#47 Claude Sonnet 4.6
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
Anthropic
Release: 2026-02-17
Tested on: 2026-05-22 00:14
anthropic/claude-sonnet-4.6::medium
~1T total (~100B active)MoEClosedEstimated
(medium)
(none)
Summary
Claude Sonnet 4.6 scores 7.6 on AI BENCHY and ranks #47. It has 10.0 reliability, a 68.3% pass rate, $1.330 total cost, and 15.72s average response time.
Archived model: this model is no longer updated or tested on new tests.
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.
7.6
Consistency
9.2
10.0
$1.330
Total Output Tokens
79,442
Total Input Tokens
0
Input Price
$3.000 / 1M
Output Price
$15.000 / 1M
Cache Read Price
N/A
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
2
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 02:03 Re-test | 7.8 | 10.0 | $2.126 | Compare | |
| 2026-07-16 22:27 New test added | 7.8 | 10.0 | $2.057 | Compare | |
| 2026-06-04 13:42 New test added | 7.4 | 10.0 | $1.418 | Compare | |
| 2026-05-22 00:14 Suite changed | 7.6 | 10.0 | $1.330 | Current run | |
| 2026-04-11 01:44 First recorded run | 8.0 | N/A | $1.161 | 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) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-05-22 00:14 · Suite changed | 60/60 attempts | 7.6 | 9.2 | 10.0 | 13/20 | 2 | 79,442 | 0 | $1.330 | 15.72s |
| 2026-06-04 13:42 · New test added | 63/63 attempts | 7.4 | 9.1 | 10.0 | 13/21 | 2 | 84,673 | 49,112 | $1.418 | 17.06s |
| Difference | — | +0.2 | +0.1 | 0.0 | 0 | 0 | -5231 | -49112 | -$0.088 | -1340ms |
Benchmark coverage differs: 60/60 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.
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
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 6.5 | 10.0 | |
| Coding | 6.9 | 6.0 | |
| Combined | 10.0 | 10.0 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 10.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |