Reasoning
198-question Diamond subset; independent AA evaluation
- 01
- 02
- 03
- 03
- 03
- 06
Claude Opus 5
Across the task benchmarks we track, Claude Opus 5’s strongest relative results are in coding, knowledge work, and reasoning. On DeepSWE v1.1, it scores 74%, ranking joint #1 among 11 models with reported results in our dataset.
Updated: Data as of:
🥇
Strongest results
| Benchmark | Measures | Score |
|---|---|---|
| OSWorld ↗2.1 / full set | Computer use | 44.33%#1 of 3 |
| DeepSWE ↗v1.1 | Coding agents | 74%Joint #1 of 11 |
| Humanity's Last Exam ↗Stable HLE — text-only subset | Expert reasoning | 54.9%#5 of 68 |
| AA-Briefcase ↗1.1 / combined Elo | Business deliverables | 1,656 Elo#6 of 57 |
Model details
| Model | Claude Opus 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 Opus 5 (max) | 1,000,000 | $5.00 (opens in a new tab) | $25.00 (opens in a new tab) | 88.226 (opens in a new tab) | 56.473 (opens in a new tab) |
| Claude Opus 5 (max) | 1,000,000 | $5.00 (opens in a new tab) | $25.00 (opens in a new tab) | 73.708 (opens in a new tab) | 54.128 (opens in a new tab) |
| Claude Opus 5 (max) | 1,000,000 | $5.00 (opens in a new tab) | $25.00 (opens in a new tab) | 60.427 (opens in a new tab) | 57.082 (opens in a new tab) |
Benchmark performance
Claude Opus 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
Terminal Use
Official 4.0 board; native agent harnesses
- 01
- 02
- 03
- 03
- 05
- 06
Web Research
Professional benchmark table; OpenAI Astra release comparison
- 01
- 02
- 03
- 04
Work Automations
Private held-out set; API mode; 50 steps; strict pass/fail
- 01
- 02
- 03
- 04
- 05
- 08
Knowledge Work
220 tasks; Stirrup agent; pairwise Elo
- 01
- 02
- 03
- 04
- 05
- 07
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 | 1,656 Elo | selection: best reported configuration per release · Claude Opus 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 | 20.4% | Claude Opus 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 | 20.55% | Claude Opus 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 | 23.9% | Claude Opus 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 | 25.27% | Claude Opus 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 | 26.94% | Claude Opus 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 | 56.6% | reported precision decimals: 1 · result quality: reported · Claude Opus 5 (max); private held-out 657 tasks; 50 turns; objective completion with zero credit for any guardrail violation. · source model href: /models/claude-opus-5 · task count: 657 · Tools enabled · turn cap: 50 | Artificial Analysis (opens in a new tab)independent |
| BrowseCompOpenAI Astra launch comparison / September 2026Accuracy · Higher is better | 90.8% | OpenAI GPT-6 Astra launch comparison; best reported reasoning setting; see source evaluation footnotes | OpenAI ↗ (opens in a new tab)provider reported |
| DeepSWEv1.1Pass@1 · Higher is better | 74% | mini-swe-agent; effort=max; ±4 percentage points | Datacurve ↗ (opens in a new tab)benchmark publisher |
| DeepSWEv1.1Pass@1 · Higher is better | 74% | max; ±4 percentage points | Datacurve ↗ (opens in a new tab)benchmark publisher |
| DeepSWEv1.1 / OpenAI Astra launch comparisonPass@1 · Higher is better | 73.7% | OpenAI GPT-6 Astra launch comparison; best reported reasoning setting; see source evaluation footnotes | OpenAI ↗ (opens in a new tab)provider reported |
| GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better | 21.6% | selection: best reported configuration per release · Claude Opus 5 (max) · tools: benchmark-defined | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,498.64 Elo | Claude Opus 5 (Medium); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,729.9 Elo | Claude Opus 5 (Max); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,603.96 Elo | Claude Opus 5 (High); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,310.56 Elo | Claude Opus 5 (Low); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GDPval-AA2.1Elo · Higher is better | 1,695.66 Elo | Claude Opus 5 (Xhigh); 220 tasks; Stirrup agent; pairwise Elo | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 91.919% | Claude Opus 5 (Medium); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 93.232% | Claude Opus 5 (Max); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 93.737% | Claude Opus 5 (High); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 88.889% | Claude Opus 5 (Low); 198-question Diamond subset; independent AA evaluation | Artificial Analysis (opens in a new tab)independent |
| GPQADiamond / Artificial AnalysisAccuracy · Higher is better | 93.737% | Claude Opus 5 (Xhigh); 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 | 63.6% | Provider benchmark table; tools enabled. Cross-model settings may differ. · subset: full · Tools enabled | Anthropic ↗ (opens in a new tab)provider reported · 2026-09-22 |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 63.6% | subset: full · Tools enabled | Anthropic ↗ (opens in a new tab)provider reported |
| Humanity's Last ExamStable HLE — full setAccuracy · Higher is better | 56.6% | subset: full · No tools | Anthropic ↗ (opens in a new tab)provider reported |
| Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better | 54.9% | question count: 2158 · reported precision decimals: 1 · Claude Opus 5 (max); original HLE; 2,158 text-only questions; no tools; pass@1; chart labels rounded to one decimal. · source model href: /models/claude-opus-5 · subset: text · No tools | Artificial Analysis (opens in a new tab)independent |
| OSWorld2.1 / full setBinary accuracy · Higher is better | 44.33% | max; batch tool; v2.1; full set | OSWorld / XLang ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0Task success · Higher is better | 53.9% | Claude Code; effort=xhigh; 53.9% ± 3.2% | Terminal-Bench ↗ (opens in a new tab)benchmark publisher |
| Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better | 48.99% | harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Claude Opus 5 (Max) | Artificial Analysis (opens in a new tab)independent |