ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Opus 4.8vsClaude 3.7 Sonnet

Claude Opus 4.8 leads 3 of 3 shared benchmarks. Claude 3.7 Sonnet is 1.7x cheaper per token. Claude Opus 4.8 has the larger context window (1M tokens).

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

Shared benchmarks
3 – 0
Claude Opus 4.8 leads
Cheaper per token
Claude 3.7 Sonnet
1.7x cheaper, input + output
Larger context
Claude Opus 4.8
1M tokens
Provider uptime (30d)
100%
Anthropic
Claude Opus 4.8
Anthropic · released 2026-05-28
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$25
Cached /1M
$0.5
Scores
17 · 13 core
Claude 3.7 Sonnet
Anthropic · released 2025-02-24
textvision
Context
200K
Max out
128K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
5 · 5 core
Quality

Benchmark matrix

BenchmarkClaude Opus 4.8Claude 3.7 SonnetΔEdge
Reported by both · 3
SWE-bench Verified88.6% 70.3% +18.3 ptClaude Opus 4.8
GPQA Diamond93.6% 79.7% epoch+13.9 ptClaude Opus 4.8
OTIS Mock AIME 2024-2025 (Epoch AI run)98.3% epoch57.8% epoch+40.5 ptClaude Opus 4.8
Only Claude Opus 4.8 reports · 13
AIME 2026100% matharenanot reported
Humanity's Last Exam (no tools)49.8% not reported
LMArena Elo1452.7 not reported
BrowseComp84.3% not reported
FrontierMath Tier 4 v2 (Epoch AI run)56.1% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)80% epochnot reported
Humanity's Last Exam (with tools)57.9% not reported
OSWorld-Verified83.4% not reported
SimpleQA Verified53% epochnot reported
SWE-bench Multilingual84.4% not reported
SWE-bench Multimodal38.4% not reported
SWE-Bench Pro69.2% not reported
Terminal-Bench 2.174.6% not reported
Only Claude 3.7 Sonnet reports · 2
AIME 2025not reported49.2% matharena
SWE-bench Verified (Epoch AI run)not reported61% epoch
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 4.8 minus Claude 3.7 Sonnet 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 4.8Claude 3.7 SonnetEdge
Context window1M tokens200K tokensClaude Opus 4.8
Max output128K tokens128K tokensTie
Input price / 1M$5 $3 Claude 3.7 Sonnet
Output price / 1M$25 $15 Claude 3.7 Sonnet
Cached input / 1M$0.5 $0.3 Claude 3.7 Sonnet
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$30$18Claude 3.7 Sonnet
Modalitiestext · visiontext · visionTie
Released2026-05-282025-02-24
Cited benchmark scores175
Reliability

Anthropic status

All providers
More matchups

Claude Opus 4.8 vs …

More matchups

Claude 3.7 Sonnet vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Opus 4.8 and Claude 3.7 Sonnet on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.