Claude Opus 5.5
| Released | 2026-09-22 |
|---|---|
| Price per 1M | $4.00 in · $20.00 out |
| Overall score | 65.8 · rank 3 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 65.8 | 3 | 56 |
| Overall: Coding | 66.1 | 3 | 41 |
| Overall: Reasoning | 66.5 | 6 | 20 |
| Overall: Agentic work | 65.2 | 3 | 38 |
| Overall: Frontend | 66.3 | 1 | 15 |
| Coding | 66.5 | 3 | 11 |
| Agents | 64.2 | 3 | 15 |
| Reasoning | 66.9 | 6 | 12 |
| Math | 67.1 | 4 | 6 |
| Knowledge | 64.5 | 5 | 2 |
| Frontend | 66.9 | 1 | 3 |
| General | 67.0 | 3 | 6 |
| Multimodal | 61.9 | 7 | 1 |
| Value vs price | +11.8 | 20 |
Buzz
| Posts on X | About 3,523 a day |
|---|---|
| Mood | 50% positive, 10% negative |
| Hacker News | 518 mentions this week |
| Checked | 2026-11-11 |
- Which model has the best overall intelligence? - Gemini 4 Carbon - Fable 5.2 - Opus 5.5 - GPT-6.2 Sol - GPT-6 Astra
- THE 10 BEST CODING IDES IN THE AGE OF CODEX AND CLAUDE CODE A coding IDE is no longer only a place you type. OpenAI Codex and Anthropic's Claude Code run as terminal agents that read a repo, edit files, run tests and open pull requests. The editor's job is to host those agents…
- Grok bot really needs a smarter model. It's so far behind Opus 5.5, Duet will crush it if it's anywhere near grok bot as a harness.
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 68.1 ±2.3 | 13 |
| High | 65.5 ±1.6 | 14 |
| Low | 61.4 ±4.0 | 5 |
| Max | 65.7 ±1.2 | 33 |
| Medium | 62.6 ±2.9 | 8 |
| Extra High | 66.8 ±4.3 | 6 |
Evidence
Coding 66.5 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| CursorBench | 57.8% | Epoch AI | 2026-11-11 |
| FrontierSWE | 62.3% | Epoch AI | 2026-11-11 |
| FrontierCode | 54.6% | Epoch AI | 2026-11-11 |
| Code Migration v1.1 | 81.0% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Coding | 87.1% | LiveBench | 2026-11-06 |
| WeirdML v3 | 31.2% | Epoch AI | 2026-11-11 |
| MirrorCode | 95.6% | Epoch AI | 2026-10-30 |
| IOI | 95.1% | Vals AI | 2026-10-29 |
| SWE-bench Multimodal | 70.2% | Vals AI | 2026-11-09 |
| SciCode | 66.9% | Epoch AI | 2026-11-11 |
| ProgramBench | 18.5% | Vals AI | 2026-11-09 |
Agents 64.2 ±0.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4 | 65.8% | Terminal-Bench | 2026-09-22 |
| SRE Bench | 33.6% | Vals AI | 2026-11-05 |
| Terminal-Bench 4.0 (Vals run) | 65.2% | Vals AI | 2026-11-09 |
| Terminal-Bench-Science | 47.1% | Vals AI | 2026-11-09 |
| APEX-Agents | 73.5% | Epoch AI | 2026-11-11 |
| Remote Labor Index | 21.3% | Epoch AI | 2026-11-11 |
| LiveBench 2.0 Agentic | 72.8% | LiveBench | 2026-11-06 |
| LiveBench 2.0 Browser Use | 88.4% | LiveBench | 2026-11-06 |
| Terminal-Bench 2.1 (Vals run) | 87.6% | Vals AI | 2026-10-01 |
| EMB v1.1 (Excel financial modeling) | 75.8% | Vals AI | 2026-11-09 |
| LiveBench 2.0 Research | 88.9% | LiveBench | 2026-11-06 |
| Tax Agent Bench | 44.5% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 67.8% | Vals AI | 2026-11-09 |
| Vending-Bench 2 | $9,235 | Epoch AI | 2026-11-11 |
| HLAB-Vals 1.1 (legal agent) | 9.2% | Vals AI | 2026-11-09 |
| CyberBench v1.1 | 55.4% | Vals AI | 2026-11-05 |
Reasoning 66.9 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 93.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 93.3% | ARC Prize | 2026-11-11 |
| Extended NYT Connections | 88.5% | Lech Mazur | 2026-11-10 |
| MysteryMechanism | 49.6% | Vals AI | 2026-11-09 |
| GPQA Diamond | 90.6% | Epoch AI | 2026-09-22 |
| CritPt | 31.7% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 98.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 98.5% | Epoch AI | 2026-11-11 |
| SimpleBench | 88.4% | SimpleBench | 2026-09-24 |
| BioMysteryBench | 79.3% | Vals AI | 2026-11-09 |
| Chess Puzzles | 67.0% | Epoch AI | 2026-10-13 |
