Anthropicproprietary
Released: 2024-03-04Claude 3 Opus
Anthropic original 2024 frontier model with rich nuance, deep context comprehension, and complex writing.
Intelligence Index
78.0/ 100
Calibrated multi-domain compositeThroughput Speed
30tok/sec
Output streaming throughputTime To First Token
680ms
Initial chunk server latencyLiveBench Contam-Free
—%
September 2026 suite scoreSourced Benchmark Evaluations (23)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| SimpleQA | Active | 23.5% | 90 | 2024-11-07 | independent | Source ↗ |
| StructFlowBench | Nearing Saturation | 61% | 75 | 2024-03-22 | independent | Source ↗ |
| FireBench | Active | 60.3% | 95 | 2024-03-20 | independent | Source ↗ |
| OpenAI-MRCR | Active | 65.5% | 80 | 2024-03-19 | independent | Source ↗ |
| ComplexBench | Nearing Saturation | 58.8% | 80 | 2024-03-18 | independent | Source ↗ |
| LongBench-Pro | Active | 64% | 80 | 2024-03-18 | independent | Source ↗ |
| ZeroSCROLLS | Nearing Saturation | 62.4% | 78 | 2024-03-17 | independent | Source ↗ |
| InfiniteBench | Nearing Saturation | 66.3% | 65 | 2024-03-16 | independent | Source ↗ |
| AgentIF | Nearing Saturation | 48.8% | 80 | 2024-03-16 | independent | Source ↗ |
| SCROLLS | Nearing Saturation | 62.4% | 65 | 2024-03-15 | independent | Source ↗ |
| RULER | Nearing Saturation | 71.8% | 84 | 2024-03-14 | independent | Source ↗ |
| MMLU-Redux | Saturated | 76.4% | 25 | 2024-03-13 | independent | Source ↗ |
| QuALITY | Nearing Saturation | 68.6% | 78 | 2024-03-13 | independent | Source ↗ |
| LongBench | Nearing Saturation | 67.1% | 65 | 2024-03-12 | independent | Source ↗ |
| QASPER | Nearing Saturation | 64.7% | 65 | 2024-03-11 | independent | Source ↗ |
| TruthfulQA | Saturated | 68.6% | 25 | 2024-03-11 | independent | Source ↗ |
| MT-Bench | Nearing Saturation | 7.4% | 75 | 2024-03-09 | independent | Source ↗ |
| IFEval | Deprecated | 70.3% | 25 | 2024-03-08 | independent | Source ↗ |
| GPQA | Nearing Saturation | 68.6% | 78 | 2024-03-08 | independent | Source ↗ |
| Needle-in-a-Haystack | Saturated | 95.6% | 44 | 2024-03-07 | independent | Source ↗ |
| MMLU | Saturated | 86.8% | 25 | 2024-03-04 | vendor-reported | Source ↗ |
| MMLU-Pro | Nearing Saturation | 68.5% | 75 | 2024-03-04 | independent | Source ↗ |
| HellaSwag | Saturated | 95.4% | 28 | 2024-03-04 | vendor-reported | Source ↗ |
Anthropic Python SDKAPI Ready
import anthropic
client = anthropic.Anthropic()
message = client.messages.create(
model="claude-3-opus",
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 Claude 3 Opus 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.