Claude Sonnet 5

AnthropicKey claude-sonnet-5Also reported as router_client:claude/claude-sonnet-5, anthropic/claude-sonnet-5, kiro/claude-sonnet-5, orcarouter/anthropic/claude-sonnet-5, claude/claude-sonnet-5, gh/claude-sonnet-5, router_client:unknown/claude-sonnet-5, vy/claude-sonnet-5, vibeproxy/claude-sonnet-5, sub-bridge/claude-sonnet-5, cursor/claude-sonnet-5, frg/claude-sonnet-5, cc/claude-sonnet-5, dario/claude-sonnet-5, omni/claude/claude-sonnet-5

Rank
#20
by active users
Active users
38
Down 24 from 62 active users in the previous 7 days. vs previous 7 days
Adoption
6.2%
of 610 accounts
Tokens
30.9B
cache included
Est. cost
$8.3K
at public list prices
First seen
Apr 14, 2026
in any submission

Nov 6–12, 2026 (UTC)610 accounts100% of tokens from an identified modelData through Nov 12, 2026, 08:05 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

8 active users on Nov 12, 2026

Daily active users for Claude Sonnet 5, Nov 6, 2026 to Nov 12, 2026. Peak 23. Use the left and right arrow keys to read each day.25130
Show daily values
Daily active users and tokens for Claude Sonnet 5
Date (UTC)Active usersTokens
Nov 6, 2026236.1B
Nov 7, 2026183.6B
Nov 8, 2026188.5B
Nov 9, 2026191.9B
Nov 10, 2026168.2B
Nov 11, 2026132.2B
Nov 12, 20268322M

Token mix

How the 30.9B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input<0.1%
  • Output0.3%
  • Cache read98%
  • Cache write1.8%
  • Reasoning<0.1%

Agents that carry Claude Sonnet 5

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. Claude Code100% of this model's tokens34active users
  2. Pi0.2% of this model's tokens2active users
  3. Senpi (OmO Native)0.1% of this model's tokens5active users
  4. Hermes Agent<0.1% of this model's tokens1active users

Benchmarks

The best result for Claude Sonnet 5 in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark. Agent rows also show Tokscale usage through that agent, side by side with the score. Usage does not explain the score.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    156.9
    Rank #33 of 158 matched modelsNo conditions reportedModel released Jun 30, 2026Source: epoch.ai (opens in a new tab)
  • Terminal-Bench 4.1Agentic coding · Terminal-Bench
    12.1%
    Rank #23 of 23 matched modelsMax · Claude CodePublished Nov 3, 2026Source: tbench.ai (opens in a new tab)

    Tokscale usage: Claude Code carried 100% of Claude Sonnet 5 tokens in the last 7 days (34 active users).

  • CursorBenchAgentic coding · Cursor, collected by Epoch AI
    34.1%
    Rank #20 of 21 matched modelsMaxModel released Jun 30, 2026Source: cursor.com (opens in a new tab)
    Show 4 more results with other run conditionsHide the other results
    • Listed as Sonnet 5 Extra High
      32.0%
      XHighModel released Jun 30, 2026Source: cursor.com (opens in a new tab)
    • Listed as Sonnet 5 High
      30.8%
      HighModel released Jun 30, 2026Source: cursor.com (opens in a new tab)
    • Listed as Sonnet 5 Medium
      28.0%
      MediumModel released Jun 30, 2026Source: cursor.com (opens in a new tab)
    • Listed as Sonnet 5 Low
      24.1%
      LowModel released Jun 30, 2026Source: cursor.com (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    53.8%
    Rank #17 of 26 matched modelsMax · mini-swe-agentModel released Jun 30, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    Show 4 more results with other run conditionsHide the other results
    • Listed as claude-sonnet-5 (xhigh)
      49.7%
      XHigh · mini-swe-agentModel released Jun 30, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as claude-sonnet-5 (high)
      48.2%
      High · mini-swe-agentModel released Jun 30, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as claude-sonnet-5 (medium)
      39.8%
      Medium · mini-swe-agentModel released Jun 30, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as claude-sonnet-5 (low)
      30.5%
      Low · mini-swe-agentModel released Jun 30, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,540
    Rank #42 of 110 matched modelsHighPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • Agent ArenaAgents · LMArena
    +0.04
    Rank #11 of 48 matched modelsHigh · Arena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    90.5%
    Rank #42 of 160 matched modelsXHighRun date Jul 1, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.5%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

