Anthropic
Claude Opus 5
Close to Fable 5 at half the price. Top of Scale AI's SWE-Bench Pro V2 (99.4%) and of OSWorld 2.0 (44.3%, scored pass or fail).
- Announced
- Access
- Public
Benchmark scores
| Test | Score | Best on the tracker | How it was measured |
|---|---|---|---|
| Epoch Capabilities Indexmany tests combined into one score | 164 points | GPT-6.2 Astra 174 points | Independentlisted as "Claude Opus 5", CI 162.02 to 167.3Run 9 Nov 2026 |
| AA Intelligence Index v5about ten tests in one score | 44.2 points | Claude Fable 5.2 64.6 points | Independentv5.0.1; listed as Claude Opus 5 (Max)Run 10 Nov 2026 |
| FrontierSWE V2very long engineering jobs | 52% | Claude Fable 5.2 70% | Independentproximus harness, max effort, mean@5 over 34 tasks, 20-hour budget (best@5 60.7) |
| Terminal-Bench 4.1long command-line tasks | 53% | Claude Opus 5.5 66% | IndependentClaude Code harness, xhigh effort, 330 trials, ±3.09 (95% CI) |
| APEX-Agentsprofessional office tasks | 66% | Gemini 4 Carbon 84% | Independentpass@1, max effort; listed as "Opus 5" |
| ARC-AGI-3puzzle games, standard harnessTypical first-time human player: 100% | 30% | Claude Fable 5.2 81% | IndependentARC Prize config "Claude Opus 5 (High)" (anthropic-claude-opus-5-high), standard harness |
| FrontierMath T1–3hard maths problems | 86% | Claude Fable 5.2 95% | Independentmax reasoning effort (claude-opus-5_max)Run 24 Jul 2026 |
| OSWorld-Verifiedusing a computerPeople (original task set): 72% | 83% | Claude Fable 5 86% | Independentplain model, max 100 steps, 1M-context variant ("claude-opus-5[1m]", 300.2 / 360 tasks)Run 1 Aug 2026 |
| GPQA DiamondPhD-level science questionsPhD experts: 70%Saturated | 94% | Gemini 4 Argon 96% | Independentmax reasoning effort (claude-opus-5_max)Run 24 Jul 2026 |
| FrontierMath T4research-level maths problemsSaturated | 73% | GPT-6.1 Sol 100% | Independentmax reasoning effort (claude-opus-5_max)Run 24 Jul 2026 |
| ARC-AGI-2visual puzzles, model aloneAverage person: 60%Saturated | 90% | GPT-6 Astra 95% | IndependentARC Prize config "Claude Opus 5 (Max)" (anthropic-claude-opus-5-max) |
| OTIS Mock AIMEcompetition mathsSaturated | 99% | GPT-5.5 100% | Independentmax reasoning effort (claude-opus-5_max)Run 24 Jul 2026 |
| METR time horizon (TH1.1 + TH2)task length an AI agent finishes half the time | 20 h | GPT-6 Astra 1.7 days | IndependentPooled TH1.1 + TH2 suites; 95% CI 566.8–5174.8 min |
Also on these charts
Sources
- Introducing Claude Opus 5Anthropic · Official · anthropic.com
- SWE-Bench Pro V2 leaderboardScale Labs · Dataset · labs.scale.com
- OSWorld 2.0 leaderboardOSWorld (XLANG Lab) · Dataset · osworld-v2.xlang.ai
- Epoch AI Benchmarking Hub (model release dates and runs)Epoch AI · Dataset · 9 Nov 2026 · epoch.ai