Claude Sonnet 5
AnthropicProprietaryReleased Jun 30, 2026
On the arena.ai Agents leaderboard, Claude Sonnet 5 has a task success rate of 4.15% (High, rank #11, 95% interval 2.46%–5.84%). Claude Sonnet 5 ranks #58 on the LMArena Text leaderboard (style control) with an Arena score of 1460.9 (±4.1, 50,871 votes). Artificial Analysis Intelligence Index: 38.2. API price: $2.00 input / $10.00 output per 1M tokens. Context: 1M. Nearest rivals: DeepSeek V4 Pro (1464.6) above and Kimi K2.6 (1460.9) below.
Quick answer
- Agents leaderboard
- #11 of 45 · 4.15% success
- Text (LMArena)
- #58 · 1460.9
- 17NAS overall
- #11 of 86
- API price (in / out)
- $2.00 / $10.00 per 1M tokens
- Closest rival
- DeepSeek V4 Pro · 1464.6
- Cheaper alternative
- DeepSeek V4.1 Flash: Text 1475.3, output $1.20 (88% cheaper)
- Data updated
- Oct 22, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
Reasoning effort comparison
Artificial Analysis measurements per reasoning effort of the same model| Effort | Intelligence | Coding | tok/s | TTFT (s) | First answer (s) |
|---|---|---|---|---|---|
| maxUsed in table | 38.2 | 71.5 | – | – | – |
| xhigh | 34.4 | – | – | – | – |
| high | 31.7 | – | – | – | – |
| medium | 28.1 | – | – | – | – |
| low | 24.3 | – | – | – | – |
| non-reasoning | 23.2 | 66.4 | – | – | – |
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 40 |  Grok 4.5 | 1465.4 | 38.8 | $6.00 | – |
| 41 |  GLM-5.1 | 1465.4 | 26.1 | $4.07 | – |
| 42 |  DeepSeek V4 Pro | 1464.6 | 36.0 | $3.96 | 91 |
| 43 | Claude Sonnet 5This page | 1460.9 | 38.2 | $10.00 | – |
| 44 |  Kimi K2.6 | 1460.9 | 27.0 | $4.00 | – |
| 45 |  Qwen3.6 Max | 1460.1 | 28.4 | – | – |
| 46 |  GPT-6 Sol | 1458.8 | 47.6 | $10.00 | – |
More from Anthropic
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 3 | Claude Opus 5.5 | 1508.8 | 57.6 | $20.00 | 98 |
| 4 | Claude Fable 5 | 1503.7 | 49.6 | $50.00 | – |
| 5 | Claude Opus 4.6 | 1502.6 | 31.9 | $25.00 | – |
| 6 | Claude Fable 5.1 | 1502.6 | 53.4 | $50.00 | 71 |
| 7 | Claude Opus 4.7 | 1501.0 | 40.7 | $25.00 | – |
| 11 | Claude Opus 5 | 1491.1 | 50.8 | $25.00 | – |
Pricing
- Official API list price: $2.00 input and $10.00 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $4.00 per 1M tokens.
- Among 81 models with an output price, it is the #52 cheapest.
- The cheapest OpenRouter route charges $2.00 input / $10.00 output.
Sources & methodology
On the arena.ai Agents leaderboard, Claude Sonnet 5 has a task success rate of 4.15% (High, rank #11, 95% interval 2.46%–5.84%).
- arena.ai Agents — agent task success rate, 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 Sonnet 5 do on the Agents leaderboard?
On the arena.ai Agents leaderboard, Claude Sonnet 5 has a task success rate of 4.15% (High, rank #11, 95% interval 2.46%–5.84%).
What rank is Claude Sonnet 5 right now?
Claude Sonnet 5 is #43 on our leaderboard of 69 scored models (Arena score 1460.9); its raw LMArena rank is #58.
What does Claude Sonnet 5 cost via API?
Input $2.00 / output $10.00 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 $4.00 per 1M tokens.
How close is Claude Sonnet 5 to the models ranked next to it?
It is 3.7 points behind DeepSeek V4 Pro (1464.6) and 0.0 points ahead of Kimi K2.6 (1460.9); gaps smaller than the confidence interval (±4.1) are not significant.
Is Claude Sonnet 5 open source? Can it be self-hosted?
Claude Sonnet 5 is a closed model, available only via official APIs or hosted services.
What is the context length of Claude Sonnet 5?
1M (1,000,000 tokens, as listed on OpenRouter).
Claude Sonnet 5 vs DeepSeek V4 Pro: which is better?
On the LMArena Text leaderboard Claude Sonnet 5 scores 1460.9 and DeepSeek V4 Pro scores 1464.6 (a 3.7-point gap, within the confidence interval, so not significant). Agent task success: Claude Sonnet 5 4.15%, DeepSeek V4 Pro 0.07%. On price, Claude Sonnet 5 costs $10.00 and DeepSeek V4 Pro $3.96 per 1M output tokens.
Is there a cheaper model close to Claude Sonnet 5?
Yes: DeepSeek V4.1 Flash scores 1475.3 on the Text leaderboard (Claude Sonnet 5: 1460.9) and costs $1.20 per 1M output tokens, about 88% less than Claude Sonnet 5 ($10.00).
Where does the Claude Sonnet 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 Oct 22, 2026.