    Show 1 more result with other run conditionsHide the other results
    • Listed as claude-sonnet-5_max
      80.3%
      MaxRun date Aug 6, 2026Source: epoch.ai (opens in a new tab)
  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    65.6%
    Rank #40 of 90 matched modelsMaxRun date Jun 30, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 95.1%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    33.7%
    Rank #62 of 86 matched modelsMaxRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as claude-sonnet-5_xhigh
      32.9%
      XHighRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, FrontierSWE. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. Anthropic is the lab's own API and the reference price for the estimates below.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.27
Est. per 1M tokens
98% cache reads
At the community mix
$0.30
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$4
Per 1M tokens at list prices
No cache

Cache reads were 98% of Claude Sonnet 5 tokens in the last 7 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • Anthropic list prices per 1M tokens: input $2, output $10, cache read $0.20, cache write $2.50.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 7 days.
  • The community mix is the tokens of every identified model in the last 7 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.

List prices by provider

  • AnthropicReferenceclaude-sonnet-5
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2.50 cache write per 1M tokens1M tokens of context
  • Amazon Bedrockanthropic.claude-sonnet-5
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2.50 cache write per 1M tokens1M tokens of context
  • Vertexclaude-sonnet-5@default
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2.50 cache write per 1M tokens1M tokens of context
  • Vertex (Anthropic)claude-sonnet-5@default
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2.50 cache write per 1M tokens1M tokens of context
Show 3 more providersShow fewer providers
  • Azureclaude-sonnet-5
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2.50 cache write per 1M tokens1M tokens of context
  • OpenRouteranthropic/claude-sonnet-5
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2.50 cache write per 1M tokens1M tokens of context
  • Vercel AI Gatewayanthropic/claude-sonnet-5
    $2 input per 1M tokens$10 output per 1M tokens$0.20 cache read per 1M tokens$2.50 cache write per 1M tokens1M tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
1M tokens
Max output
128K tokens
Input
Text, Image, PDF
Output
Text
Knowledge cutoff
Jan 31, 2026
Release date
Jun 29, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Claude Sonnet 5 most in this period, by tokens. Hidden accounts are never listed.

  1. 1G Man@genx7up20.3Btokens$5.3Kest. cost6active days$5.3K est. cost · 6 active days
  2. 2midego@midego17.7Btokens$1.7Kest. cost3active days$1.7K est. cost · 3 active days
  3. 3Robin Dirksen@robindirksen1882.5Mtokens$199est. cost7active days$199 est. cost · 7 active days
  4. 4Koala@koalaauto520.1Mtokens$159est. cost4active days$159 est. cost · 4 active days
  5. 5Bae-ChangHyun@Changroro440.7Mtokens$107est. cost5active days$107 est. cost · 5 active days
  6. 6Jonathannkayy@Jonathannkayy234.7Mtokens$538est. cost7active days$538 est. cost · 7 active days
  7. 7Burak@drementer143.7Mtokens$35est. cost3active days$35 est. cost · 3 active days
  8. 8registered2nd@registered2nd140Mtokens$72est. cost6active days$72 est. cost · 6 active days
  9. 9Mark Ferraz@mferraznw87.5Mtokens$32est. cost3active days$32 est. cost · 3 active days
  10. 10SuperStar@superstar88285.4Mtokens$33est. cost3active days$33 est. cost · 3 active days

More from Anthropic

Other Anthropic models in the same period, by active users.

  1. Claude Opus 5.571% adoption434active users
  2. Claude Sonnet 5.545% adoption277active users
  3. Claude Haiku 5.541% adoption249active users
  4. Claude Fable 5.232% adoption197active users
  5. Claude Fable 5.125% adoption154active users
  6. Claude Opus 58.2% adoption50active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • Epoch AIEpoch Capabilities Index, Epoch's own runs and the external results it collects.CC BY 4.0 · Retrieved Nov 12, 2026 · Data through Nov 9, 2026Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.
  • LMArenaWebDev Arena and Agent Arena leaderboards.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 19, 2026LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), Hugging Face.
  • Terminal-BenchTerminal-Bench 4.1 official leaderboard rows (results only, no task content).Terms not stated · Retrieved Nov 12, 2026 · Data through Nov 11, 2026Terminal-Bench 4.1 leaderboard, tbench.ai. Every score links back to the leaderboard.
  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count