ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.1vsClaude Sonnet 4.5

Claude Sonnet 4.5 leads 4 of 6 shared benchmarks. Claude Sonnet 4.5 is 5x cheaper per token. Both offer a 200K-token context window.

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
1 – 4
Claude Sonnet 4.5 leads · 1 tied
Cheaper per token
Claude Sonnet 4.5
5x cheaper, input + output
Larger context
Tie
both 200K tokens
Provider uptime (30d)
100%
Anthropic
Claude Opus 4.1
Anthropic · released 2025-08-05
textvision
Context
200K
Max out
32K
Input /1M
$15
Output /1M
$75
Cached /1M
$1.5
Scores
6 · 6 core
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Context
200K
Max out
64K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
21 · 10 core
Quality

Benchmark matrix

BenchmarkClaude Opus 4.1Claude Sonnet 4.5ΔEdge
Reported by both · 6
SWE-bench Verified74.5% 77.2% -2.7 ptClaude Sonnet 4.5
GPQA Diamond77.3% epoch83.4% -6.1 ptClaude Sonnet 4.5
FrontierMath Tier 4 v2 (Epoch AI run)2.4% epoch2.4% epoch0Tie
FrontierMath Tiers 1-3 v2 (Epoch AI run)12.6% epoch23.9% epoch-11.3 ptClaude Sonnet 4.5
OTIS Mock AIME 2024-2025 (Epoch AI run)68.9% epoch77.8% epoch-8.9 ptClaude Sonnet 4.5
SWE-bench Verified (Epoch AI run)73.3% epoch71.3% epoch+2 ptClaude Opus 4.1
Only Claude Opus 4.1 reports · 0
Claude Opus 4.1 reports nothing Claude Sonnet 4.5 does not.
Only Claude Sonnet 4.5 reports · 14
AIME 2025not reported84.2% matharena
Humanity's Last Exam (no tools)not reported17.7%
ARC-AGI-2 (Verified)not reported13.6%
GDPval-AAnot reported1276
Humanity's Last Exam (with tools)not reported33.6%
MCP Atlasnot reported43.8%
MMMLUnot reported89.5%
MMMU-Pro (no tools)not reported63.4%
MMMU-Pro (with tools)not reported68.9%
OSWorld-Verifiednot reported61.4%
SimpleQA Verifiednot reported30.7% epoch
Tau2-bench Retailnot reported86.2%
Tau2-bench Telecomnot reported98%
Terminal-Bench 2.0not reported51%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Opus 4.1 minus Claude Sonnet 4.5 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecClaude Opus 4.1Claude Sonnet 4.5Edge
Context window200K tokens200K tokensTie
Max output32K tokens64K tokensClaude Sonnet 4.5
Input price / 1M$15 $3 Claude Sonnet 4.5
Output price / 1M$75 $15 Claude Sonnet 4.5
Cached input / 1M$1.5 $0.3 Claude Sonnet 4.5
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$90$18Claude Sonnet 4.5
Modalitiestext · visiontext · visionTie
Released2025-08-052025-09-29
Cited benchmark scores621
Reliability

Anthropic status

All providers
More matchups

Claude Opus 4.1 vs …

More matchups

Claude Sonnet 4.5 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 4.1 and Claude Sonnet 4.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.