Terminal Use
Official 4.0 board; native agent harnesses
- 01
- 02
- 03
- 03
- 05
Claude Sonnet 5.5
Across the task benchmarks we track, Claude Sonnet 5.5’s strongest relative results are in knowledge work, terminal use, and work automations. On GDPval-AA v2.1, it scores 1,838 Elo, ranking #3 among 38 models with reported results in our dataset.
Updated: Data as of:
🥇
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| Agent Index ↗v1.2 Preview | Overall agent capability | 85.8 / 100#3 of 26 |
| AA-Briefcase ↗1.1 / combined Elo | Business deliverables | 1,814 Elo#1 of 57 |
| LiveBench: Design ↗2.0 / 2026-10-25 | Documents and presentations | 85%#2 of 25 |
| Humanity's Last Exam ↗Stable HLE — text-only subset | Expert reasoning | 55%#4 of 68 |
Model details
| Model | Claude Sonnet 5.5 |
|---|---|
| Agent Index v1.2 | 85.8 / 100 · Rank 3 · Preview |
| Creator | Anthropic (opens in a new tab) |
| Availability | Proprietary |
| Context size | 1,000,000 tokens (opens in a new tab) |
| Max output | 128,000 tokens (opens in a new tab) |
| Knowledge cutoff | Not reported |
| 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 |
|---|---|---|---|---|---|
| Claude Sonnet 5.5 (max with fallback) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 529.016 (opens in a new tab) | 141.843 (opens in a new tab) |
| Claude Sonnet 5.5 (max with fallback) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 514.907 (opens in a new tab) | 139.308 (opens in a new tab) |
| Claude Sonnet 5.5 (max with fallback) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 497.061 (opens in a new tab) | 134.954 (opens in a new tab) |
| Claude Sonnet 5.5 (max with fallback) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 522.437 (opens in a new tab) | 144.019 (opens in a new tab) |
Benchmark performance
Claude Sonnet 5.5 in color, alongside leading models. Latest stored reports, best effort per report date.
Terminal-Bench 4.0 ↗
Work Automations
Private held-out set; API mode; 50 steps; strict pass/fail
- 01
- 02
- 03
- 04
- 05
Knowledge Work
220 tasks; Stirrup agent; pairwise Elo
- 01
- 02
- 03
- 04
- 05
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 | 1,814 Elo | selection: publisher default displayed configuration · Claude Sonnet 5.5 (max with fallback) | Artificial Analysis (opens in a new tab)independent |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 18.26% | Claude Sonnet 5.5 (default fallbacks, Low); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 18.57% | Claude Sonnet 5.5 (default fallbacks, Between tools); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 23.29% | Claude Sonnet 5.5 (default fallbacks, Medium); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 29.38% | Claude Sonnet 5.5 (default fallbacks, High); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 36.83% | Claude Sonnet 5.5 (default fallbacks, XHigh); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 44.75% | Claude Sonnet 5.5 (default fallbacks, Max); private held-out 657 tasks; API mode; 50-step cap; strict completion | Zapier ↗ (opens in a new tab)benchmark publisher |
| AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better | 71.8% | max with fallback | Artificial Analysis (opens in a new tab)independent |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 25.8% | selection: publisher default displayed configuration · Claude Sonnet 5.5 (max with fallback) | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,181.72 Elo | Claude Sonnet 5.5 (Low, Default Fallback); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,837.82 Elo | Claude Sonnet 5.5 (Max, Default Fallback); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,735.08 Elo | Claude Sonnet 5.5 (Xhigh, Default Fallback); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,556.89 Elo | Claude Sonnet 5.5 (High, Default Fallback); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,328.63 Elo | Claude Sonnet 5.5 (Medium, Default Fallback); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| HLE-Diamond1,000 questions / no toolsAccuracy · Higher is better | 53.3% | selection: best reported configuration per release · Claude Sonnet 5.5 (Max, Default Fallback) · No tools | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 56.9% | 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 — full setAccuracy · Higher is better | 64.5% | subset: full · Tools enabled | Anthropic ↗ (opens in a new tab)provider reported · 2026-09-28 |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 55% | question count: 2158 · reported precision decimals: 1 · Claude Sonnet 5.5 (max with fallback); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/claude-sonnet-5-5 · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| LiveBench: Agentic2.0 / 2026-10-25Accuracy · Higher is better | 63.4% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: agentic | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Browser Use2.0 / 2026-10-25Accuracy · Higher is better | 89.3% | 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 · 2026-10-25 |
| LiveBench: Coding2.0 / 2026-10-25Accuracy · Higher is better | 94.7% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: coding | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Data Analysis2.0 / 2026-10-25Accuracy · Higher is better | 59.5% | 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 · 2026-10-25 |
| LiveBench: Design2.0 / 2026-10-25Accuracy · Higher is better | 85% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: design | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Reasoning2.0 / 2026-10-25Accuracy · Higher is better | 91.6% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: reasoning | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| LiveBench: Research2.0 / 2026-10-25Accuracy · Higher is better | 83.6% | release: 2026-10-25 · Highest supported effort unless publisher reports an exception; single run · suite: research | LiveBench ↗ (opens in a new tab)benchmark publisher · 2026-10-25 |
| Terminal-Bench4.0Task success · Higher is better | 61.8% | Claude Code; effort=max; 61.8% ± 2.9% | Terminal-Bench ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0Task success · Higher is better | 61.8% | Claude Code; max; ±2.9 percentage points | Terminal-Bench ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 63.636% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Claude Sonnet 5.5 (Max, Default Fallback) | Artificial Analysis (opens in a new tab)independent |