#46 Claude Sonnet 5
medium- Cost
- $0.007
- Time
- 6.4s
- Tokens
- 832 tok
Anthropic
Release: 2026-06-30
Tested on: 2026-08-14 02:11
anthropic/claude-sonnet-5::medium
~1T total (~100B active)MoEClosedEstimated
(medium)
(none)
Summary
Claude Sonnet 5 scores 8.2 on AI BENCHY and ranks #46. It has 10.0 reliability, a 75.8% pass rate, $0.922 total cost, and 12.54s average response time.
What makes Claude Sonnet 5 unique: It stands out most in Instructions following, where it ranks #3, while Combined is its weakest area at #13.
Model facts
Researched on 2026-08-12
- Parameters
- ~1T total (~100B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose parameter counts.
8.2
Consistency
9.0
10.0
$0.922
Total Output Tokens
63,204
Total Input Tokens
145,953
Input Price
$2.000 / 1M
Output Price
$10.000 / 1M
Flaky tests
3
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:11 Re-test | 8.2 | 10.0 | $0.922 | Current run | |
| 2026-07-16 22:33 New test added | 8.3 | 10.0 | $0.922 | Compare | |
| 2026-06-30 21:33 Initial run | 7.9 | 10.0 | $0.550 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-08-14 02:11 · Current run | 66/66 attempts | 8.2 | 9.0 | 10.0 | 15/22 | 3 | 63,204 | 145,953 | $0.922 | 12.54s |
| 2026-06-30 21:33 · Initial run | 63/63 attempts | 7.9 | 9.0 | 10.0 | 15/21 | 3 | 41,685 | 67,416 | $0.550 | 9.94s |
| Difference | — | +0.3 | 0.0 | 0.0 | 0 | 0 | +21519 | +78537 | +$0.373 | +2603ms |
Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 63/63 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.
These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price |
|---|---|---|
| 2026-08-14 12:51 | $2.000 / 1M | $10.000 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Claude Sonnet 5mediumvsGemini 2.5 FlashmediumClaude Sonnet 5mediumvsQwen3.8 2.4T A95BlowClaude Sonnet 5mediumvsMuse Spark 1.1lowClaude Sonnet 5mediumvsGPT-5 MinimediumClaude Sonnet 5mediumvsInkling SmallhighClaude Sonnet 5mediumvsMuse Glimmer 30BxhighClaude Sonnet 5mediumvsSeed 2.1 TurbomediumClaude Sonnet 5mediumvsInklinghighClaude Sonnet 5mediumvsGPT-5.2mediumClaude Sonnet 5mediumvsMuse Spark 1.1high
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 10.0 | 10.0 | |
| Coding | 9.0 | 7.9 | |
| Combined | 7.3 | 6.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 4.8 | 3.2 | |
| Instructions following | 9.9 | 10.0 | |
| Puzzle Solving | 7.7 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |