | [DesignArena UI component generation](https://benchize.com/benchmarks/designarena%3Aui-components.md) | 1,162elo | — | 65 / 112 | — | [designarena · public](https://www.designarena.ai/api/leaderboard#board=ui-components) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1162 \| elo \| ui-components \| Higher is better \| ### Configuration arenaType models category uicomponent inputModality Not reported sourceModelVersion claude-sonnet-4-5 variationName public ### Reported statistics averageGenerationTimeMs 84444 battles 2771 losses 1460 standardError Not reported winRate 47.3 wins 1311 ### Source [Original source](https://www.designarena.ai/api/leaderboard#board=ui-components) Source designarena Original model label Claude Sonnet 4.5 Source version public Observed 2026-10-21T16:37:57.993Z Evidence SHA-256 `46482ec1b4012638eace65493daea4750e2088098018fd9d5fc46126fc1f8557` Source locator `/data/98` | | | | | | | --- Cite as: Claude Sonnet 4.5 — Benchize, https://benchize.com/models/claude-sonnet-4-5 (retrieved 2026-10-21)