Claude Opus 5

AnthropicProprietaryReleased Jul 24, 2026

On the arena.ai Agents leaderboard, Claude Opus 5 has a Net Improvement of 7.50% (Max, rank #11, 95% interval 6.20%–8.79%). Claude Opus 5 ranks #15 on the LMArena Text leaderboard (style control) with an Arena score of 1489.9 (±3.6, 73,730 votes). API price: $5.00 input / $25.00 output per 1M tokens. Context: 1M. Nearest rivals: Muse Spark 1.1 (1490.6) above and Gemini 3.7 Flash (1489.3) below.

Quick answer

Agents leaderboard
#11 of 37 · 7.50% success
Text (LMArena)
#15 · 1489.9
17NAS overall
#11 of 36
API price (in / out)
$5.00 / $25.00 per 1M tokens
Data updated
Nov 9, 2026 · synced daily

Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter

Key metrics

Agent Net Improvement7.50%Max31,928 sessions · #11
Arena score1489.9±3.6LMArena #15 · 73,730 votes
Intelligence–Variant: max
Coding–Artificial Analysis
Writing (creative)1486.4±6.4LMArena creative writing #10 / 418
List price in / out$5.00 / $25.00USD per 1M tokens
Lowest route$5.00 / $25.00Cheapest OpenRouter route
Context1Mtokens
Output speed–AA measured median
TTFT / first answer–AA measured median

Rank history

LMArena rank, last 25 days
#12#14#16Oct 16Nov 9

#14 on Oct 16, #15 now; best #13 in this period.

Models ranked nearby

Sorted by Arena score
#ModelArenaIntel.Output $tok/s
10Muse Spark 1.31495.836.6$4.25–
11Muse Spark 1.21494.0–$4.25–
12Muse Spark 1.11490.6–$4.25–
13Claude Opus 5This page1489.9–$25.00–
14Gemini 3.7 Flash1489.3–$3.75–
15Muse Spark1489.0–––
16Kimi K31487.3–$15.00–

More from Anthropic

#ModelArenaIntel.Output $tok/s
4Claude Opus 5.51505.759.1$20.0096
5Claude Fable 51503.8–$50.00–
6Claude Fable 5.11503.149.2$50.0068
7Claude Opus 4.61502.9–$25.00–
8Claude Opus 4.71501.0–$25.00–
23Claude Opus 4.81482.0–$25.00–

Pricing

  • Official API list price: $5.00 input and $25.00 output per 1M tokens (USD).
  • At a typical 3:1 input-to-output ratio, the blended cost is about $10.00 per 1M tokens.
  • Among 68 models with an output price, it is the #59 cheapest.
  • The cheapest OpenRouter route charges $5.00 input / $25.00 output.

Sources & methodology

On the arena.ai Agents leaderboard, Claude Opus 5 has a Net Improvement of 7.50% (Max, rank #11, 95% interval 6.20%–8.79%).

  • arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
  • LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
  • Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
  • OpenRouter — Route prices, context length and listing date.

Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).

Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.

FAQ

How does Claude Opus 5 do on the Agents leaderboard?

On the arena.ai Agents leaderboard, Claude Opus 5 has a Net Improvement of 7.50% (Max, rank #11, 95% interval 6.20%–8.79%).

What rank is Claude Opus 5 right now?

Claude Opus 5 is #13 on our leaderboard of 64 scored models (Arena score 1489.9); its raw LMArena rank is #15.

What does Claude Opus 5 cost via API?

Input $5.00 / output $25.00 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $10.00 per 1M tokens.

How close is Claude Opus 5 to the models ranked next to it?

It is 0.7 points behind Muse Spark 1.1 (1490.6) and 0.6 points ahead of Gemini 3.7 Flash (1489.3); gaps smaller than the confidence interval (±3.6) are not significant.

Is Claude Opus 5 open source? Can it be self-hosted?

Claude Opus 5 is a closed model, available only via official APIs or hosted services.

What is the context length of Claude Opus 5?

1M (1,000,000 tokens, as listed on OpenRouter).

Claude Opus 5 vs Muse Spark 1.1: which is better?

On the LMArena Text leaderboard Claude Opus 5 scores 1489.9 and Muse Spark 1.1 scores 1490.6 (a 0.7-point gap, within the confidence interval, so not significant). Agent task success: Claude Opus 5 7.50%, Muse Spark 1.1 -7.86%. On price, Claude Opus 5 costs $25.00 and Muse Spark 1.1 $4.25 per 1M output tokens.

Is there a cheaper model close to Claude Opus 5?

Yes: Gemini 3.8 Flash scores 1497.5 on the Text leaderboard (Claude Opus 5: 1489.9) and costs $3.75 per 1M output tokens, about 85% less than Claude Opus 5 ($25.00).

Where does the Claude Opus 5 data come from and how often is it updated?

Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Nov 9, 2026.

Related leaderboards