Claude 3.5 Sonnet
Claude 3.5 Sonnet is a model by Anthropic for writing code and reasoning and agentic, it stands 2nd of 217 on Mmlu — Epoch AI, and 4 sellers in the catalogue publish a price for it.
text + image + file → text + code · made by Anthropic
Sold by 6 ways
| Seller | Lane | Rate |
|---|---|---|
| AWS Bedrock cloud | standard | $3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeraw.githubusercontent.com · read 2026-10-31 |
| Amazon Web Services cloud | batch | $3per Mtok in$15per Mtok outaws.amazon.com · read 2026-08-25 |
| DigitalOcean cloud | standard | $3per Mtok in$15per Mtok out$0.3per Mtok cached$3.75per Mtok cache writeraw.githubusercontent.com · read 2026-10-31 |
| Snowflake Cortex cloud | standard | $3per Mtok in$15per Mtok out$0.3per Mtok cachedraw.githubusercontent.com · read 2026-10-31 |
| AWS Bedrock 0 ways | $6per Mtok in$30per Mtok out$0.6per Mtok cached | |
| AWS Bedrock cloudnot on the seller's list today | long-context | $6per Mtok in$30per Mtok out$0.6per Mtok cachedraw.githubusercontent.com · read 2026-10-13 |
| Amazon Web Services cloud | standard | $6per Mtok in$30per Mtok outaws.amazon.com · read 2026-08-25 |
Measured 26 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 2ndof 217 | Mmlu — Epoch AI | EM | 0.873 |
| 7thof 15 | Cad eval — Epoch AI | Overall pass (%) | 0.48 |
| 7thof 16 | The agent company — Epoch AI | % Score | 0.344 |
| 14thof 22 | Cybench — Epoch AI | Unguided % Solved | 0.175 |
| 18thof 41 | Balrog — Epoch AI | Average progress | 0.326 |
| 20thof 69 | Aider polyglot coding leaderboard | Percent correct | 64 |
| 20thof 54 | Live bench — Epoch AI | Global average | 59.03 |
| 21stof 49 | Lech mazur writing — Epoch AI | Mean score | 8.03 |
| 29thof 50 | Video mme — Epoch AI | Overall (no subtitles) | 0.6 |
| 33rdof 42 | Gso — Epoch AI | Score OPT@1 | 0.046 |
| 33rdof 49 | Metr time horizons — Epoch AI | average_score | 0.452 |
| 33rdof 38 | Vpct — Epoch AI | Correct | 0.33 |
| 39thof 72 | Aider polyglot — Epoch AI | Percent correct | 51.6 |
| 39thof 46 | Enigma eval — Epoch AI | Accuracy | 0.91 |
| 48thof 92 | Forecastbench — Epoch AI | Overall score | 63.2 |
| 54thof 56 | Humanity's Last Exam (Epoch AI replication) | Accuracy | 4.08 |
| 55thof 108 | Math level 5 — Epoch AI | mean_score | 56.949 |
| 69thof 72 | Frontiermath tier 4 — Epoch AI | mean_score | 0 |
| 69thof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.414 |
| 84thof 101 | FrontierMath (Tiers 1-3) | mean_score | 2.069 |
| 110thof 165 | LMArena · Vision | Score (Elo) | 1160 |
| 113thof 173 | Weirdml — Epoch AI | Accuracy | 39.97 |
| 166thof 235 | Dtbench — Epoch AI | Accuracy | 67.84 |
| 192ndof 414 | LMArena · Text | Score (Elo) | 1374 |
| 231stof 326 | GPQA Diamond | mean_score | 55.303 |
| 255thof 306 | OTIS Mock AIME 2024-2025 | mean_score | 8.472 |
About
Claude 3.5 Sonnet — a text and code model from Anthropic, sold by 4 companies from $3 in and $15 out per million tokens, placed 2nd of 217 on Mmlu — Epoch AI.
It takes text, images and files and returns text and code, with a context window of 200,000 tokens. It was published in June 2024, trained on material up to April 2024. Its sellers say it can call a tool. The catalogue files it under code, reasoning and agents. Four companies sell it. The cheapest is $3 in and $15 out per million tokens at AWS Bedrock. Beside the standard rate there is a batch lane. It has been measured on 26 boards, and stands best at 2nd of 217 on Mmlu — Epoch AI.
Every current figure
- Maker
- Anthropic
- Register
- model
- Takes
- text + image + file
- Returns
- text + code
- Context
- 200,000 tokens
- Longest answer
- 8,200 tokens
- Published
- June 2024
- Knowledge to
- April 2024
- Licence
- not read
- Sellers
- 4
- Maker's own price
- not read
- Price
- $3 in and $15 out per million tokens — AWS Bedrock
- Boards
- 26
- Best place
- 2nd of 217 — Mmlu — Epoch AI
Known as 3 names
DeepSeek R1 + claude-3-5-sonnet-20241022Claude-3.5-Sonnet-20241022Claude Sonnet 3.5