Claude Opus 5

AnthropicKey claude-opus-5Also reported as anthropic/claude-opus-5, router_client:claude/claude-opus-5, kiro/claude-opus-5, teamclaude/claude-opus-5, claude/claude-opus-5, cbai/claude-opus-5, devin/claude-opus-5, vilao/ccf/claude-opus-5, cursor/claude-opus-5, orcarouter/anthropic/claude-opus-5, my anthropic sub/claude-opus-5, pve-claude-mjlee/claude-opus-5, router_client:unknown/claude-opus-5, aion/claude-opus-5, hr-kr/claude-opus-5, a6/claude-opus-5, th/claude-opus-5, vilao/claude-opus-5, s6o/claude-opus-5, sekai/claude-opus-5

Rank
#16
by active users
Active users
163
Down 493 from 656 active users in the previous 30 days. vs previous 30 days
Adoption
17%
of 958 accounts
Tokens
87.7B
cache included
Est. cost
$82.5K
at public list prices
First seen
Jul 6, 2026
in any submission

Oct 14 – Nov 12, 2026 (UTC)958 accounts100% of tokens from an identified modelData through Nov 12, 2026, 00:47 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

1 active users on Nov 12, 2026

Daily active users for Claude Opus 5, Oct 14, 2026 to Nov 12, 2026. Peak 49. Use the left and right arrow keys to read each day.50250
Show daily values
Daily active users and tokens for Claude Opus 5
Date (UTC)Active usersTokens
Oct 14, 2026364.9B
Oct 15, 2026442.7B
Oct 16, 2026453.9B
Oct 17, 2026181.5B
Oct 18, 2026383.5B
Oct 19, 2026495.2B
Oct 20, 2026485.6B
Oct 21, 2026415.5B
Oct 22, 2026455.6B
Oct 23, 2026334B
Oct 24, 2026271.1B
Oct 25, 202620719.8M
Oct 26, 2026393.7B
Oct 27, 2026373.7B
Oct 28, 2026292.2B
Oct 29, 2026322.8B
Oct 30, 2026293.6B
Oct 31, 2026231.7B
Nov 1, 2026262B
Nov 2, 2026302.3B
Nov 3, 2026281.3B
Nov 4, 202623885.6M
Nov 5, 2026231.6B
Nov 6, 2026241.8B
Nov 7, 2026183B
Nov 8, 2026205.6B
Nov 9, 2026233.8B
Nov 10, 2026172.4B
Nov 11, 2026121.2B
Nov 12, 2026150.2K

Token mix

How the 87.7B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input1.9%
  • Output0.4%
  • Cache read94%
  • Cache write3.9%
  • Reasoning<0.1%

Agents that carry Claude Opus 5

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

  1. Claude Code85% of this model's tokens143active users
  2. Senpi (OmO Native)6.7% of this model's tokens26active users
  3. Oh My Pi4.0% of this model's tokens4active users
  4. Hermes Agent1.3% of this model's tokens3active users
  5. OpenCode1.2% of this model's tokens3active users
  6. ZCode0.8% of this model's tokens1active users
  7. Pi0.3% of this model's tokens6active users
  8. DeepSeek Harness0.2% of this model's tokens1active users
  9. Aside0.1% of this model's tokens2active users
  10. Grok Build<0.1% of this model's tokens1active users
  11. Codex CLI<0.1% of this model's tokens1active users
  12. Junie<0.1% of this model's tokens1active users
  13. Droid<0.1% of this model's tokens1active users

Benchmarks

The best result for Claude Opus 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
    163.9
    Rank #7 of 160 matched modelsNo conditions reportedModel released Jul 24, 2026Source: epoch.ai (opens in a new tab)
  • Terminal-Bench 4.0Agentic coding · Terminal-Bench
    53.9%
    Rank #6 of 23 matched modelsXHigh · Claude CodePublished Sep 17, 2026Source: tbench.ai (opens in a new tab)

    Tokscale usage: Claude Code carried 85% of Claude Opus 5 tokens in the last 30 days (143 active users).

    Show 4 more results with other run conditionsHide the other results
    • Listed as Opus 5
      51.8%
      Max · Claude CodePublished Aug 27, 2026Source: tbench.ai (opens in a new tab)
    • Listed as Opus 5
      50.3%
      High · Claude CodePublished Sep 17, 2026Source: tbench.ai (opens in a new tab)
    • Listed as Opus 5
      44.9%
      Medium · Claude CodePublished Sep 17, 2026Source: tbench.ai (opens in a new tab)
    • Listed as Opus 5
      34.8%
      Low · Claude CodePublished Sep 17, 2026Source: tbench.ai (opens in a new tab)
  • CursorBenchAgentic coding · Cursor, collected by Epoch AI
    46.6%
    Rank #7 of 18 matched modelsMaxModel released Jul 24, 2026Source: cursor.com (opens in a new tab)
    Show 4 more results with other run conditionsHide the other results
    • Listed as Opus 5 Extra High
      46.1%
      XHighModel released Jul 24, 2026Source: cursor.com (opens in a new tab)
    • Listed as Opus 5 High
      44.7%
      HighModel released Jul 24, 2026Source: cursor.com (opens in a new tab)
    • Listed as Opus 5 Medium
      43.3%
      MediumModel released Jul 24, 2026Source: cursor.com (opens in a new tab)
    • Listed as Opus 5 Low
      40.7%
      LowModel released Jul 24, 2026Source: cursor.com (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    73.6%
    Rank #3 of 26 matched modelsMax · mini-swe-agentModel released Jul 24, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    Show 4 more results with other run conditionsHide the other results
    • Listed as claude-opus-5 (xhigh)
      73.2%
      XHigh · mini-swe-agentModel released Jul 24, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as claude-opus-5 (high)
      72.8%
      High · mini-swe-agentModel released Jul 24, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as claude-opus-5 (medium)
      68.9%
      Medium · mini-swe-agentModel released Jul 24, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as claude-opus-5 (low)
      58.1%
      Low · mini-swe-agentModel released Jul 24, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • FrontierSWEAgentic coding · FrontierSWE, collected by Epoch AI
    52.0%
    Rank #6 of 21 matched modelsMax · proximusModel released Jul 24, 2026Source: frontierswe.com (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,689
    Rank #7 of 110 matched modelsMaxPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as Claude Opus 5 (High)
      1,659
      HighPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • Agent ArenaAgents · LMArena
    +0.08
    Rank #9 of 48 matched modelsMax · Arena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    93.9%
    Rank #14 of 151 matched modelsMaxRun date Jul 24, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.4%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

