Work Automations
Private 657 tasks; 50 turns; objective completion
- 01
- 02
- 03
- 04
- 05
- 37
Claude Haiku 5.5
Across the task benchmarks we track, Claude Haiku 5.5’s strongest relative results are in work automations. On AutomationBench-AA, it scores 36%, ranking #37 among 55 models with reported results in our dataset.
Updated: Data as of:
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| Agent Index ↗v1.2 Preview | Overall agent capability | 45.4 / 100#10 of 26 |
| AA-Briefcase ↗1.1 / combined Elo | Business deliverables | 1,576 Elo#10 of 57 |
| LiveBench: Design ↗2.0 / 2026-10-25 | Documents and presentations | 83.1%#5 of 25 |
| LiveBench: Coding ↗2.0 / 2026-10-25 | Coding with LiveBench | 91.4%#8 of 25 |
Model details
| Model | Claude Haiku 5.5 |
|---|---|
| Agent Index v1.2 | 45.4 / 100 · Rank 10 · Preview |
| Creator | Anthropic (opens in a new tab) |
| Availability | Proprietary |
| Context size | Not reported |
| Max output | Not reported |
| Knowledge cutoff | 2026-06 |
| License | Not reported |
Pricing and performance
Per provider and reported configuration. Prices are USD per 1M tokens.
| Provider / configuration | Contexttokens | InputUSD / 1M tokens | OutputUSD / 1M tokens | LatencyTTFT · seconds | Speedtokens / sec |
|---|---|---|---|---|---|
| Standard API, prompts above 100K input tokens | Not reported | $0.50 (opens in a new tab) | $2.50 (opens in a new tab) | Not reported | Not reported |
| Standard API, prompts up to 100K input tokens | Not reported | $0.10 (opens in a new tab) | $0.50 (opens in a new tab) | Not reported | Not reported |
Benchmark performance
Claude Haiku 5.5 in color, alongside leading models. Latest stored reports, best effort per report date.
AutomationBench-AA ↗
Reported benchmarks
All published results in our dataset, with versions, evaluation settings, and sources.
| Benchmark | Score | Evaluation setup | Source |
|---|---|---|---|
| AA-Briefcase1.1 / combined EloCombined Elo · Higher is better | 1,576 Elo | selection: best reported configuration per release · Claude Haiku 5.5 (max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 36% | reported precision decimals: 1 · result quality: provisional · Claude Haiku 5.5 (xhigh); private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. Publisher flags elevated refusals in pre-release testing and plans a rerun. Provisional result. · source model href: /models/claude-haiku-5-5-xhigh · task count: 657 · Tools enabled · turn cap: 50 | Artificial Analysis (opens in a new tab)independent |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 20.8% | selection: best reported configuration per release · Claude Haiku 5.5 (max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| HLE-Diamond1,000 questions / no toolsAccuracy · Higher is better | 29.6% | selection: best reported configuration per release · Claude Haiku 5.5 (max) · No tools | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 57.4% | Haiku 5.5 launch comparison; reported no-tools and with-tools configurations. · subset: full · Tools enabled | Anthropic ↗ (opens in a new tab)provider reported · 2026-10-07 |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 45.9% | Haiku 5.5 launch comparison; reported no-tools and with-tools configurations. · subset: full · No tools | Anthropic ↗ (opens in a new tab)provider reported · 2026-10-07 |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 44.4% | question count: 2158 · reported precision decimals: 1 · Claude Haiku 5.5 (max); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/claude-haiku-5-5 · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| LiveBench: Agentic2.0 / 2026-10-25Accuracy · Higher is better | 40% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: agentic | LiveBench ↗ (opens in a new tab)benchmark publisher |
| LiveBench: Browser Use2.0 / 2026-10-25Accuracy · Higher is better | 69.5% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: browser-use | LiveBench ↗ (opens in a new tab)benchmark publisher |
| LiveBench: Coding2.0 / 2026-10-25Accuracy · Higher is better | 91.4% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding | LiveBench ↗ (opens in a new tab)benchmark publisher |
| LiveBench: Data Analysis2.0 / 2026-10-25Accuracy · Higher is better | 53.1% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: data-analysis | LiveBench ↗ (opens in a new tab)benchmark publisher |
| LiveBench: Design2.0 / 2026-10-25Accuracy · Higher is better | 83.1% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: design | LiveBench ↗ (opens in a new tab)benchmark publisher |
| LiveBench: Reasoning2.0 / 2026-10-25Accuracy · Higher is better | 82.4% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: reasoning | LiveBench ↗ (opens in a new tab)benchmark publisher |
| LiveBench: Research2.0 / 2026-10-25Accuracy · Higher is better | 81.9% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: research | LiveBench ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 32.8% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Claude Haiku 5.5 (max) | Artificial Analysis (opens in a new tab)independent |