ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.7 SonnetvsClaude Sonnet 4.5

Claude Sonnet 4.5 leads 5 of 5 shared benchmarks. Both list the same combined token price. Both offer a 200K-token context window.

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

Shared benchmarks
0 – 5
Claude Sonnet 4.5 leads
Cheaper per token
Tie
list price, input + output
Larger context
Tie
both 200K tokens
Provider uptime (30d)
100%
Anthropic
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
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 3.7 SonnetClaude Sonnet 4.5ΔEdge
Reported by both · 5
SWE-bench Verified70.3% 77.2% -6.9 ptClaude Sonnet 4.5
GPQA Diamond79.7% epoch83.4% -3.7 ptClaude Sonnet 4.5
AIME 202549.2% matharena84.2% matharena-35 ptClaude Sonnet 4.5
OTIS Mock AIME 2024-2025 (Epoch AI run)57.8% epoch77.8% epoch-20 ptClaude Sonnet 4.5
SWE-bench Verified (Epoch AI run)61% epoch71.3% epoch-10.3 ptClaude Sonnet 4.5
Only Claude 3.7 Sonnet reports · 0
Claude 3.7 Sonnet reports nothing Claude Sonnet 4.5 does not.
Only Claude Sonnet 4.5 reports · 15
Humanity's Last Exam (no tools)not reported17.7%
ARC-AGI-2 (Verified)not reported13.6%
FrontierMath Tier 4 v2 (Epoch AI run)not reported2.4% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported23.9% epoch
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 3.7 Sonnet 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 3.7 SonnetClaude Sonnet 4.5Edge
Context window200K tokens200K tokensTie
Max output128K tokens64K tokensClaude 3.7 Sonnet
Input price / 1M$3 $3 Tie
Output price / 1M$15 $15 Tie
Cached input / 1M$0.3 $0.3 Tie
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$18Tie
Modalitiestext · visiontext · visionTie
Released2025-02-242025-09-29
Cited benchmark scores521
Reliability

Anthropic status

All providers
More matchups

Claude 3.7 Sonnet 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 3.7 Sonnet and Claude Sonnet 4.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.