BlogLLM Benchmark Scores as Published, Side by Side
Claude Opus 4.1: Benchmark Scores as Published
Every result the catalog holds for Claude Opus 4.1: 15 tests in 7 areas, from 4 pages. All were printed by Anthropic itself. Each number is as printed; nothing is ranked or rescored.
Developer AnthropicReleased 2025-08-05Data version 2026103001, as of 2026-10-30
Knowledge Work
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| Vals Finance Agent (version not stated) | 50.9% | Anthropic, Claude Sonnet 4.5checked 2026-10-15 | Effort: extended thinking (up to 64K) |
Agentic Coding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| SWE-bench Verified | 74.5% | Anthropic, Claude Opus 4.1checked 2026-10-15; printed on 2 more pages | Effort: none |
| Terminal-Bench 2.0 | 46.5% | Anthropic, Claude Opus 4.5checked 2026-10-15 | - |
| Terminal-Bench (version not stated) | 43.3% | Anthropic, Claude Opus 4.1checked 2026-10-15; printed on 1 more page | Effort: none; Harness: Terminus 1 |
Science and Math
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| GPQA Diamond | 80.9% | Anthropic, Claude Opus 4.1checked 2026-10-15; printed on 2 more pages | Effort: extended thinking, up to 64K |
| AIME 2025 | 78% | Anthropic, Claude Opus 4.1checked 2026-10-15; printed on 1 more page | Effort: extended thinking, up to 64K |
Computer Use
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| OSWorld-Verified | 44.4% | Anthropic, Claude Opus 4.5checked 2026-10-15; printed on 1 more page | - |
Multimodal Understanding
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMMU (validation) | 77.1% | Anthropic, Claude Opus 4.1checked 2026-10-15; printed on 2 more pages | Effort: extended thinking, up to 64K |
Tool Use and Workflows
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| τ²-bench Telecom | 71.5% | Anthropic, Claude Opus 4.5checked 2026-10-15; printed on 1 more page | - |
| MCP Atlas | 40.9% | Anthropic, Claude Opus 4.5checked 2026-10-15 | - |
| τ²-bench Retail | 86.8% | Anthropic, Claude Opus 4.5checked 2026-10-15; printed on 1 more page | - |
| τ²-bench Airline | 63% | Anthropic, Claude Sonnet 4.5checked 2026-10-15 | Effort: extended thinking (up to 64K) |
| τ-bench Airline | 56% | Anthropic, Claude Opus 4.1checked 2026-10-15 | Effort: extended thinking, up to 64K |
| τ-bench Retail | 82.4% | Anthropic, Claude Opus 4.1checked 2026-10-15 | Effort: extended thinking, up to 64K |
Multilingual
| Test | Value | Printed by | Setup as printed |
|---|---|---|---|
| MMMLU | 89.5% | Anthropic, Claude Opus 4.1checked 2026-10-15; printed on 2 more pages | Effort: extended thinking, up to 64K |
Price
API list prices in US dollars per one million tokens, as printed on the developer's pricing page on the day checked.
| Price | Value | Printed by | Setup as printed |
|---|---|---|---|
| Input | $15 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Cached input | $1.5 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Cache write | $18.75 | Anthropic, Anthropic API pricingchecked 2026-10-15 | Cache: 5 minute cache |
| Cache write, 1 hour | $30 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Output | $75 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Input, batch | $7.5 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
| Output, batch | $37.5 | Anthropic, Anthropic API pricingchecked 2026-10-15 | - |
More from Anthropic
- Claude Haiku 5.5
- Claude Sonnet 5.5
- Claude Opus 5.5
- Claude Fable 5.1
- Claude Mythos 5.1
- Claude Opus 5
- Claude Sonnet 5
- Claude Fable 5
- Claude Mythos 5
- Claude Opus 4.8
- Claude Opus 4.7
- Claude Mythos Preview
- Claude Sonnet 4.6
- Claude Opus 4.6
- Claude Opus 4.5
- Claude Haiku 4.5
- Claude Sonnet 4.5
- Claude Opus 4
- Claude Sonnet 4
- Claude 3.7 Sonnet
- Claude 3.5 Sonnet
Every number here is read from the same catalog file as the benchmark table, data version 2026103001. Where one page printed the model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.