ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.7 SonnetvsGPT-5.4 Pro

GPT-5.4 Pro leads 1 of 1 shared benchmark. Claude 3.7 Sonnet is 11.7x cheaper per token. GPT-5.4 Pro has the larger context window (1.1M tokens).

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

Shared benchmarks
0 – 1
GPT-5.4 Pro leads
Cheaper per token
Claude 3.7 Sonnet
11.7x cheaper, input + output
Larger context
GPT-5.4 Pro
1.1M tokens
Provider uptime (30d)
100% · 94.4056%
Anthropic · OpenAI
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
GPT-5.4 Pro
OpenAI · released 2026-03-05
textvision
Context
1.1M
Max out
128K
Input /1M
$30
Output /1M
$180
Cached /1M
Scores
13 · 8 core
Quality

Benchmark matrix

BenchmarkClaude 3.7 SonnetGPT-5.4 ProΔEdge
Reported by both · 1
GPQA Diamond79.7% epoch94.4% -14.7 ptGPT-5.4 Pro
Only Claude 3.7 Sonnet reports · 4
SWE-bench Verified70.3% not reported
AIME 202549.2% matharenanot reported
OTIS Mock AIME 2024-2025 (Epoch AI run)57.8% epochnot reported
SWE-bench Verified (Epoch AI run)61% epochnot reported
Only GPT-5.4 Pro reports · 11
Humanity's Last Exam (no tools)not reported42.7%
ARC-AGI-1 (Verified)not reported94.5%
ARC-AGI-2 (Verified)not reported83.3%
BrowseCompnot reported89.3%
FrontierMath Tier 1-3not reported50%
FrontierMath Tier 4not reported38%
FrontierMath Tier 4 v2 (Epoch AI run)not reported58.5% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported82.5% epoch
GDPval (wins or ties)not reported82%
Humanity's Last Exam (with tools)not reported58.7%
SimpleQA Verifiednot reported46.3% 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 3.7 Sonnet minus GPT-5.4 Pro 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 SonnetGPT-5.4 ProEdge
Context window200K tokens1.1M tokensGPT-5.4 Pro
Max output128K tokens128K tokensTie
Input price / 1M$3 $30 Claude 3.7 Sonnet
Output price / 1M$15 $180 Claude 3.7 Sonnet
Cached input / 1M$0.3
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$210Claude 3.7 Sonnet
Modalitiestext · visiontext · visionTie
Released2025-02-242026-03-05
Cited benchmark scores513
Reliability

Provider status

All providers
More matchups

Claude 3.7 Sonnet vs …

More matchups

GPT-5.4 Pro vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude 3.7 Sonnet and GPT-5.4 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.