# Claude Haiku 5.5High > Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-haiku-5-5-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-haiku-5-5-high. Anthropic Canonical URL: https://benchize.com/models/claude-haiku-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 | Source | | | --- | --- | --- | --- | --- | --- | --- | | [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,604.76 | — | 22 / 81 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1604.7648624369513 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1591.074149124102 rank 32 upper 1618.4555757498006 variance 48.79282578922965 votes 2203 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Haiku 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/538/row` | | | | | | | | [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,586.15 | — | 24 / 90 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1586.154813685055 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1575.2430780821367 rank 34 upper 1597.0665492879732 variance 30.99498899391527 votes 3514 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Haiku 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/245/row` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 81.5% | — | 110 / 245 | 0.02usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.815 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.016372071000000002 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup anthropic-claude-haiku-5-5 modelType CoT Reasoning effort high sourceModelVersion anthropic-claude-haiku-5-5-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Haiku 5.5 (High) Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/272` | | | | | | | | [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,586.15 | — | 24 / 90 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1586.154813685055 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1575.2430780821367 rank 34 upper 1597.0665492879732 variance 30.99498899391527 votes 3514 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Haiku 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/33/row` | | | | | | | | [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 97.22% | SE ±1.31 pp | 26 / 124 | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9722222222222222 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9722222222222222 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort high sourceModelVersion claude-haiku-5-5_high ### Reported statistics Uncertainty Standard error: ±1.31 pp standardError 0.013109441770118595 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label claude-haiku-5-5 Source version OTIS Mock AIME 2024-2025 Evaluated 2026-10-07T21:16:25.000Z Observed 2026-10-22T03:00:05.281Z Evidence SHA-256 `b7c9da8c0587c82f1e0d814ceb496c24308380b997a16203b6e5d39eb07f4f50` Source locator `/rows/7` | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,705 | Range 1,666.7–1,743 | 57 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1705 \| rating \| reported \| Higher is better \| \| `overall` \| 77.97 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 74.69 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 77.42 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 72.89 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 78.34 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 84.94 \| source_score \| rubric \| Higher is better \| \| `slop` \| 85.39 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 96.1 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 82.29 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 74.73 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 77.18 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 72.81 \| source_score \| rubric \| Higher is better \| ### Configuration provider claude-code Reasoning effort high scoreScope 10_task_current sourceConfiguration claude-haiku-5-5-high thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,666.7–1,743 interval [1666.7,1743] rank 57 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Claude Haiku 5.5 (high) Evaluated 2026-10-08 Observed 2026-10-22T04:40:14.102Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/56` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 30.69% | — | 121 / 243 | 0.05usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3069444444444444 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.046677990833333315 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup anthropic-claude-haiku-5-5 modelType CoT Reasoning effort high sourceModelVersion anthropic-claude-haiku-5-5-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Haiku 5.5 (High) Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/273` | | | | | | | | [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,568.85 | — | 25 / 89 | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1568.8460806000896 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev Reasoning effort high thinkingEnabled true ### Reported statistics lower 1539.1240672886402 rank 34 upper 1598.568093911539 variance 229.9642184180323 votes 449 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label Claude Haiku 5.5 (High) Observed 2026-10-22T00:45:04.817Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/393/row` | | | | | | | | [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 55.88% | — | 59 / 125 | $0.2 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5588 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.616 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.1998 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort high 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 Haiku 5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Haiku%205.5/high/extended` | | | | | | | | [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 41.89% | — | 62 / 125 | $0.26 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4189 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.466 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.256 \| 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 Haiku 5.5 Observed 2026-10-22T05:40:03.220Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Haiku%205.5/high/main` | | | | | | | --- Cite as: Claude Haiku 5.5High — Benchize, https://benchize.com/models/claude-haiku-5-5-high (retrieved 2026-10-22)