MMLU-ProVerified
88%
MMLU-Pro (AA run)
Models / Anthropic
Claude 4.1 Opus (Reasoning)
Claude 4.1 · Released 2025-08-05
AA Intelligence Index 33.7. Listed on Artificial Analysis with API pricing $15/$75 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.
Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.
#78 of 131 on AA Index · current snapshot
34 AA Index · 13 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.Composite55
ContextUnlisted
Input / 1M$15
Output / 1M$75
Knowledge cutoffunpublished
Output speed0 t/s
TTFT (default API)0.00s
Statussolid
- Knowledge
- 88
- Reasoning
- 81
- Math
- 80
- Coding
- 65
- Agentic
- 71
- Long context
- 66
75average across 6 tested families
Benchmark placements
Per-benchmark positions
Where Claude 4.1 Opus (Reasoning) places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.
| Benchmark | Family | Rank | Score | Source | Date |
|---|---|---|---|---|---|
| MMLU-Pro | Knowledge | #7/ 34 | 88 | Artificial Analysis | 2026-07-28 |
| LiveCodeBench | Coding | #21/ 26 | 65 | Artificial Analysis | 2026-07-28 |
| AIME | Math | #25/ 32 | 80 | Artificial Analysis | 2026-07-28 |
| τ³-Bench Banking | Agentic | #45/ 143 | 71 | Artificial Analysis | 2026-07-28 |
| AA-LCR | Long context | #55/ 143 | 66 | Artificial Analysis | 2026-07-28 |
| AA output speed | Performance | #74/ 149 | Artificial Analysis | 2026-07-28 | |
| AA time to first token | Performance | #74/ 149 | Artificial Analysis | 2026-07-28 | |
| IFBench | Reasoning | #87/ 121 | 55 | Artificial Analysis | 2026-07-28 |
| Artificial Analysis Intelligence Index | Reasoning | #91/ 147 | 34 | Artificial Analysis | 2026-07-28 |
| SciCode | Coding | #95/ 144 | 41 | Artificial Analysis | 2026-07-28 |
| GPQA Diamond | Reasoning | #107/ 149 | 81 | Artificial Analysis | 2026-07-28 |
| Terminal-Bench | Agentic | #112/ 148 | 34 | Artificial Analysis | 2026-07-28 |
| Humanity's Last Exam | Reasoning | #117/ 144 | 12 | Artificial Analysis | 2026-07-28 |
Family context
Strongest rows in each family
The three highest-scoring carded models in each capability family. Where Claude 4.1 Opus (Reasoning) shows up, it's highlighted.
KnowledgeClaude 4.1 Opus (Reasoning) · 88
- 191
- 291
- 391
ReasoningClaude 4.1 Opus (Reasoning) · 81
- 195
- 294
- 394
MathClaude 4.1 Opus (Reasoning) · 80
- 199
- 299
- 399
CodingClaude 4.1 Opus (Reasoning) · 65
- 196
- 296
- 396
AgenticClaude 4.1 Opus (Reasoning) · 71
- 1100
- 2100
- 3100
Multimodal
- 172
- 272
- 371
Long contextClaude 4.1 Opus (Reasoning) · 66
- 176
- 276
- 375
Tool use
- 189
- 287
- 387
Safety
- 192
- 292
- 391
Human preference
- 195
- 292
- 391
Newest receipts
13 recentLast 120 days
Benchmark rows added to the public ledger for Claude 4.1 Opus (Reasoning) in the last 120 days. Older rows live in the full table below.
| Benchmark | Family | Score | Source | Days ago |
|---|---|---|---|---|
| AA-LCR | Long context | 66.33% | Artificial Analysis | 4 |
| AA output speed | Performance | 0 t/s | Artificial Analysis | 4 |
| AA time to first token | Performance | 0.00s | Artificial Analysis | 4 |
| AIME | Math | 80.33% | Artificial Analysis | 4 |
| Artificial Analysis Intelligence Index | Reasoning | 33.7% | Artificial Analysis | 4 |
| GPQA Diamond | Reasoning | 80.9% | Artificial Analysis | 4 |
| Humanity's Last Exam | Reasoning | 11.9% | Artificial Analysis | 4 |
| IFBench | Reasoning | 55.44% | Artificial Analysis | 4 |
| LiveCodeBench | Coding | 65.4% | Artificial Analysis | 4 |
| MMLU-Pro | Knowledge | 88% | Artificial Analysis | 4 |
| SciCode | Coding | 40.9% | Artificial Analysis | 4 |
| τ³-Bench Banking | Agentic | 71.37% | Artificial Analysis | 4 |
| Terminal-Bench | Agentic | 34.34% | Artificial Analysis | 4 |
Family coverage
Best score per family
A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.
Price vs. performance
Where Claude 4.1 Opus (Reasoning) sits on the scatter
Hover or tab any dot for name, score, and input price.
AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotxAIMiniMaxMetaZhipuXiaomiOtherMeituanCohereNVIDIA
Full benchmark ledger
Every catalog benchmark for Claude 4.1 Opus (Reasoning). Scores link to the original source; gaps mean no public row exists yet.
13 of 32 catalog benchmarks have a sourced row for Claude 4.1 Opus (Reasoning).
Knowledge
Reasoning
33.7%
AA Intelligence Index v4.1
GPQA DiamondVerified
80.9%
GPQA Diamond (AA run)
Humanity's Last ExamVerified
11.9%
HLE (AA run)
IFBenchVerified
55.44%
IFBench (AA run)
Math
AIMEVerified
80.33%
AIME 2025 (AA run)
Coding
LiveCodeBenchVerified
65.4%
LiveCodeBench (AA run)
SciCodeVerified
40.9%
SciCode (AA run)
Agentic
Terminal-BenchVerified
34.34%
Terminal-Bench Hard (AA run)
τ³-Bench BankingVerified
71.37%
τ²-Bench Banking (AA run; maps to τ³ explainer)
Long context
AA-LCRVerified
66.33%
AA-LCR (AA run)
Performance
AA output speedVerified
0 t/s
Median output tokens/s (1k prompt, default provider)
AA time to first tokenVerified
0.00s
Median time to first token (1k prompt, default provider)
Sources
Where the numbers come from
- Artificial Analysis models index· checked 2026-08-01