Reasoning
198-question Diamond subset; independent AA evaluation
- 01
- 02
- 03
- 03
- 03
- 17
Claude Sonnet 5
Across the task benchmarks we track, Claude Sonnet 5’s strongest relative results are in knowledge work, reasoning, and work automations. On GDPval-AA v2.1, it scores 1,470 Elo, ranking #20 among 38 models with reported results in our dataset.
Updated: Data as of:
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| Humanity's Last Exam ↗Stable HLE — text-only subset | Expert reasoning | 41.3%#28 of 68 |
| AA-Briefcase ↗1.1 / combined Elo | Business deliverables | 1,357 Elo#25 of 57 |
| GDPval-AA ↗2.1 | Knowledge work | 1,470.38 Elo#20 of 38 |
| GPQA ↗Diamond / Artificial Analysis | Reasoning | 91.11%Joint #17 of 30 |
Model details
| Model | Claude Sonnet 5 |
|---|---|
| Agent Index v1.2 | Insufficient coverage (3/7) · 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 (max) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 225.112 (opens in a new tab) | 82.708 (opens in a new tab) |
| Claude Sonnet 5 (max) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 167.136 (opens in a new tab) | 82.915 (opens in a new tab) |
| Claude Sonnet 5 (max) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 231.315 (opens in a new tab) | 83.274 (opens in a new tab) |
| Claude Sonnet 5 (max) | 1,000,000 | $2.00 (opens in a new tab) | $10.00 (opens in a new tab) | 210.089 (opens in a new tab) | 79.391 (opens in a new tab) |
Benchmark performance
Claude Sonnet 5 in color, alongside leading models. Latest stored reports, best effort per report date.
GPQA Diamond ↗
Coding
113 tasks; mini-swe-agent
- 01
- 01
- 01
- 04
- 05
- 11
Terminal Use
Official 4.0 board; native agent harnesses
- 01
- 02
- 03
- 03
- 05
- 14
Work Automations
Private held-out set; API mode; 50 steps; strict pass/fail
- 01
- 02
- 03
- 04
- 05
- 16
Knowledge Work
220 tasks; Stirrup agent; pairwise Elo
- 01
- 02
- 03
- 04
- 05
- 20
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 | 1,357 Elo | selection: best reported configuration per release · Claude Sonnet 5 (max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| AutomationBench1.0.6 / Zapier held-out private setStrict task completion · Higher is better | 3.65% | Claude Sonnet 5 (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 | 5.78% | Claude Sonnet 5 (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 | 7.61% | Claude Sonnet 5 (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 | 9.89% | Claude Sonnet 5 (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 | 10.65% | Claude Sonnet 5 (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 | 36.5% | reported precision decimals: 1 · result quality: reported · Claude Sonnet 5 (max); private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. · source model href: /models/claude-sonnet-5 · task count: 657 · Tools enabled · turn cap: 50 | Artificial Analysis (opens in a new tab)independent |
| DeepSWEv1.1Pass@1 · Higher is better | 54% | mini-swe-agent; effort=max; ±4 percentage points | Datacurve ↗ (opens in a new tab)benchmark publisher |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 13.2% | selection: best reported configuration per release · Claude Sonnet 5 (max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,166.62 Elo | Claude Sonnet 5 (Medium); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,220.8 Elo | Claude Sonnet 5 (Non-reasoning, High); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,262.64 Elo | Claude Sonnet 5 (High); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,366.08 Elo | Claude Sonnet 5 (Xhigh); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,470.38 Elo | Claude Sonnet 5 (Max); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,075.82 Elo | Claude Sonnet 5 (Low); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 80% | Claude Sonnet 5 (Non-reasoning, High); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 91.111% | Claude Sonnet 5 (Max); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 54.9% | subset: full · Tools enabled | Anthropic ↗ (opens in a new tab)provider reported · 2026-09-28 |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 57.4% | Full 2,500 questions; thinking auto; total 1M-token cap; no context compaction; Opus 4.6 judge. Tools variant: search, fetch, programmatic tool calling and code execution. · subset: full · Tools enabled | Anthropic ↗ (opens in a new tab)provider reported |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 43.2% | Full 2,500 questions; thinking auto; total 1M-token cap; no context compaction; Opus 4.6 judge. Tools variant: search, fetch, programmatic tool calling and code execution. · subset: full · No tools | Anthropic ↗ (opens in a new tab)provider reported |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 41.3% | question count: 2158 · reported precision decimals: 1 · Claude Sonnet 5 (max); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/claude-sonnet-5 · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| Terminal-Bench4.0Task success · Higher is better | 12.4% | Claude Code; effort=max; 12.4% ± 3.1% | Terminal-Bench ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 14.141% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Claude Sonnet 5 (Max) | Artificial Analysis (opens in a new tab)independent |