Claude Opus 5 Max
| Released | 2026-07-24 |
|---|---|
| Price per 1M | $5.00 in · $25.00 out |
| Overall score | 63.3 · rank 42 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
| Configuration | Max |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 63.3 | 42 | 37 |
| Overall: Coding | 63.2 | 39 | 28 |
| Overall: Reasoning | 64.9 | 35 | 15 |
| Overall: Agentic work | 63.2 | 36 | 27 |
| Overall: Frontend | 63.0 | 38 | 11 |
| Coding | 62.9 | 45 | 9 |
| Agents | 62.5 | 33 | 10 |
| Reasoning | 66.1 | 31 | 8 |
| Math | 64.2 | 24 | 4 |
| Knowledge | 63.5 | 13 | 3 |
| Frontend | 62.9 | 20 | 1 |
| General | 61.0 | 50 | 1 |
| Multimodal | 63.6 | 3 | 1 |
| Value vs price | +6.5 | 103 |
Buzz
| Posts on X | About 117 a day |
|---|---|
| Mood | 16% positive, 32% negative |
| Hacker News | 52 mentions this week |
| Checked | 2026-11-11 |
- 🇨🇳 DeepSeek and other leading AI companies in China together generate only around one-tenth of the combined revenue of US rivals OpenAI and Anthropic, estimates show, as competition pushes already low Chinese fees further down. Chinese AI companies have gained ground with open-…
- Oh no. Fable 5.2 repeatedly hallucinates contrarian objections that misread you if you make no mistakes. Noooo. This is one of the biggest wastes of time I remember strongly from working with Opus 5 when it came out. Anthropic needs to fix that. Has anyone else seen this? I’ve …
- They built an AI agent in 20 minutes and sold it to Anthropic for $100k - and at Stanford showed how to repeat it from scratch: 02:00 - how to build your first agent with Opus 5 in 20 minutes 22:34 - one agent replaces an Anthropic engineering team worth $200k a year 49:47 - …
Evidence
Coding 62.9 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 46.6% | Epoch AI | 2026-11-11 |
| FrontierSWE | 52.0% | Epoch AI | 2026-11-11 |
| DeepSWE | 73.7% | Epoch AI | 2026-11-11 |
| FrontierCode | 53.4% | Epoch AI | 2026-11-11 |
| MirrorCode | 87.8% | Epoch AI | 2026-10-20 |
| IOI | 84.3% | Vals AI | 2026-10-29 |
| SciCode | 56.4% | Epoch AI | 2026-11-11 |
| LiveCodeBench (Vals run) | 89.0% | Vals AI | 2026-09-01 |
| ProgramBench | 3.0% | Vals AI | 2026-11-09 |
Agents 62.5 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 52.1% | Terminal-Bench | 2026-07-24 |
| OSWorld 2.0 | 31.4% | Epoch AI | 2026-11-11 |
| SRE Bench | 12.2% | Vals AI | 2026-11-05 |
| Terminal-Bench 4.0 (Vals run) | 53.5% | Vals AI | 2026-11-09 |
| Terminal-Bench-Science | 27.1% | Vals AI | 2026-11-09 |
| APEX-Agents | 65.8% | Epoch AI | 2026-11-11 |
| tau2-bench Banking Knowledge | 48.7% | tau2-bench | 2026-08-03 |
| Tax Agent Bench | 47.1% | Vals AI | 2026-11-09 |
| SkillsBench | 60.4% | Vals AI | 2026-10-29 |
| BALROG | 63.4% | Epoch AI | 2026-11-11 |
| CyberBench v1.1 | 65.4% | Vals AI | 2026-11-05 |
Reasoning 66.1 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 90.4% | Epoch AI | 2026-11-11 |
| MysteryMechanism | 37.4% | Vals AI | 2026-11-09 |
| ARC-AGI-2 (ARC Prize verified) | 90.4% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 93.9% | Epoch AI | 2026-07-24 |
| CritPt | 29.1% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 97.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 97.5% | Epoch AI | 2026-11-11 |
| BioMysteryBench | 79.3% | Vals AI | 2026-11-09 |
| Chess Puzzles | 43.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 59.0% | Epoch AI | 2026-07-25 |
Math 64.2 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 85.6% | Epoch AI | 2026-07-24 |
| FrontierMath Tier 4 | 73.2% | Epoch AI | 2026-07-24 |
| OTIS Mock AIME 2024-2025 | 98.9% | Epoch AI | 2026-07-24 |
| ProofBench v1.1 | 99.0% | Vals AI | 2026-11-09 |
| ProofBench | 99.0% | Epoch AI | 2026-11-11 |
Knowledge 63.5 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 59.9% | Epoch AI | 2026-08-10 |
| MMLU-Pro (Vals run) | 91.6% | Vals AI | 2026-09-01 |
| Legal Research Bench | 55.3% | Vals AI | 2026-11-09 |
Frontend 62.9 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,691 | LMArena | 2026-11-09 |
General 61.0 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Text | 1,489 | LMArena | 2026-11-09 |
Multimodal 63.6 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MMMU-Pro (Vals run) | 89.9% | Vals AI | 2026-09-01 |
Names matched to this model
claude-opus-5-max