#143 Mercury 2
none- Cost
- $0.002
- Time
- 1.8s
- Tokens
- 1,514 tok
Inception
Release: 2026-02-24
Tested on: 2026-05-22 00:39
inception/mercury-2::none
~100BOtherClosedEstimated
(medium)
(none)
Summary
Mercury 2 scores 4.6 on AI BENCHY and ranks #143. It has 10.0 reliability, a 25.0% pass rate, $0.009 total cost, and 614ms average response time.
What makes Mercury 2 unique: It stands out most in Domain specific, where it ranks #4, while Anti-AI Tricks is its weakest area at #18. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Model facts
Researched on 2026-08-12
- Parameters
- ~100B
- Architecture
- Other
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Diffusion transformer; parameter topology and count are undisclosed.
4.6
Consistency
9.1
10.0
$0.009
Total Output Tokens
2,984
Total Input Tokens
0
Input Price
$0.250 / 1M
Output Price
$0.750 / 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 03:05 Re-test | 4.7 | 10.0 | $0.030 | Compare | |
| 2026-07-16 23:13 New test added | 4.6 | 10.0 | $0.030 | Compare | |
| 2026-06-04 14:27 New test added | 4.5 | 10.0 | $0.011 | Compare | |
| 2026-05-22 00:39 Suite changed | 4.6 | 10.0 | $0.009 | Current run | |
| 2026-04-11 01:44 First recorded run | 4.8 | N/A | $0.007 | 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 00:39 · Suite changed | 60/60 attempts | 4.6 | 9.1 | 10.0 | 4/20 | 2 | 2,984 | 0 | $0.009 | 614ms |
| 2026-08-14 03:05 · Re-test | 66/66 attempts | 4.7 | 9.2 | 10.0 | 4/22 | 2 | 9,584 | 89,637 | $0.030 | 825ms |
| Difference | — | -0.1 | -0.1 | 0.0 | 0 | 0 | -6600 | -89637 | -$0.021 | -211ms |
Benchmark coverage differs: 60/60 attempts (Target: 3 repeats per test) versus 66/66 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
Quick Compare
Mercury 2nonevsCobuddymediumFree AvailableMercury 2nonevsMiniMax M2.5mediumMercury 2nonevsGranite 4.2 8BnoneMercury 2nonevsGLM 4.7 FlashmediumMercury 2nonevsTrinity Large PreviewdefaultFree AvailableMercury 2nonevsgpt-oss-120bnoneMercury 2nonevsKAT Coder AIR V2.5defaultMercury 2nonevsMercury 2.5noneMercury 2nonevsNemotron 3 SupernoneFree AvailableMercury 2nonevsQwen3.5-9Bmedium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.0 | 10.0 | |
| Coding | 3.5 | 9.4 | |
| Combined | 3.0 | 10.0 | |
| Data parsing and extraction | 7.3 | 5.9 | |
| Domain specific | 5.3 | 7.2 | |
| General Intelligence | 4.8 | 10.0 | |
| Instructions following | 6.5 | 10.0 | |
| Puzzle Solving | 3.1 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |