Skip to content

Claude Sonnet 4.6 vs Claude Sonnet 5

Close to a tie overall. They cost the same, and both read a 1M-token context.

Claude Sonnet 4.6

by Anthropic · #17 of 67 overall

Coming soon · price at launch
Context
1M
Input / 1M
$3.00
Output / 1M
$15.00

Claude Sonnet 5

by Anthropic · #20 of 67 overall

Coming soon · price at launch
Context
1M
Input / 1M
$3.00
Output / 1M
$15.00

Better overall

About even

Grade 79.2 vs 77.4

Cheaper

Same price

Both $6.00 blended

Larger context

Same

1M vs 1M tokens

SWE-bench Verified

Claude Sonnet 5

79.6% vs 85.2%

Head to head

Public benchmarks. Longer is better; each value links to its source.

LMArena TextElo-style rating · LMArena (CC BY 4.0) · Oct 15, 2026
Claude Sonnet 4.6Claude Sonnet 4.6: 1,472
Claude Sonnet 5Claude Sonnet 5: 1,461
LMArena WebDevElo-style rating · LMArena (CC BY 4.0) · Oct 13, 2026
Claude Sonnet 4.6Claude Sonnet 4.6: 1,522
Claude Sonnet 5Claude Sonnet 5: 1,540
LMArena CodingElo-style rating · LMArena (CC BY 4.0) · Oct 15, 2026
Claude Sonnet 4.6Claude Sonnet 4.6: 1,528
Claude Sonnet 5Claude Sonnet 5: 1,520
SWE-bench Verified% of issues resolved · SWE-bench · Jun 30, 2026 · reference
Claude Sonnet 4.6Claude Sonnet 4.6: 79.6%v
SWE-Bench Pro% of tasks resolved · Scale AI SWE-Bench Pro · Jun 30, 2026 · reference
Claude Sonnet 4.6Claude Sonnet 4.6: —
Terminal-Bench 4.0% of tasks passed · Terminal-Bench · Sep 28, 2026 · reference
Claude Sonnet 4.6Claude Sonnet 4.6: —
Terminal-Bench 2.1% of tasks passed · Terminal-Bench · Jun 30, 2026 · reference
Claude Sonnet 4.6Claude Sonnet 4.6: —
Terminal-Bench 2.0% of tasks passed · Terminal-Bench · Feb 17, 2026 · reference
Claude Sonnet 4.6Claude Sonnet 4.6: 59.1%v
Claude Sonnet 5Claude Sonnet 5: —

Claude Sonnet 4.6Claude Sonnet 5v = reported by the model’s maker. — = no public score yet. Arena bars span the range across every model we grade.

What it costs you

Drag to match your monthly usage.

Claude Sonnet 4.6$1,200 /month
Claude Sonnet 5$1,200 /month

They cost the same at this usage.

At a glance

AttributeClaude Sonnet 4.6Claude Sonnet 5
Made byAnthropicAnthropic
AvailabilityComing soonComing soon
Overall gradeExcellent · 79.2Excellent · 77.4
Overall rank#17 of 67#20 of 67
Input price$3.00 per 1M$3.00 per 1M
Output price$15.00 per 1M$15.00 per 1M
Context window1,000,000 tokens1,000,000 tokens
Reasoning levelsYesYes
Reads imagesYesYes
Model IDclaude-sonnet-4-6claude-sonnet-5

Try both with one key

Same endpoint, same key, both hosted in the USA. Change one word to switch models, in Claude Code, Cursor, Cline or your own code.

Get your API key
# Ask either model the same thing
curl https://fullsendai.com/v1/chat/completions \
  -H "Authorization: Bearer $FULLSEND_API_KEY" \
  -d '{"model": "claude-sonnet-4-6", "messages": [...]}'

# …then swap one word
  -d '{"model": "claude-sonnet-5", "messages": [...]}'

Questions

Is Claude Sonnet 4.6 or Claude Sonnet 5 better?

They grade within two points of each other (79.2 and 77.4), so pick on price and the benchmarks that match your work.

Which is cheaper, Claude Sonnet 4.6 or Claude Sonnet 5?

Claude Sonnet 4.6: $3.00 in and $15.00 out per million tokens, against $3.00 and $15.00 through FullsendAI.

Which has the larger context window?

Neither: both take 1,000,000 tokens.

Can I use both with one API key?

Yes, once they launch: both are coming soon, at the prices shown, and both will use the same FullsendAI key.

Model rankingsAll benchmarksCompare other models

Scores: LMArena (CC BY 4.0), SWE-bench, Scale AI SWE-Bench Pro, Terminal-Bench, and model makers’ published results where marked v. Prices are FullsendAI’s, per million tokens. Data as of Oct 28, 2026.