Specification
most-agreed values
Context
200K
Max output
4K
Released
—
Knowledge cutoff
—
Retires
2025-08-01
Open weights
—
Input
—
Output
—
Price
US dollars per million tokens · most-agreed
Input
$15.00
Output
$75.00
Cache read
$1.50
Cache write
$18.75
Quality
6 benchmarks · 2 sources
Composite
13th
percentile of 344 scored models
Rank
301 / 344
±0.05 sd
Evidence
6 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
coding2nd1/3 bench
reasoning19th2/4 bench
math16th2/7 bench
knowledge6th1/1 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| MATH level 5 | 37.5 ±1.1 | default | Epoch AI | 2025-01-27 |
| GPQA diamond | 47.2 ±2.6 | default | Epoch AI | 2025-01-27 |
| Chess Puzzles | 3.0 ±1.7 | default | Epoch AI | 2026-10-13 |
| OTIS Mock AIME 2024-2025 | 4.7 ±2.0 | default | Epoch AI | 2025-02-25 |
| SimpleQA Verified | 12.6 ±1.1 | default | Epoch AI | 2026-08-31 |
| SWE-Bench verified | 11.4 | default · RAG baseline · 2 runs | SWE-bench | — |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 5 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| bedrock | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 4K | — |
| bedrock · eu | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 4K | — |
| bedrock · us | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 4K | — |
| vercel_ai_gateway · vercel-ai-gateway | $15.00 | $75.00 | $1.50 | $18.75 | 200K | 4K | — |
| vertex_ai-anthropic_models | $15.00 | $75.00 | — | — | 200K | 4K | 2025-08-01 |
More from Anthropic
most-hosted first