ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 5vsClaude Sonnet 4.6

Claude Opus 5 leads 4 of 4 shared benchmarks. Claude Sonnet 4.6 is 1.7x cheaper per token. Both offer a 1M-token context window.

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

Shared benchmarks
4 – 0
Claude Opus 5 leads
Cheaper per token
Claude Sonnet 4.6
1.7x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100%
Anthropic
Claude Opus 5
Anthropic · released 2026-07-24
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$25
Cached /1M
$0.5
Scores
9 · 6 core
Claude Sonnet 4.6
Anthropic · released 2026-02-17
textvision
Context
1M
Max out
128K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
19 · 8 core
Quality

Benchmark matrix

BenchmarkClaude Opus 5Claude Sonnet 4.6ΔEdge
Reported by both · 4
GPQA Diamond93.9% epoch89.9% +4 ptClaude Opus 5
Humanity's Last Exam (no tools)56.6% 33.2% +23.4 ptClaude Opus 5
OTIS Mock AIME 2024-2025 (Epoch AI run)98.9% epoch85.8% epoch+13.1 ptClaude Opus 5
SimpleQA Verified59.9% epoch35.5% epoch+24.4 ptClaude Opus 5
Only Claude Opus 5 reports · 5
CursorBench 3.2.070% not reported
FrontierMath Tier 4 v2 (Epoch AI run)73.2% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)85.6% epochnot reported
GDPval-AA v21824 not reported
Terminal-Bench Science 0.129% not reported
Only Claude Sonnet 4.6 reports · 14
SWE-bench Verifiednot reported79.6%
LMArena Elonot reported1458.3
ARC-AGI-2 (Verified)not reported58.3%
GDPval-AAnot reported1633
Humanity's Last Exam (with tools)not reported49%
MCP Atlasnot reported61.3%
MMMLUnot reported89.3%
MMMU-Pro (no tools)not reported74.5%
MMMU-Pro (with tools)not reported75.6%
OSWorld-Verifiednot reported72.5%
SWE-bench Verified (Epoch AI run)not reported75.2% epoch
Tau2-bench Retailnot reported91.7%
Tau2-bench Telecomnot reported97.9%
Terminal-Bench 2.0not reported59.1%
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 5 minus Claude Sonnet 4.6 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 5Claude Sonnet 4.6Edge
Context window1M tokens1M tokensTie
Max output128K tokens128K tokensTie
Input price / 1M$5 $3 Claude Sonnet 4.6
Output price / 1M$25 $15 Claude Sonnet 4.6
Cached input / 1M$0.5 $0.3 Claude Sonnet 4.6
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$30$18Claude Sonnet 4.6
Modalitiestext · visiontext · visionTie
Released2026-07-242026-02-17
Cited benchmark scores919
Reliability

Anthropic status

All providers
More matchups

Claude Opus 5 vs …

More matchups

Claude Sonnet 4.6 vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 5 and Claude Sonnet 4.6 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.