Balanced Claude model for coding, analysis, agent workflows, and cost control
Specification
most-agreed values
Context
200K
Max output
64K
Released
2025-02-19
Knowledge cutoff
2025-02
Retires
—
Open weights
no
Input
text, image
Output
text
Price
US dollars per million tokens · most-agreed
Input
$3.00
Output
$15.00
Cache read
$0.30
Cache write
$3.75
Quality
7 benchmarks · 3 sources
Composite
64th
percentile of 344 scored models
Rank
126 / 344
±0.05 sd
Evidence
7 × 3
3 or more benchmarks, from 2 or more sources
Effort range
12.5
points between effort settings
coding60th2/3 bench
reasoning78th1/4 bench
math49th4/7 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| 32k | 69th | 5 |
| 16k | 62nd | 4 |
| 64k | 61st | 5 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 91.2 ±0.8 | 64k | Epoch AI | 2025-03-13 |
| ↳ | 90.0 ±0.8 | 32k | Epoch AI | 2025-03-12 |
| ↳ | 86.2 ±0.9 | 16k | Epoch AI | 2025-02-26 |
| ↳ | 68.2 ±1.1 | default | Epoch AI | 2025-02-24 |
| Settings differ by 23.0 points on this benchmark. | ||||
| Aider polyglot | 64.9 | 32k · aider diff | Aider | 2025-02-24 |
| GPQA diamond | 78.5 ±2.7 | 64k | Epoch AI | 2025-05-26 |
| ↳ | 76.8 ±3.0 | 16k | Epoch AI | 2025-02-26 |
| ↳ | 76.8 ±3.0 | 32k | Epoch AI | 2025-03-10 |
| ↳ | 66.0 ±2.7 | default | Epoch AI | 2025-02-24 |
| Settings differ by 12.5 points on this benchmark. | ||||
| SWE-Bench verified | 61.0 ±2.2 | default | Epoch AI | 2026-02-04 |
| ↳ | 59.6 | default · Aime-coder v1 · 2 runs | SWE-bench | — |
| Sources and settings disagree by 1.4 points. Both figures stand. | ||||
| OTIS Mock AIME 2024-2025 | 57.8 ±7.4 | 64k | Epoch AI | 2025-03-13 |
| ↳ | 53.3 ±7.5 | 32k | Epoch AI | 2025-03-12 |
| ↳ | 46.7 ±7.5 | 16k | Epoch AI | 2025-02-26 |
| ↳ | 21.9 ±4.8 | default | Epoch AI | 2025-02-25 |
| Settings differ by 35.9 points on this benchmark. | ||||
| FrontierMath-Tier-4-2025-07-01 | 0.0 ±0.0 | 64k | Epoch AI | 2025-07-01 |
| FrontierMath-v1 | 2.1 ±1.2 | 16k · 2 runs | Epoch AI | 2025-03-06 |
| ↳ | 1.7 ±1.1 | 32k · 2 runs | Epoch AI | 2025-03-13 |
| ↳ | 1.6 ±0.0 | default · 2 runs | Epoch AI | 2025-03-06 |
| ↳ | 1.6 ±1.0 | 64k · 2 runs | Epoch AI | 2025-03-13 |
| Settings differ by 0.5 points on this benchmark. | ||||
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 12 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| abacus | $3.00 | $15.00 | — | — | 200K | 64K | — |
| bedrock · eu | $3.00 | $15.00 | $0.30 | $3.75 | 200K | 8K | — |
| bedrock_converse | $3.00 | $15.00 | $0.30 | $3.75 | 200K | 8K | — |
| bedrock_converse · us | $3.00 | $15.00 | $0.30 | $3.75 | 200K | 8K | — |
| helicone | $3.00 | $15.00 | $0.30 | $3.75 | 200K | 64K | — |
| replicate · replicate | $3.00 | $15.00 | — | — | — | — | — |
| snowflake | $3.00 | $15.00 | $0.30 | — | 200K | 16K | — |
| vercel_ai_gateway · vercel-ai-gateway | $3.00 | $15.00 | $0.30 | $3.75 | 200K | 64K | — |
| deepinfra | $3.30 | $16.50 | $0.33 | — | 200K | 200K | — |
| bedrock | $3.60 | $18.00 | $0.36 | $4.50 | 200K | 8K | — |
| heroku · heroku | — | — | — | — | 200K | 8K | — |
| qiniu-ai | — | — | — | — | 200K | 128K | — |
Other listings of this model
same model, different key
More from Anthropic
most-hosted first