// head_to_head

Claude Sonnet 4.6 vs GPT-5.4

Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.

OpenRouter + LiveBenchAll comparisonsFull leaderboard

GPT-5.4 is the better model, at roughly the same price.

GPT-5.4 leads by 5.0 points overall and the two list within about 10% of each other, so the cheaper-but-weaker trade-off does not apply. Price parity plus a score gap usually makes this an easy call. Claude Sonnet 4.6 also leads on measured cost per point of capability, at $0.1561 per point.

anthropic

Claude Sonnet 4.6

Blended / 1M
$6.00
Context
1M
Released
Feb 17, 2026
Overall score
73.0
reasoningtool callingimage inputfile inputprompt caching

openai

GPT-5.4

Blended / 1M
$5.63
Context
1.1M
Released
Mar 5, 2026
Overall score
78.0
reasoningtool callingimage inputfile inputprompt caching

Specs and pricing

MetricClaude Sonnet 4.6GPT-5.4
LiveBench overall

Mean of the seven LiveBench category scores, 0–100. Higher is better.

73.078.0win
Cost per point

Measured benchmark spend divided by overall score — dollars per point of capability.

$0.1561win$0.2198
Blended price / 1M

3:1 input:output mix, the usual shape of production traffic.

$6.00$5.63
Input price / 1M$3.00$2.50win
Output price / 1M$15.00$15.00
Cached input / 1M

Price of an input token served from the prompt cache, where the provider publishes one.

$0.300$0.250win
Context window1M1.1M
Max output tokens128K128K

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Claude Sonnet 4.6 on top, GPT-5.4 below, both out of 100.

Agentic coding
42.6
53.8
Coding
79.3
77.5
Reasoning
84.8
88.1
Mathematics
87.0
94.1
Data analysis
77.9
79.3
Language
76.1
82.6
Instruction following
63.2
70.2

What each one costs to run

Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.

WorkloadClaude Sonnet 4.6GPT-5.4
Support chatbot

1.2K in / 400 out × 200K requests

$1725.60/mo$1638.00/mo
RAG assistant

8K in / 600 out × 100K requests

$2220.00/mo$2000.00/mo
Coding agent

40K in / 4K out × 20K requests

$2088.00/mo$1940.00/mo
Document extraction

20K in / 1.5K out × 50K requests

$3990.00/mo$3512.50/mo
Bulk classification

500 in / 20 out × 5M requests

$7650.00/mo$6625.00/mo
Run these two through the cost calculator

Which should you pick?

You are running this at volume

Claude Sonnet 4.6

Lowest measured cost per point of capability at $0.1561 per point — the gap compounds with every request.

Quality matters more than the bill

GPT-5.4

Highest overall LiveBench score of the two at 78.0.

The workload is coding or agentic work

GPT-5.4

Leads on agentic coding — 53.8 against 42.6.

Claude Sonnet 4.6 vs GPT-5.4 FAQ

Which is better, Claude Sonnet 4.6 or GPT-5.4?

GPT-5.4 is the better model, at roughly the same price. GPT-5.4 leads by 5.0 points overall and the two list within about 10% of each other, so the cheaper-but-weaker trade-off does not apply. Price parity plus a score gap usually makes this an easy call. Claude Sonnet 4.6 also leads on measured cost per point of capability, at $0.1561 per point.

Is Claude Sonnet 4.6 cheaper than GPT-5.4?

They cost about the same. Both land near $6.00 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.

Claude Sonnet 4.6 vs GPT-5.4: which scores higher on benchmarks?

Claude Sonnet 4.6 scores 73.0 and GPT-5.4 scores 78.0 overall on LiveBench, the mean of its seven categories. That is a 5.0-point lead for GPT-5.4. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.

Which gives better value for money, Claude Sonnet 4.6 or GPT-5.4?

Claude Sonnet 4.6. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. Claude Sonnet 4.6 works out at $0.1561 per point and GPT-5.4 at $0.2198.

Does Claude Sonnet 4.6 or GPT-5.4 have a bigger context window?

They are effectively the same — 1M for Claude Sonnet 4.6 and 1.1M for GPT-5.4.

Do Claude Sonnet 4.6 and GPT-5.4 support prompt caching?

Both publish a cached-input rate: $0.300 per million for Claude Sonnet 4.6 and $0.250 for GPT-5.4, against full input rates of $3.00 and $2.50. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.

Related comparisons

How these numbers are produced

  • Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
  • ScoresLiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
  • Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
  • “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.

Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.