Claude Sonnet 5 (Adaptive Reasoning, Max Effort)
By Anthropic · released 2026-06-30 (2 months) · snapshot 2026-09-09
- Intelligence index
- 38.40
- Cost to run the AA index
- $6998
- Price per 1M tokens (in / out)
- $2.00 / $10.0
- End-to-end time
- 184.8s
Is Claude Sonnet 5 (Adaptive Reasoning, Max Effort) on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-6 Astra (max) is at least as smart for the same money or less.
Next step up: Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | Anthropic | 38.40 | $6998 | 184.8s | 2026-06-30 | ||
| 2 | GPT-6 Astra (max) | OpenAI | 52.80 | $5324 | 331.3s | 2026-09-03 | Frontier | |
| 3 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback) | Anthropic | 53.20 | $9063 | 146.8s | 2026-09-01 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
Claude Sonnet 5 (Adaptive Reasoning, Max Effort) today
3 of 6 effort levels plotted. The remaining levels lack intelligence or benchmark cost data.
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: claude-sonnet-5.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- Claude Sonnet 5 (max) vs GPT-6 Astra (max)
- Claude Sonnet 5 (max) vs Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)
- Claude Sonnet 5 (max) vs Claude Sonnet 5 (Adaptive Reasoning, Low Effort)
- Claude Sonnet 5 (max) vs Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)
- Claude Sonnet 5 (max) vs Claude Sonnet 5 (Adaptive Reasoning, High Effort)
- Claude Sonnet 5 (max) vs Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)
- Claude Sonnet 5 (max) vs Claude Sonnet 5 (Non-reasoning, High Effort)
- Claude Sonnet 5 (max) vs GPT-6 Astra (medium)
- Claude Sonnet 5 (max) vs GPT-6 Astra (high)
- Claude Sonnet 5 (max) vs GPT-6 Astra (xhigh)
- Claude Sonnet 5 (max) vs Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)
Compare Claude Sonnet 5 (Adaptive Reasoning, Max Effort) with measured models
What the Claude Sonnet 5 release did to the frontier on 2026-06-30
None of its 6 effort levels reached the frontier at launch.
Closest miss: Claude Sonnet 5 (max), 0.2 points below GPT-5.5 (xhigh) at 1.3× the cost.
Should you use Claude Sonnet 5 (Adaptive Reasoning, Max Effort)?
Should you use Claude Sonnet 5 (Adaptive Reasoning, Max Effort)?
Only when it fits your setup: GPT-6 Astra (max) is at least as smart for the same money or less, so Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is off the value frontier today.
What is better and cheaper than Claude Sonnet 5 (Adaptive Reasoning, Max Effort)?
GPT-6 Astra (max) — at least as smart for the same money or less.
How much does Claude Sonnet 5 (Adaptive Reasoning, Max Effort) cost?
$2.00/$10 in/out per 1M tokens, and $6998 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is Claude Sonnet 5 (Adaptive Reasoning, Max Effort) on the Pareto frontier?
No: GPT-6 Astra (max) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where Claude Sonnet 5 (Adaptive Reasoning, Max Effort) is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/claude-sonnet-5 · Markdown: /api/v1/models/claude-sonnet-5?format=md · llms.txt · agent skill