| LiveBench 2.0 Reasoning | 92.2% | LiveBench | 2026-11-06 |
| Mystery Game Puzzles | 71.0% | Epoch AI | 2026-09-29 |
| LiveBench 2.0 Data Analysis | 80.3% | LiveBench | 2026-11-06 |
Math 67.1 ±1.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 91.2% | Epoch AI | 2026-09-22 |
| FrontierMath Tier 4 | 95.0% | Epoch AI | 2026-09-22 |
| MathArena ArXivMath (latest month) | 79.8% | MathArena | 2026-11-11 |
| OTIS Mock AIME 2024-2025 | 100.0% | Epoch AI | 2026-09-22 |
| ProofBench v1.1 | 100.0% | Vals AI | 2026-11-09 |
| ProofBench | 100.0% | Epoch AI | 2026-11-11 |
| MathArena BrokenArXiv (latest month) | 77.8% | MathArena | 2026-11-11 |
Knowledge 64.5 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| SimpleQA Verified | 72.2% | Epoch AI | 2026-09-22 |
| Legal Research Bench | 50.5% | Vals AI | 2026-11-09 |
Frontend 66.9 ±3.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LiveBench 2.0 Design | 83.3% | LiveBench | 2026-11-06 |
| Vibe Code Bench v1.1 | 90.3% | Vals AI | 2026-11-09 |
| LMArena WebDev | 1,818 | LMArena | 2026-11-09 |
General 67.0 ±1.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,692 | Lech Mazur | 2026-10-26 |
| EQ-Bench 4 | 1,340 | EQ-Bench | 2026-10-24 |
| EQ-Bench Creative Writing v3 | 2,051 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,506 | LMArena | 2026-11-09 |
| Creative Story-Writing (Lech Mazur) | 93.0% | Lech Mazur | 2026-10-23 |
| EQ-Bench Longform Creative Writing | 84.6% | EQ-Bench | 2026-11-11 |
Multimodal 61.9 ±4.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,295 | LMArena | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| APEX-Agents | 52.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 97.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 97.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 97.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 | 88.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 97.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 97.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 97.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 88.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 91.7% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 92.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 87.5% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 | 70.1% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 91.7% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 92.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 87.5% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 70.1% | ARC Prize | A stronger configuration result was used |
| CritPt | 30.9% | Epoch AI | A stronger configuration result was used |
| CritPt | 31.7% | Epoch AI | A stronger configuration result was used |
| CritPt | 27.7% | Epoch AI | A stronger configuration result was used |
| CritPt | 17.7% | Epoch AI | A stronger configuration result was used |
| CursorBench | 56.0% | Epoch AI | A stronger configuration result was used |
| CursorBench | 56.0% | Epoch AI | A stronger configuration result was used |
| CursorBench | 52.5% | Epoch AI | A stronger configuration result was used |
| CursorBench | 43.7% | Epoch AI | A stronger configuration result was used |
| Extended NYT Connections | 87.8% | Lech Mazur | A stronger configuration result was used |
| MirrorCode | 78.9% | Epoch AI | A stronger configuration result was used |
| SciCode | 60.4% | Epoch AI | A stronger configuration result was used |
| SciCode | 65.1% | Epoch AI | A stronger configuration result was used |
| SciCode | 59.3% | Epoch AI | A stronger configuration result was used |
| SciCode | 58.6% | Epoch AI | A stronger configuration result was used |
Names matched to this model
claude-opus-5-5