- Score
- 9.4 (+5.08 points)
- Total Cost (Current Price)
- $0.183 · 58.5% cheaper
- Response Time (avg)
- 6.24s · 93.9% faster
Minimax
Release: 2026-02-12
Tested on: 2026-10-01 00:38
minimax/minimax-m2.5::medium
230B total (10B active)MoEWeights available Summary
MiniMax M2.5 scores 4.3 on AI BENCHY and ranks #348. It has 9.3 reliability, a 42.0% pass rate, $0.440 total cost, and 102.32s average response time.
What makes MiniMax M2.5 unique: It stands out most in Anti-AI Tricks, where it ranks #2, while Domain specific is its weakest area at #10.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 9.6 (+5.27 points)
- Total Cost (Current Price)
- $0.460 · 4.5% costlier
- Response Time (avg)
- 7.15s · 93.0% faster
- Score
- 8.3 (+3.97 points)
- Total Cost (Current Price)
- $0.000 · 100.0% cheaper
- Response Time (avg)
- 88.74s · 13.3% faster
Model facts
Researched on 2026-08-12
- Parameters
- 230B total (10B active)
- Architecture
- MoE
- Availability
- Weights available
- License
- MiniMax modified MIT
4.3
Consistency
6.8
9.3
Total Output Tokens
290,496
Total Input Tokens
188,239
Input Price
$0.270 / 1M
Output Price
$1.080 / 1M
Cache Read Price
$0.027 / 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
9
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.
#348 MiniMax M2.5
medium
Reached the allocated time limit (300 seconds) without receiving showcase output.
- Cost
- $0.000
- Time
- 300.0s
- Tokens
- 0 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 00:38 Re-test | 4.3 | 9.3 | $0.440 ↑ | Current run | |
| 2026-07-16 21:18 New test added | 4.6 | 10.0 | $0.340 ↓ | Compare | |
| 2026-06-04 13:23 New test added | 5.3 | 8.9 | $0.385 ↓ | Compare | |
| 2026-05-21 23:48 Suite changed | 5.4 | 8.3 | $0.305 | Compare | |
| 2026-04-20 17:48 First recorded run | 5.7 | N/A | $0.250 | 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 | $0.150 / 1M | $1.150 / 1M | N/A | N/A |
| 2026-06-10 13:42 | $0.150 / 1M | $0.900 / 1M | N/A | N/A |
| 2026-06-29 01:00 | $0.120 / 1M | $0.480 / 1M | N/A | N/A |
| 2026-08-14 12:51 | $0.220 / 1M | $0.900 / 1M | N/A | N/A |
| 2026-10-01 18:33 | $0.270 / 1M | $1.080 / 1M | $0.027 / 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
MiniMax M2.5mediumvsMercury 2noneMiniMax M2.5mediumvsGLM 4.7 FlashmediumMiniMax M2.5mediumvsCobuddymediumFree AvailableMiniMax M2.5mediumvsgpt-oss-120bnoneMiniMax M2.5mediumvsGranite 4.2 8BnoneMiniMax M2.5mediumvsMercury 2.5noneMiniMax M2.5mediumvsTrinity Large PreviewnoneFree AvailableMiniMax M2.5mediumvsQwen3.5-9BmediumMiniMax M2.5mediumvsKAT Coder AIR V2.5noneMiniMax M2.5mediumvsLing 3.0 Tinynone
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 3.0 | 10.0 | |
| Anti-AI Tricks | 7.9 | 6.3 | |
| Coding | 3.4 | 9.1 | |
| Combined | 3.7 | 1.8 | |
| Data parsing and extraction | 4.6 | 1.7 | |
| Domain specific | 2.9 | 7.2 | |
| General Intelligence | 3.8 | 2.5 | |
| Instructions following | 7.5 | 10.0 | |
| Puzzle Solving | 5.3 | 7.2 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |