Anthropic

Claude Sonnet 5

Tool callingStructured outputReasoningImage inputFile input
Claude Sonnet 5 launch post cover

Everyday Claude agent model for coding, planning, browsing, and general work

Context
1M
Released
3mo ago
Input / 1M tokens
$2.00
Output / 1M tokens
$10.00
Cached input / 1M tokens
$0.20
Cache write / 1M tokens
$2.50

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

DeepSWE 1.1

Primary coding-agent benchmark · 113 tasks · Data generated 2026-09-22

Official leaderboard
53.8%
pass@1 · highest published configuration
mini-swe-agent · max reasoning
pass@4
78.8%
Average cost / attempt
$26.40
Benchmark runs
4

All published configurations

Harness / reasoningpass@1pass@4Cost / attempt
mini-swe-agent · max53.8%78.8%$26.40
mini-swe-agent · xhigh49.7%75.2%$11.89
mini-swe-agent · high48.2%79.6%$7.43
mini-swe-agent · medium39.8%64.6%$4.08
mini-swe-agent · low30.5%57.5%$2.19

pass@1 is the success rate across scored attempts; pass@4 is the share of tasks solved in at least one of four attempts. Costs are reported by DeepSWE for each configuration. These results are not directly comparable to evaluations using different harnesses. Official source JSON.

Other published benchmarks

EvaluationReported score and source
FrontierMath-Tier-4-v2-Private
29.3%
Epoch AI · claude-sonnet-5_max
Reasoning effort: max
Epoch AI evaluation
FrontierMath-Tiers-1-3-v2-Private
65.6%
Epoch AI · claude-sonnet-5_max
Reasoning effort: max
Epoch AI evaluation
GPQA diamond
80.3%
Epoch AI · claude-sonnet-5_max
Reasoning effort: max
Epoch AI evaluation
GPQA diamond
90.5%
Epoch AI · claude-sonnet-5_xhigh
Reasoning effort: xhigh
Epoch AI evaluation
OTIS Mock AIME 2024-2025
80.0%
Epoch AI · claude-sonnet-5_max
Reasoning effort: max
Epoch AI evaluation
OTIS Mock AIME 2024-2025
94.7%
Epoch AI · claude-sonnet-5_xhigh
Reasoning effort: xhigh
Epoch AI evaluation
SimpleQA Verified
33.7%
Epoch AI · claude-sonnet-5_max
Reasoning effort: max
Epoch AI evaluation
SimpleQA Verified
32.9%
Epoch AI · claude-sonnet-5_xhigh
Reasoning effort: xhigh
Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer
Anthropic
Model family
Claude
Type
Language model
Predecessor
—
Successor
—
Released
June 30, 2026
Model ID
anthropic/claude-sonnet-5
Openness
Closed
License
—
Input modalities
text, image, file
Output modalities
text
Modality
text+image+file->text
Tokenizer
Claude
Max output tokens
128K
Knowledge cutoff
2026-01-31
Hugging Face
—
Source freshness
Metadata synced Oct 8, 2026, 10:17 PM UTC
Additional source evidence
Source model
anthropic/claude-sonnet-5
Source family
claude-sonnet
Last updated
2026-06-30
Knowledge cutoff
2026-01-31
Model context
1M
Model output limit
128K
Open weights
No
File attachments
Yes
Reasoning
Yes
Tool calling
Yes
Temperature control
No

