# Claude Sonnet 5.5High > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-sonnet-5-5-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-sonnet-5-5-high. Anthropic Canonical URL: https://benchize.com/models/claude-sonnet-5-5-high Last updated: Thu, 22 Oct 2026 06:30:09 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Anthropic ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Terminal-Bench 2.1 / hard](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Ahard.md) | 76.67% | SE ±5.09 pp | 8 / 43 | $0.78 | 1,381.96source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.776061 \| USD \| per_test \| Lower is better \| \| `latency` \| 1381.955 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.09 pp sourcePopulation 76 stderr 5.092 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/hard/anthropic~1claude-sonnet-5-5` | | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 67.36% | — | 62 / 243 | 0.28usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6736111111111112 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.2767547333333332 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup anthropic-claude-sonnet-5-5 modelType CoT Reasoning effort high sourceModelVersion anthropic-claude-sonnet-5-5-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Sonnet 5.5 (High) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/295` | | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 61.46% | — | 18 / 125 | $0.35 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6146 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.669 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.3459 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort high sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0.0067 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Sonnet 5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Sonnet%205.5/high/extended` | | | | | | | | | [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,709.99 | — | 6 / 90 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1709.9863830846468 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1700.0793862057865 rank 7 upper 1719.893379963507 variance 25.549821497243624 votes 5158 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Sonnet 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/218/row` | | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 29.38% | — | 21 / 113 | $0.36 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 29.38 \| percent \| reported \| Higher is better \| \| `cost` \| 0.36 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Provider default Reasoning effort high Model configuration Claude Sonnet 5.5 (default fallbacks, High) thinkingEnabled true Fallback is enabled for refusals; this does not mean every task used a fallback model. ### Reported statistics rank 21 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label Claude Sonnet 5.5 (default fallbacks, High) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/20` | | | | | | | | | [Terminal-Bench 2.1 / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aoverall.md) | 83.15% | SE ±1.72 pp | 6 / 43 | $0.63 | 465.83source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.146 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.625494 \| USD \| per_test \| Lower is better \| \| `latency` \| 465.828 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.72 pp sourcePopulation 76 stderr 1.716 tokenTotals {"cache_read_tokens":43257785,"cache_write_tokens":3960025,"input_tokens":47223436,"output_tokens":3585507,"reasoning_tokens":379696} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/overall/anthropic~1claude-sonnet-5-5` | | | | | | | | | [Terminal-Bench 2.1 / medium](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Amedium.md) | 86.06% | SE ±1.21 pp | 2 / 43 | $0.55 | 753.79source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.061 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.550492 \| USD \| per_test \| Lower is better \| \| `latency` \| 753.794 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.21 pp sourcePopulation 76 stderr 1.212 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/medium/anthropic~1claude-sonnet-5-5` | | | | | | | | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 49.38% | — | 19 / 125 | $0.42 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4938 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.5435 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.4175 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort high sourceVersion v1_1 subset main ### Reported statistics flaggedRate 0 sampleSize 100 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Sonnet 5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Sonnet%205.5/high/main` | | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 92% | — | 57 / 245 | 0.11usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.92 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.10514802000000001 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup anthropic-claude-sonnet-5-5 modelType CoT Reasoning effort high sourceModelVersion anthropic-claude-sonnet-5-5-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Sonnet 5.5 (High) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/295` | | | | | | | | | [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,702.96 | — | 5 / 89 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1702.960497384395 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1678.7323445995476 rank 6 upper 1727.1886501692425 variance 152.80741373659816 votes 790 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Sonnet 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/365/row` | | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 2,017.8 | Range 1,974.2–2,063.3 | 30 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 2017.8 \| rating \| reported \| Higher is better \| \| `overall` \| 80.96 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 74.19 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 80.98 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 75.27 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 81.82 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 85.95 \| source_score \| rubric \| Higher is better \| \| `slop` \| 84.58 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 94.96 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 84.45 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 77.55 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 79 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 80.45 \| source_score \| rubric \| Higher is better \| ### Configuration provider claude-code Reasoning effort high scoreScope 10_task_current sourceConfiguration claude-sonnet-5-5-high thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,974.2–2,063.3 interval [1974.2,2063.3] rank 30 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Claude Sonnet 5.5 (high) Evaluated 2026-10-08 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/29` | | | | | | | | | [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,745.85 | — | 6 / 81 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1745.8492483135683 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1733.464764990476 rank 6 upper 1758.2337316366602 variance 39.92634942582275 votes 3311 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Sonnet 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/512/row` | | | | | | | | | [ARC-AGI-3](https://benchize.com/benchmarks/arc-prize%3Av3_Semi_Private.md) | 1.2% | — | 29 / 65 | 5,487.23usd | — | [arc prize · v3](https://arcprize.org/media/data/leaderboard/v3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.01203076515291301 \| score_fraction \| v3_Semi_Private \| Higher is better \| \| `total_cost` \| 5487.227968 \| usd \| v3_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v3_Semi_Private harness standard modelGroup anthropic-claude-sonnet-5-5 modelType CoT Reasoning effort high sourceModelVersion anthropic-claude-sonnet-5-5-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v3.json) Source arc prize Original model label Claude Sonnet 5.5 (High) Source version v3 Observed 2026-10-22T05:20:04.578Z Evidence SHA-256 `3ce335487296bb2dcf4ba9546c5a2a02b1907db5b08887cd9ff4429fed824916` Source locator `/evaluations/103` | | | | | | | | | [Terminal-Bench 2.1 / easy](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Aeasy.md) | 91.67% | SE ±8.33 pp | 15 / 43 | $0.49 | 10,364.66source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.49001 \| USD \| per_test \| Lower is better \| \| `latency` \| 10364.662 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort high harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.33 pp sourcePopulation 76 stderr 8.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 2.1 Observed 2026-10-22T02:10:27.811Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/easy/anthropic~1claude-sonnet-5-5` | | | | | | | | | [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,709.99 | — | 6 / 90 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1709.9863830846468 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1700.0793862057865 rank 7 upper 1719.893379963507 variance 25.549821497243624 votes 5158 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Sonnet 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/6/row` | | | | | | | | --- Cite as: Claude Sonnet 5.5High — Benchize, https://benchize.com/models/claude-sonnet-5-5-high (retrieved 2026-10-22)