#215 KAT-Coder-Air V2.5
medium- Cost
- $0.003
- Time
- 23.7s
- Tokens
- 4,924 tok
Kwaipilot
Release: 2026-07-14
Tested on: 2026-08-14 03:26
kwaipilot/kat-coder-air-v2.5::medium
~35B total (~3B active)MoEClosedEstimated
Summary
KAT-Coder-Air V2.5 scores 5.6 on AI BENCHY and ranks #215. It has 9.6 reliability, a 45.5% pass rate, $0.048 total cost, and 8.65s average response time.
What makes KAT-Coder-Air V2.5 unique: It stands out most in Anti-AI Tricks, where it ranks #1, while Coding is its weakest area at #9.
Model facts
Researched on 2026-08-12
- Parameters
- ~35B total (~3B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. Weights were announced but were not available for the exact checkpoint at research time.
5.6
Consistency
8.9
9.6
$0.048
Total Output Tokens
66,576
Total Input Tokens
51,369
Input Price
$0.150 / 1M
Output Price
$0.600 / 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 03:26 Re-test | 5.6 | 9.6 | $0.048 | Current run | |
| 2026-07-16 23:34 New test added | 5.6 | 9.9 | $0.048 | Compare | |
| 2026-07-14 11:05 Initial run | 6.2 | 9.7 | $0.045 | 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 03:26 · Current run | 66/66 attempts | 5.6 | 8.9 | 9.6 | 8/22 | 3 | 66,576 | 51,369 | $0.048 | 8.65s |
| 2026-07-16 23:34 · New test added | 66/66 attempts | 5.6 | 8.9 | 9.9 | 8/22 | 3 | 66,174 | 51,472 | $0.048 | 8.42s |
| Difference | — | 0.0 | 0.0 | -0.3 | 0 | 0 | +402 | -103 | +$0.001 | +232ms |
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 | $0.150 / 1M | $0.600 / 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
KAT-Coder-Air V2.5mediumvsGemma 4 26B A4BnoneFree AvailableKAT-Coder-Air V2.5mediumvsNemotron 3.5 LightninghighFree AvailableKAT-Coder-Air V2.5mediumvsKAT-Coder-Air V2.5highKAT-Coder-Air V2.5mediumvsQwen3.6 27BnoneKAT-Coder-Air V2.5mediumvsQwen3.5-122B-A10BnoneKAT-Coder-Air V2.5mediumvsQwen3.8 27BnoneKAT-Coder-Air V2.5mediumvsKimi K2.6noneKAT-Coder-Air V2.5mediumvsDeepSeek V4 Flash 0423noneKAT-Coder-Air V2.5mediumvsGLM 5.1noneKAT-Coder-Air V2.5mediumvsLaguna S 2.1mediumFree Available
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.7 | 8.0 | |
| Coding | 3.6 | 7.0 | |
| Combined | 6.5 | 10.0 | |
| Data parsing and extraction | 6.5 | 10.0 | |
| Domain specific | 3.0 | 10.0 | |
| General Intelligence | 5.0 | 10.0 | |
| Instructions following | 10.0 | 10.0 | |
| Puzzle Solving | 3.6 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |