# Claude Opus 5.5Extra high > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-opus-5-5-xhigh. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-opus-5-5-xhigh. Anthropic Canonical URL: https://benchize.com/models/claude-opus-5-5-xhigh Last updated: Thu, 22 Oct 2026 09:10:07 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 | | | --- | --- | --- | --- | --- | --- | --- | --- | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 92.5% | — | 5 / 243 | 0.67usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.925 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.6709066333333333 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup anthropic-claude-opus-5-5 modelType CoT Reasoning effort xhigh sourceModelVersion anthropic-claude-opus-5-5-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Opus 5.5 (XHigh) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/239` | | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 97.5% | — | 12 / 245 | 0.22usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.975 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.22304864 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup anthropic-claude-opus-5-5 modelType CoT Reasoning effort xhigh sourceModelVersion anthropic-claude-opus-5-5-xhigh thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Opus 5.5 (XHigh) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/237` | | | | | | | | | [Humanity's Sixth Sense](https://benchize.com/benchmarks/scale%3Ahss.md) | 44.6source score | CI 40.8–48.4 | 4 / 24 | — | — | [scale](https://labs.scale.com/leaderboard/hss) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 44.6 \| source_score \| reported \| Higher is better \| ### Configuration Reasoning effort xhigh Model configuration Claude-Opus-5.5 (xhigh) sourceModelVersion Not reported thinkingEnabled true ### Reported statistics Uncertainty Confidence interval: 40.8–48.4 contaminationWarning Not reported rank 4 reportedConfidenceHalfWidth 3.8 ### Source [Original source](https://labs.scale.com/leaderboard/hss) Source scale Original model label Claude-Opus-5.5 (xhigh) Observed 2026-10-22T03:30:05.638Z Evidence SHA-256 `9aef0db6386d5b31f1d49d426629277bbcbeeacd4cdf5a90febbef505a4e77f6` Source locator `/rows/3` | | | | | | | | | [Vibe Code Bench 1-100 / overall](https://benchize.com/benchmarks/vals-ai%3Avcb-1-100%3Aoverall.md) | 30.36% | SE ±4.83 pp | 1 / 16 | $44.12 | 8,909.32source duration | [Vals AI · 1.0](https://www.vals.ai/_astro/benchmark_view_vcb_1_100.ZqWqHxGl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.361 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 44.115239 \| USD \| per_test \| Lower is better \| \| `latency` \| 8909.323 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort xhigh harness OpenHands maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.83 pp sourcePopulation 25 stderr 4.829 tokenTotals {"cache_read_tokens":1892520053,"cache_write_tokens":210090234,"input_tokens":2102678416,"output_tokens":41082260,"reasoning_tokens":15418154} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vcb_1_100.ZqWqHxGl.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1.0 Observed 2026-10-22T02:10:23.806Z Evidence SHA-256 `4a3ebdcd9364ec3a21193d00de0bf723384d85187244abff859527fd3cc51891` Source locator `/tasks/overall/anthropic~1claude-opus-5-5` | | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 2,778.4 | Range 2,704.4–2,838.9 | 1 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 2778.4 \| rating \| reported \| Higher is better \| \| `overall` \| 85.83 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 79.83 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 85.4 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 84.87 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 82.89 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 98.64 \| source_score \| rubric \| Higher is better \| \| `slop` \| 88.55 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 97.27 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 88.37 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 82.5 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 83.15 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 84.42 \| source_score \| rubric \| Higher is better \| ### Configuration provider claude-code Reasoning effort xhigh scoreScope 10_task_current sourceConfiguration claude-opus-5-5-xhigh thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 2,704.4–2,838.9 interval [2704.4,2838.9] rank 1 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Claude Opus 5.5 (xhigh) Evaluated 2026-10-11 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/0` | | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 35.77% | — | 9 / 113 | $0.89 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/MBpMAlj5k_Qpj1iTRcXO7kAjUP_VB-QuD3gMvxxThCQ.C6QAp2jN.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 35.77 \| percent \| reported \| Higher is better \| \| `cost` \| 0.89 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Provider default Reasoning effort xhigh Model configuration Claude Opus 5.5 (default fallbacks, XHigh) thinkingEnabled true Fallback is enabled for refusals; this does not mean every task used a fallback model. ### Reported statistics rank 9 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/MBpMAlj5k_Qpj1iTRcXO7kAjUP_VB-QuD3gMvxxThCQ.C6QAp2jN.mjs) Source zapier Original model label Claude Opus 5.5 (default fallbacks, XHigh) Observed 2026-10-22T08:20:03.209Z Evidence SHA-256 `6f5ef9e0d3799e2bac5ae924407ac89f608f18c17f3ef238887356808b094579` Source locator `/rows/8` | | | | | | | | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 51.42% | — | 10 / 125 | $2.25 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5142 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.568 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 2.2545 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort xhigh 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 Opus 5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%205.5/xhigh/main` | | | | | | | | | [TapTap Maker public](https://benchize.com/benchmarks/taptap-maker%3Apublic.md) | 85.52% | Range 85.52–85.52% | 3 / 30 | $3.04 | — | [taptap maker](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `l2_pass_rate` \| 0.8552 \| score_fraction \| reported \| Higher is better \| \| `cost_per_case` \| 3.0435 \| USD \| per_case \| Lower is better \| ### Configuration datasetVersion 0.2.3 edition 2026-10-18-v6-voxel harness claude Reasoning effort xhigh reasoningMode adaptive ### Reported statistics Uncertainty Reported interval: 85.52–85.52% interval [0.8552,0.8552] intervalMethod bootstrap-case rank 3 rankInterval [1,3] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label claude-opus-5-5 Observed 2026-10-22T06:30:04.044Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/public/2` | | | | | | | | | [TapTap Maker heldout](https://benchize.com/benchmarks/taptap-maker%3Aheldout.md) | 75.93% | Range 75.93–75.93% | 3 / 30 | — | — | [taptap maker](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `l2_pass_rate` \| 0.7593 \| score_fraction \| reported \| Higher is better \| ### Configuration datasetVersion 0.2.3 edition 2026-10-18-v6-voxel harness claude Reasoning effort xhigh reasoningMode Not reported ### Reported statistics Uncertainty Reported interval: 75.93–75.93% interval [0.7593,0.7593] intervalMethod bootstrap-case rank 3 rankInterval [1,3] ### Source [Original source](https://maker.taptap.cn/leaderboard/data/editions/2026-10-18-v6-voxel.json) Source taptap maker Original model label claude-opus-5-5 Observed 2026-10-22T06:30:04.044Z Evidence SHA-256 `ad2d7f1adeae0548a4edc0b5e75d11449b443449ff76533d04bc1fb1b6d7035e` Source locator `/heldout/2` | | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 63.53% | — | 11 / 125 | $1.86 | — | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6353 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.692 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 1.8587 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort xhigh sourceVersion v1_1 subset extended ### Reported statistics flaggedRate 0 sampleSize 150 ### Source [Original source](https://cognition.com/data/frontiercode-leaderboard/data.json) Source frontiercode Original model label Claude Opus 5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Opus%205.5/xhigh/extended` | | | | | | | | | [WeirdML v3](https://benchize.com/benchmarks/weirdml%3Av3.md) | 0.31source score | Range 0.3–0.32 | 3 / 25 | — | — | [weirdml · b0120fe](https://htihle.github.io/assets/data/weirdml_v3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3120028142857143 \| source_score \| reported \| Higher is better \| \| `mean_final_best` \| 0.49830967402597404 \| source_score \| reported \| Higher is better \| ### Configuration budget {"kind":"equivalent_tokens","limit":50000000,"start":500000} harness claude_code Reasoning effort xhigh sourceConfiguration opus-5.5 thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 0.3–0.32 interval [0.29990502494039434,0.32383739437800335] intervalMethod {"assumptions":"Independent fresh runs; approximately normal scores; shared variance prior. Pool fitted within analysis mode, including incomplete models; pool estimation uncertainty is not propagated.","confidence":0.95,"draws":10000,"fixed_tasks":true,"method":"partially_pooled_variance","pool":{"degrees_of_freedom":1533,"fallback":false,"prior_df":4,"variance":0.0026383113392869583},"seed":20260915,"unit":"run"} runCount 77 taskCount 11 ### Source [Original source](https://htihle.github.io/assets/data/weirdml_v3.json) Source weirdml Original model label Claude Opus 5.5 (xhigh) Source version b0120fe Observed 2026-10-22T04:50:05.075Z Evidence SHA-256 `82c3a8de423b23ca0af9761429299a2f21edb0b819e947fdc863f8b5ea4a49b8` Source locator `/rows/2` | | | | | | | | --- Cite as: Claude Opus 5.5Extra high — Benchize, https://benchize.com/models/claude-opus-5-5-xhigh (retrieved 2026-10-22)