Anthropicproprietary
Released: 2026-06-01Anthropic: Claude Opus 4.5
Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...
Intelligence Index
91.5/ 100
Calibrated multi-domain compositeThroughput Speed
55tok/sec
Output streaming throughputTime To First Token
420ms
Initial chunk server latencyLiveBench Contam-Free
80.5%
September 2026 suite scoreLiveBench Multi-Domain Evaluation Breakdown
Monthly refreshed contamination-free test setsLogical Reasoning84.2%
Coding & Repo Repair82.4%
Mathematics (AIME)81.4%
Data Analysis & Tables77.8%
Language & Comprehension79.6%
Instruction Following80.5%
Sourced Benchmark Evaluations (61)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| ARC-AGI-3 | Active | 57.7% | 93 | 2026-07-06 | independent | Source ↗ |
| ARC-AGI-2 | Nearing Saturation | 69.3% | 75 | 2026-06-29 | independent | Source ↗ |
| FrontierMath | Active | 23.8% | 98 | 2026-06-26 | independent | Source ↗ |
| PutnamBench | Active | 44.3% | 90 | 2026-06-25 | independent | Source ↗ |
| SWE-Lancer | Deprecated | 59.1% | 20 | 2026-06-23 | independent | Source ↗ |
| Omni-MATH | Deprecated | 63% | 10 | 2026-06-23 | independent | Source ↗ |
| Soohak | Active | 64.7% | 98 | 2026-06-21 | independent | Source ↗ |
| FrontierCode | Active | 50.4% | 98 | 2026-06-21 | independent | Source ↗ |
| Humanity's Last Exam | Active | 39.1% | 93 | 2026-06-19 | independent | Source ↗ |
| StructFlowBench | Nearing Saturation | 68.4% | 75 | 2026-06-19 | independent | Source ↗ |
| AIME | Nearing Saturation | 80.8% | 75 | 2026-06-19 | independent | Source ↗ |
| OlympiadBench | Active | 69.8% | 80 | 2026-06-18 | independent | Source ↗ |
| MathArena | Active | 68.1% | 99 | 2026-06-17 | independent | Source ↗ |
| FireBench | Active | 67.6% | 95 | 2026-06-17 | independent | Source ↗ |
| Terminal-Bench | Active | 60.8% | 80 | 2026-06-17 | independent | Source ↗ |
| OpenAI-MRCR | Active | 76.9% | 80 | 2026-06-16 | independent | Source ↗ |
| SimpleQA | Active | 47.6% | 90 | 2026-06-16 | independent | Source ↗ |
| CodeContests | Deprecated | 56.5% | 10 | 2026-06-16 | independent | Source ↗ |
| ComplexBench | Nearing Saturation | 66% | 80 | 2026-06-15 | independent | Source ↗ |
| SWE-bench Pro | Active | 53.9% | 90 | 2026-06-15 | independent | Source ↗ |
| LongBench-Pro | Active | 75% | 80 | 2026-06-15 | independent | Source ↗ |
| ZeroSCROLLS | Nearing Saturation | 73.2% | 78 | 2026-06-14 | independent | Source ↗ |
| MultiPL-E | Deprecated | 79.9% | 10 | 2026-06-14 | independent | Source ↗ |
| LiveCodeBench | Saturated | 71.3% | 39 | 2026-06-13 | independent | Source ↗ |
| AgentIF | Nearing Saturation | 54.7% | 80 | 2026-06-13 | independent | Source ↗ |
| MATH | Saturated | 83.4% | 25 | 2026-06-13 | independent | Source ↗ |
| InfiniteBench | Nearing Saturation | 77.8% | 65 | 2026-06-13 | independent | Source ↗ |
| Mercury | Deprecated | 76.5% | 10 | 2026-06-12 | independent | Source ↗ |
| SCROLLS | Nearing Saturation | 73.2% | 65 | 2026-06-12 | independent | Source ↗ |
