Opus 4.7vsOpus 4.1
Across 4 shared benchmarks, Opus 4.7 leads overall: Opus 4.7 wins 4, Opus 4.1 wins 0, with 0 ties and an average score difference of +20.72.
Opus 4.74 wins(100%)(0%)0 winsOpus 4.1
Benchmark scores
Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.
Math and Reasoning
Opus 4.7 2/2| Benchmark | Opus 4.7 | Opus 4.1 | Diff |
|---|---|---|---|
| FrontierMath | 43.806 / 60极高强度思考（无工具） | 5.9035 / 60Normal (No Tools) | +37.90 |
| FrontierMath - Tier 4 | 22.9012 / 80极高强度思考（无工具） | 4.2040 / 80Thinking (No Tools, 32K Budget) | +18.70 |
Coding and Software Engineer
Opus 4.7 1/1| Benchmark | Opus 4.7 | Opus 4.1 | Diff |
|---|---|---|---|
| SWE-bench Verified | 87.605 / 108Extended (with tools) | 74.5036 / 108Extended (with tools) | +13.10 |
General Knowledge
Opus 4.7 1/1| Benchmark | Opus 4.7 | Opus 4.1 | Diff |
|---|---|---|---|
| GPQA Diamond | 94.204 / 178Extended (no tools) | 8169 / 178Extended (no tools) | +13.20 |
Specs
| Field | Opus 4.7 | Opus 4.1 |
|---|---|---|
| Publisher | Anthropic | Anthropic |
| Release date | 2026-04-16 | 2025-08-06 |
| Model type | Reasoning model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1000K | 200K |
| Max output | 128K | 32K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Opus 4.7 | Opus 4.1 |
|---|---|---|
| Text input | $5 / 1M tokens | $15 / 1M tokens |
| Text output | $25 / 1M tokens | $75 / 1M tokens |
| Cache read | $0.5 / 1M tokens | $1.5 / 1M tokens |
| Cache write | $6.25 / 1M tokens | $18.75 / 1M tokens |
Summary
- Opus 4.7leads in:Math and Reasoning (2/2), Coding and Software Engineer (1/1), General Knowledge (1/1)
On average across the 4 shared benchmarks, Opus 4.7 scores 20.72 higher.
Largest single-benchmark gap: FrontierMath — Opus 4.7 43.80 vs Opus 4.1 5.90 (+37.90).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.