    Show 2 more results with other run conditionsHide the other results
    • Listed as claude-opus-5
      92.9%
      No conditions reportedRun date Aug 6, 2026Source: epoch.ai (opens in a new tab)
    • Listed as claude-opus-5_low
      87.9%
      LowRun date Aug 6, 2026Source: epoch.ai (opens in a new tab)
  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    85.6%
    Rank #12 of 86 matched modelsMaxRun date Jul 24, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 93.7%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    59.9%
    Rank #17 of 80 matched modelsMaxRun date Aug 10, 2026Source: epoch.ai (opens in a new tab)

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

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Oct 21, 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
$0.90
Est. per 1M tokens
94% cache reads
At the community mix
$0.76
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$10
Per 1M tokens at list prices
No cache

Cache reads were 94% of Claude Opus 5 tokens in the last 30 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 $5, output $25, cache read $0.50, cache write $6.25.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 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-opus-5
    $5 input per 1M tokens$25 output per 1M tokens$0.50 cache read per 1M tokens$6.25 cache write per 1M tokens1M tokens of context
  • Amazon Bedrockanthropic.claude-opus-5
    $5 input per 1M tokens$25 output per 1M tokens$0.50 cache read per 1M tokens$6.25 cache write per 1M tokens1M tokens of context
  • Vertexclaude-opus-5@default
    $5 input per 1M tokens$25 output per 1M tokens$0.50 cache read per 1M tokens$6.25 cache write per 1M tokens1M tokens of context
  • Vertex (Anthropic)claude-opus-5@default
    $5 input per 1M tokens$25 output per 1M tokens$0.50 cache read per 1M tokens$6.25 cache write per 1M tokens1M tokens of context
Show 3 more providersShow fewer providers
  • Azureclaude-opus-5
    $5 input per 1M tokens$25 output per 1M tokens$0.50 cache read per 1M tokens$6.25 cache write per 1M tokens1M tokens of context
  • OpenRouteranthropic/claude-opus-5
    $5 input per 1M tokens$25 output per 1M tokens$0.50 cache read per 1M tokens$6.25 cache write per 1M tokens1M tokens of context
  • Vercel AI Gatewayanthropic/claude-opus-5
    $5 input per 1M tokens$25 output per 1M tokens$0.50 cache read per 1M tokens$6.25 cache write per 1M tokens1M tokens of context

Specs

From models.dev (MIT), retrieved Oct 21, 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
May 2026
Release date
Jul 24, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

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

  1. 1Jeff Emanuel@Dicklesworthstone14.3Btokens$8.8Kest. cost16active days$8.8K est. cost · 16 active days
  2. 2Shad0w23333@Shad0w233335.7Btokens$4.2Kest. cost14active days$4.2K est. cost · 14 active days
  3. 3yunwang6131@yunwang61314.5Btokens$3.9Kest. cost26active days$3.9K est. cost · 26 active days
  4. 4Ing Tian@IngTian4.3Btokens$3.6Kest. cost19active days$3.6K est. cost · 19 active days
  5. 5Khaliq@khaliqgant4.1Btokens$4.2Kest. cost10active days$4.2K est. cost · 10 active days
  6. 6Daniel@daniel-diao3.7Btokens$2.4Kest. cost21active days$2.4K est. cost · 21 active days
  7. 7DayLab@daylab-official3.6Btokens$3Kest. cost7active days$3K est. cost · 7 active days
  8. 8Wooseok Sung@MercuriusDream3.1Btokens$3Kest. cost7active days$3K est. cost · 7 active days
  9. 9abilliontokens@abilliontokens3Btokens$3.3Kest. cost17active days$3.3K est. cost · 17 active days
  10. 10Limber Cheng@limberc2.9Btokens$5.6Kest. cost13active days$5.6K est. cost · 13 active days

More from Anthropic

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

  1. Claude Opus 5.574% adoption709active users
  2. Claude Sonnet 5.558% adoption555active users
  3. Claude Haiku 5.550% adoption477active users
  4. Claude Fable 5.138% adoption361active users
  5. Claude Opus 4.823% adoption222active users
  6. Claude Fable 5.218% adoption176active 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 Oct 21, 2026 · Data through Oct 15, 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 4.0 official leaderboard rows (results only, no task content).Terms not stated · Retrieved Oct 21, 2026 · Data through Oct 6, 2026Terminal-Bench 4.0 leaderboard, tbench.ai. Every score links back to the leaderboard.
  • models.devSpecs and list prices per provider.MIT · Retrieved Oct 21, 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