| MMLU-Pro | Nearing Saturation | 84.2% | 75 | 2026-06-12 | independent | Source ↗ |
| RULER | Nearing Saturation | 84.2% | 84 | 2026-06-11 | independent | Source ↗ |
| TabMWP | Saturated | 78.3% | 25 | 2026-06-11 | independent | Source ↗ |
| CyberSecEval | Deprecated | 78.2% | 10 | 2026-06-11 | independent | Source ↗ |
| SWE-bench Verified | Saturated | 67.8% | 25 | 2026-06-10 | independent | Source ↗ |
| MMLU-Redux | Saturated | 89.7% | 25 | 2026-06-10 | independent | Source ↗ |
| QuALITY | Nearing Saturation | 80.5% | 78 | 2026-06-10 | independent | Source ↗ |
| LongBench | Nearing Saturation | 78.7% | 65 | 2026-06-09 | independent | Source ↗ |
| SWE-bench | Deprecated | 59.1% | 10 | 2026-06-09 | independent | Source ↗ |
| MGSM | Nearing Saturation | 80.8% | 65 | 2026-06-09 | independent | Source ↗ |
| AGIEval | Saturated | 76.4% | 25 | 2026-06-08 | independent | Source ↗ |
| QASPER | Nearing Saturation | 75.9% | 65 | 2026-06-08 | independent | Source ↗ |
| TruthfulQA | Saturated | 80.5% | 25 | 2026-06-08 | independent | Source ↗ |
| GSM-Hard | Deprecated | 81.7% | 10 | 2026-06-07 | independent | Source ↗ |
| SuperGLUE | Saturated | 90.6% | 25 | 2026-06-07 | independent | Source ↗ |
| CodeXGLUE | Deprecated | 81.7% | 23 | 2026-06-06 | independent | Source ↗ |
| MT-Bench | Nearing Saturation | 8.3% | 75 | 2026-06-06 | independent | Source ↗ |
| BIG-Bench Hard | Saturated | 87% | 25 | 2026-06-06 | independent | Source ↗ |
| WinoGrande | Saturated | 92.4% | 28 | 2026-06-05 | independent | Source ↗ |
| MBPP+ | Nearing Saturation | 88.6% | 65 | 2026-06-05 | independent | Source ↗ |
| IFEval | Deprecated | 78.9% | 25 | 2026-06-05 | independent | Source ↗ |
| GPQA | Nearing Saturation | 80.5% | 78 | 2026-06-05 | independent | Source ↗ |
| Needle-in-a-Haystack | Saturated | 98.3% | 44 | 2026-06-04 | independent | Source ↗ |
| HumanEval+ | Saturated | 93.9% | 25 | 2026-06-04 | independent | Source ↗ |
| CommonsenseQA | Saturated | 93.2% | 28 | 2026-06-04 | independent | Source ↗ |
| MBPP | Saturated | 92.1% | 25 | 2026-06-03 | independent | Source ↗ |
| GSM8K | Saturated | 91.9% | 25 | 2026-06-03 | independent | Source ↗ |
| GLUE | Saturated | 95.9% | 28 | 2026-06-03 | independent | Source ↗ |
| MMLU | Saturated | 93.3% | 25 | 2026-06-02 | independent | Source ↗ |
| HumanEval | Saturated | 99.1% | 25 | 2026-06-02 | independent | Source ↗ |
| ARC-AGI | Saturated | 83.5% | 25 | 2026-06-02 | independent | Source ↗ |
| LiveBench (Continuous) | Active | 80.5% | 94 | 2025-02-01 | independent | Source ↗ |
Anthropic Python SDKAPI Ready
import anthropic
client = anthropic.Anthropic()
message = client.messages.create(
model="anthropic-claude-opus-4-5",
max_tokens=2048,
temperature=0,
messages=[{"role": "user", "content": "Execute SWE-bench verified repository fix"}]
)
print(message.content[0].text)Evaluation & Sourcing Notes
Scores listed for Anthropic: Claude Opus 4.5 represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.