# Claude Haiku 5.5Low

> Source: Benchize (https://benchize.com) — https://benchize.com/models/claude-haiku-5-5-low. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/claude-haiku-5-5-low.

Anthropic

Canonical URL: https://benchize.com/models/claude-haiku-5-5-low
Last updated: Fri, 23 Oct 2026 05:50:59 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 |  |
| --- | --- | --- | --- | --- | --- | --- |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,497.5 | Range 1,444–1,543 | 80 / 126 | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1497.5 \| rating \| reported \| Higher is better \| \| `overall` \| 75.23 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 72.56 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 75.7 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 70.68 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 79.09 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 77.91 \| source_score \| rubric \| Higher is better \| \| `slop` \| 83.54 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 94.51 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 80.73 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 72.3 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 75.2 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 65.5 \| source_score \| rubric \| Higher is better \| ### Configuration provider claude-code Reasoning effort low scoreScope 10_task_current sourceConfiguration claude-haiku-5-5-low thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,444–1,543 interval [1444,1543] rank 81 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Claude Haiku 5.5 (low) Evaluated 2026-10-08 Observed 2026-10-23T04:40:19.855Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/80` |  |  |  |  |  |  |
| [FrontierCode 1.1 main](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Amain.md) | 34.76% | — | 93 / 125 | $0.06 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.3476 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.385 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.0596 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort low 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 2026-10-23T05:40:09.900Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Haiku%205.5/low/main` |  |  |  |  |  |  |
| [Chess Puzzles](https://benchize.com/benchmarks/epoch-ai%3Achess_puzzles.md) | 24% | SE ±4.29 pp | 56 / 78 | — | [epoch ai · Chess Puzzles](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.24 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.24 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Chess Puzzles reasoningBudget Not reported Reasoning effort low sourceModelVersion claude-haiku-5-5_low ### Reported statistics Uncertainty Standard error: ±4.29 pp standardError 0.04292346959909278 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) Source epoch ai Original model label claude-haiku-5-5 Source version Chess Puzzles Evaluated 2026-10-13T07:50:03.000Z Observed 2026-10-23T03:00:09.937Z Evidence SHA-256 `a5b99d6d35252907b04e9a802873a9754ecc0248be92a1ebbd2ef0450e4bb015` Source locator `/rows/153` |  |  |  |  |  |  |
| [FrontierCode 1.1 extended](https://benchize.com/benchmarks/frontiercode%3Av1_1%3Aextended.md) | 48.19% | — | 93 / 125 | $0.05 | [frontiercode](https://cognition.com/data/frontiercode-leaderboard/data.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.4819 \| score_fraction \| blocking_criteria_adjusted \| Higher is better \| \| `correct` \| 0.53 \| score_fraction \| raw_rubric \| Higher is better \| \| `cost` \| 0.0486 \| USD \| per_rollout \| Lower is better \| ### Configuration harness claude-code Reasoning effort low 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 2026-10-23T05:40:09.900Z Evidence SHA-256 `ff0040778b7bdf69c705ad7474f771fb5e53cfaf5cf8573b3a4614153543d75f` Source locator `/v1_1/data/Claude%20Haiku%205.5/low/extended` |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 50.33% | — | 166 / 245 | 0.00528usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.5033333333333334 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.005280606 \| 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 low sourceModelVersion anthropic-claude-haiku-5-5-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Claude Haiku 5.5 (Low) Source version v1 Observed 2026-10-23T05:20:16.177Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/274` |  |  |  |  |  |  |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 84.75% | — | 101 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 84.75 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 88.61 \| percent \| category \| Higher is better \| \| `language` \| 99.9 \| percent \| category \| Higher is better \| \| `utility` \| 89.31 \| percent \| category \| Higher is better \| \| `reasoning` \| 81.2 \| percent \| category \| Higher is better \| \| `text_editing` \| 95.77 \| percent \| category \| Higher is better \| \| `rule_following` \| 33.56 \| percent \| category \| Higher is better \| \| `hallucination` \| 89.61 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort low Model configuration Claude Haiku 5.5 (Reasoning, Low) thinkingEnabled true ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Claude Haiku 5.5 (Reasoning, Low) Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/130` |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 2.78% | — | 186 / 243 | 0.00799usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.027777777777777776 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.007986432500000003 \| 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 low sourceModelVersion anthropic-claude-haiku-5-5-low thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Claude Haiku 5.5 (Low) Source version v2 Observed 2026-10-23T05:20:16.411Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/275` |  |  |  |  |  |  |
| [BullshitBench v2](https://benchize.com/benchmarks/bullshitbench%3Av2.md) | 53% | — | 66 / 197 | — | [bullshitbench · v2](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=92793d458f1bed8d6937610eb459978496afed07) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `green_rate` \| 0.53 \| score_fraction \| all_attempts \| Higher is better \| \| `red_rate` \| 0.08 \| score_fraction \| all_attempts \| Lower is better \| \| `refusal_rate` \| 0.0 \| score_fraction \| all_attempts \| Lower is better \| \| `avg_score` \| 1.46 \| score \| judge_grade_0_to_2 \| Higher is better \| ### Configuration Reasoning effort low suite v2 thinkingEnabled true ### Reported statistics acceptedCount 8 answeredCount 100 clearCount 53 errorCount 0 partialCount 39 rank 53 refusalCount 0 sampleSize 100 ### Source [Original source](https://api.github.com/repos/petergpt/bullshit-benchmark/contents/data/v2/latest/leaderboard.csv?ref=92793d458f1bed8d6937610eb459978496afed07) Source bullshitbench Original model label anthropic/claude-haiku-5.5 Source version v2 Observed 2026-10-23T03:10:10.254Z Evidence SHA-256 `98b485e08764d1c97144bc4f7b28ced1a96d50850947c775870dfda0e5d749b5` Source locator `/rows/52` |  |  |  |  |  |  |

---
Cite as: Claude Haiku 5.5Low — Benchize, https://benchize.com/models/claude-haiku-5-5-low (retrieved 2026-10-23)