Published benchmarks

BenchmarkScoreEvaluation detailsEvidence
SWE-Bench Verified85.2 · resolved2026-06-30Source
SWE-Bench Pro63.2 · resolve rate2026-06-30Source
SWE-Bench Multilingual78.3 · resolve rate2026-06-30Source
Terminal-Bench80.4 · success rateTerminus-2 · 2.1 · 2026-06-30Source
OSWorld-Verified81.2 · success rate2026-06-30Source
BrowseComp84.7 · accuracysingle agent · 2026-06-30Source
FrontierCode38.8 · pass ratev1 · 2026-06-30Source
Complete source record (JSON)
{
  "id": "anthropic/claude-sonnet-5",
  "name": "Claude Sonnet 5",
  "description": "Everyday Claude agent model for coding, planning, browsing, and general work",
  "family": "claude-sonnet",
  "last_updated": "2026-06-30",
  "knowledge": "2026-01-31",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "temperature": false,
  "modalities": {
    "input": [
      "text",
      "image",
      "pdf"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 1000000,
    "output": 128000
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Verified",
      "score": 85.2,
      "source": "https://www.anthropic.com/news/claude-sonnet-5",
      "metric": "resolved",
      "date": "2026-06-30"
    },
    {
      "name": "SWE-Bench Pro",
      "score": 63.2,
      "source": "https://www.anthropic.com/news/claude-sonnet-5",
      "metric": "resolve rate",
      "date": "2026-06-30"
    },
    {
      "name": "SWE-Bench Multilingual",
      "score": 78.3,
      "source": "https://www.anthropic.com/news/claude-sonnet-5",
      "metric": "resolve rate",
      "date": "2026-06-30"
    },
    {
      "name": "Terminal-Bench",
      "score": 80.4,
      "source": "https://www.anthropic.com/news/claude-sonnet-5",
      "metric": "success rate",
      "harness": "Terminus-2",
      "version": "2.1",
      "date": "2026-06-30"
    },
    {
      "name": "OSWorld-Verified",
      "score": 81.2,
      "source": "https://www.anthropic.com/news/claude-sonnet-5",
      "metric": "success rate",
      "date": "2026-06-30"
    },
    {
      "name": "BrowseComp",
      "score": 84.7,
      "source": "https://www.anthropic.com/news/claude-sonnet-5",
      "metric": "accuracy",
      "variant": "single agent",
      "date": "2026-06-30"
    },
    {
      "name": "FrontierCode",
      "score": 38.8,
      "source": "https://www.anthropic.com/news/claude-sonnet-5",
      "metric": "pass rate",
      "version": "v1",
      "date": "2026-06-30"
    }
  ],
  "release_date": "2026-06-30",
  "open_weights": false
}

Infrastructure

Provider availability

All providers
ProviderEndpointContextInput /M tokensOutput /M tokensCached input /M tokensCache write /M tokensUptime 1dData handling
Amazon Bedrockamazon-bedrock/global1M$2.00$10.00$0.20$2.50100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Amazon Bedrockamazon-bedrock/globalBatch pricing1M$2.00$10.00$0.20$2.50100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Anthropicanthropic1M$2.00$10.00$0.20$2.50100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

AnthropicanthropicBatch pricing1M$2.00$10.00$0.20$2.50100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Azureazure/global1M$2.00$10.00$0.20$2.5093.28%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Azureazure/globalBatch pricing1M$2.00$10.00$0.20$2.5097.24%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Claude Platform on AWSclaude-on-aws1M$2.00$10.00$0.20$2.50100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Claude Platform on AWSclaude-on-awsBatch pricing1M$2.00$10.00$0.20$2.50100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Googlegoogle-vertex/global1M$2.00$10.00$0.20$2.50100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Googlegoogle-vertex/globalBatch pricing1M$2.00$10.00$0.20$2.50100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Amazon Bedrockamazon-bedrock/eu-west-11M$2.20$11.00$0.22$2.75100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Amazon Bedrockamazon-bedrock/us-east-11M$2.20$11.00$0.22$2.75100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Amazon Bedrockamazon-bedrock/eu-west-1Batch pricing1M$2.20$11.00$0.22$2.75100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Amazon Bedrockamazon-bedrock/us-east-1Batch pricing1M$2.20$11.00$0.22$2.75100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Azureazure/us1M$2.20$11.00$0.22$2.75—
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Azureazure/usBatch pricing1M$2.20$11.00$0.22$2.75—
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Googlegoogle-vertex/us1M$2.20$11.00$0.22$2.75100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Googlegoogle-vertex/europe1M$2.20$11.00$0.22$2.75100.00%
ZDR: Yes

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Googlegoogle-vertex/usBatch pricing1M$2.20$11.00$0.22$2.75100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Googlegoogle-vertex/europeBatch pricing1M$2.20$11.00$0.22$2.75100.00%
ZDR: No

Training: Unknown

Prompt logging: Unknown

Retention: Unknown

Checked 2026-10-15

Provider data:OpenRouter

Text provenance

Transitioning

Claude text watermarking

Anthropic says Claude models launched before August 2, 2026 have a transition period and are being moved to the same watermarking system over time.

Official explanation