ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Sonnet 4vsGPT-5.4 nano

GPT-5.4 nano leads 2 of 2 shared benchmarks. GPT-5.4 nano is 12.4x cheaper per token. GPT-5.4 nano has the larger context window (400K tokens).

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

Shared benchmarks
0 – 2
GPT-5.4 nano leads
Cheaper per token
GPT-5.4 nano
12.4x cheaper, input + output
Larger context
GPT-5.4 nano
400K tokens
Provider uptime (30d)
100% · 94.386%
Anthropic · OpenAI
Claude Sonnet 4
Anthropic · released 2025-05-22
textvision
Context
200K
Max out
64K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
4 · 4 core
GPT-5.4 nano
OpenAI · released 2026-03-17
textvision
Context
400K
Max out
128K
Input /1M
$0.2
Output /1M
$1.25
Cached /1M
$0.02
Scores
10 · 6 core
Quality

Benchmark matrix

BenchmarkClaude Sonnet 4GPT-5.4 nanoΔEdge
Reported by both · 2
GPQA Diamond79.2% epoch82.8% -3.6 ptGPT-5.4 nano
OTIS Mock AIME 2024-2025 (Epoch AI run)71.1% epoch87.8% epoch-16.7 ptGPT-5.4 nano
Only Claude Sonnet 4 reports · 2
SWE-bench Verified72.7% not reported
AIME 2024 (no extended thinking)33.1% not reported
Only GPT-5.4 nano reports · 7
FrontierMath Tier 4 v2 (Epoch AI run)not reported12.2% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported44.9% epoch
OSWorld-Verifiednot reported39%
SimpleQA Verifiednot reported11.7% epoch
SWE-Bench Pronot reported52.4%
Terminal-Bench 2.0not reported46.3%
Toolathlonnot reported35.5%
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 Sonnet 4 minus GPT-5.4 nano 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 Sonnet 4GPT-5.4 nanoEdge
Context window200K tokens400K tokensGPT-5.4 nano
Max output64K tokens128K tokensGPT-5.4 nano
Input price / 1M$3 $0.2 GPT-5.4 nano
Output price / 1M$15 $1.25 GPT-5.4 nano
Cached input / 1M$0.3 $0.02 GPT-5.4 nano
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$1.45GPT-5.4 nano
Modalitiestext · visiontext · visionTie
Released2025-05-222026-03-17
Cited benchmark scores410
Reliability

Provider status

All providers
More matchups

Claude Sonnet 4 vs …

More matchups

GPT-5.4 nano vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Sonnet 4 and GPT-5.4 nano on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.