- Score
- 9.4 (+4.06 points)
- Total Cost (Current Price)
- $0.183 · 30.4% cheaper
- Response Time (avg)
- 6.24s · 82.6% faster
Moonshot AI
Release: 2026-01-27
Tested on: 2026-10-01 01:23
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 #299. It has 10.0 reliability, a 29.0% pass rate, $0.262 total cost, and 35.86s average response time.
What makes Kimi K2.5 unique: It stands out most in General Intelligence, where it ranks #1, while Anti-AI Tricks is its weakest area at #14.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 7.5 (+2.24 points)
- Total Cost (Current Price)
- $0.000 · 100.0% cheaper
- Response Time (avg)
- 29.38s · 18.1% faster
- Score
- 8.6 (+3.27 points)
- Total Cost (Current Price)
- $0.061 · 76.9% cheaper
- Response Time (avg)
- 7.51s · 79.1% faster
Model facts
Researched on 2026-08-12
- Parameters
- 1T total (32B active)
- Architecture
- MoE
- Availability
- Weights available
- License
- Modified MIT
5.3
Consistency
8.6
10.0
Total Output Tokens
49,389
Total Input Tokens
275,349
Input Price
$0.450 / 1M
Output Price
$2.250 / 1M
Cache Read Price
$0.070 / 1M
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
4
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.
#299 MoonshotAI: Kimi K2.5
none- Cost
- $0.015
- Time
- 89.1s
- Tokens
- 5,421 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 01:23 Re-test | 5.3 | 10.0 | $0.262 ↑ | Current run | |
| 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 | Compare | |
| 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.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-06-04 15:40 | $0.400 / 1M | $1.900 / 1M | N/A | N/A |
| 2026-06-17 10:07 | $0.375 / 1M | $2.025 / 1M | N/A | N/A |
| 2026-08-14 12:51 | $0.571 / 1M | $2.850 / 1M | N/A | N/A |
| 2026-10-01 18:33 | $0.450 / 1M | $2.250 / 1M | $0.070 / 1M | N/A |
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 K2.5nonevsGranite 4.2 8BlowKimi K2.5nonevsLaguna XS 2.1noneFree AvailableKimi K2.5nonevsGPT-5.6 LunanoneKimi K2.5nonevsQwen3.6 35B A3BnoneKimi K2.5nonevsEmber-1noneKimi K2.5nonevsInkling SmalllowFree AvailableKimi K2.5nonevsStep 3.5 FlashmediumKimi K2.5nonevsLing 3.0 FlashnoneKimi K2.5nonevsMiMo-V2.6-FlashnoneKimi K2.5nonevsNemotron 3.5 LightninghighFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 5.0 | 10.0 | |
| Anti-AI Tricks | 3.6 | 8.4 | |
| Coding | 5.5 | 10.0 | |
| Combined | 2.8 | 1.8 | |
| Data parsing and extraction | 7.3 | 5.8 | |
| Domain specific | 3.0 | 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 |