#126 MoonshotAI: Kimi K2.5
none- Cost
- $0.015
- Time
- 89.1s
- Tokens
- 5,421 tok
Moonshot AI
Release: 2026-01-27
Tested on: 2026-05-22 00:03
moonshotai/kimi-k2.5::none
1T total (32B active)MoEWeights available
(medium)
(none)
Summary
Kimi K2.5 scores 5.3 on AI BENCHY and ranks #126. It has 10.0 reliability, a 36.7% pass rate, $0.026 total cost, and 14.16s average response time.
What makes Kimi K2.5 unique: It stands out most in Domain specific, where it ranks #1, while Combined is its weakest area at #18. Its total benchmark cost is unusually low for its score range.
Model facts
Researched on 2026-08-12
- Parameters
- 1T total (32B active)
- Architecture
- MoE
- Availability
- Weights available
- License
- Modified MIT
5.3
Consistency
8.9
10.0
$0.026
Total Output Tokens
6,734
Total Input Tokens
0
Input Price
$0.400 / 1M
Output Price
$1.900 / 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 01:55 Re-test | 5.4 | 10.0 | $0.127 ↑ | Compare | |
| 2026-07-16 22:13 New test added | 5.5 | 10.0 | $0.127 ↑ | Compare | |
| 2026-06-04 13:32 New test added | 5.2 | 10.0 | $0.028 ↑ | Compare | |
| 2026-05-22 00:03 Suite changed | 5.3 | 10.0 | $0.026 | Current run | |
| 2026-04-20 17:48 First recorded run | 5.5 | N/A | $0.017 | 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 00:03 · Suite changed | 60/60 attempts | 5.3 | 8.9 | 10.0 | 6/20 | 3 | 6,734 | 0 | $0.026 | 14.16s |
| 2026-06-04 13:32 · New test added | 63/63 attempts | 5.2 | 8.9 | 10.0 | 6/21 | 3 | 6,657 | 36,034 | $0.028 | 13.18s |
| Difference | — | +0.1 | 0.0 | 0.0 | 0 | 0 | +77 | -36034 | -$0.002 | +985ms |
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
Quick Compare
Kimi K2.5nonevsMiMo-V2.5-PrononeKimi K2.5nonevsDeepSeek V4 Flash 0731noneKimi K2.5nonevsGPT-5.6 LunanoneKimi K2.5nonevsLaguna S 2.1highFree AvailableKimi K2.5nonevsKAT-Coder-Air V2.5lowKimi K2.5nonevsInkling SmallnoneKimi K2.5nonevsLaguna S 2.1mediumFree AvailableKimi K2.5nonevsLaguna XS 2.1noneFree AvailableKimi K2.5nonevsDeepSeek V4 Flash 0423noneKimi K2.5nonevsSeed-2.0-Codenone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 3.6 | 8.4 | |
| Coding | 6.8 | 10.0 | |
| Combined | 2.8 | 2.1 | |
| Data parsing and extraction | 7.3 | 5.8 | |
| Domain specific | 5.3 | 10.0 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 6.5 | 10.0 | |
| Puzzle Solving | 3.0 | 10.0 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |