MiniMax M2.5vsKimi K2.5
MiniMax M2.5 and Kimi K2.5 are tied across 14 shared benchmarks: MiniMax M2.5 leads on 7, Kimi K2.5 leads on 7, with 0 ties and an average score difference of -1.56.
MiniMax M2.5
MiniMaxAI · 2026-02-12 · Reasoning model
Kimi K2.5
Moonshot AI · 2026-01-27 · Multimodal model
MiniMax M2.57 wins(50%)(50%)7 winsKimi K2.5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 14 shared benchmarks.
General Knowledge
Kimi K2.5 5/5| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| HLE | 19.40121 / 172Thinking (No Tools) | 50.2027 / 172Thinking (With Tools) | -30.80 |
| LiveBench | 60.1468 / 115Deep Thinking (No Tools) | 69.0742 / 115Thinking (No Tools) | -8.93 |
| ARC-AGI-2 | 4.9047 / 62Thinking (No Tools) | 11.8039 / 62Thinking (No Tools) | -6.90 |
| GPQA Diamond | 85.2053 / 187Thinking (No Tools) | 87.6037 / 187Thinking (No Tools) | -2.40 |
| ARC-AGI | 63.7035 / 68Thinking (No Tools) | 65.3034 / 68Thinking (No Tools) | -1.60 |
Claw-style Agent Evaluation
MiniMax M2.5 2/2| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| Claw Bench | 92.104 / 29Thinking (With Tools) | 81.7018 / 29Thinking (With Tools) | +10.40 |
| Pinch Bench | 87.806 / 37Thinking (With Tools) | 84.8017 / 37Thinking (With Tools) | +3 |
Coding and Software Engineer
MiniMax M2.5 2/2| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 55.4026 / 54 | 50.7041 / 54Thinking (With Tools) | +4.70 |
| SWE-bench Verified | 80.2014 / 112 | 76.8030 / 112Thinking (With Tools) | +3.40 |
AI Agent - Information Search
MiniMax M2.5 1/1| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| BrowseComp | 76.3023 / 53 | 60.6036 / 53Thinking (With Tools + Internet) | +15.70 |
AI Agent - Tool Usage
MiniMax M2.5 1/1| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 51.7031 / 47 | 50.8034 / 47Thinking (With Tools) | +0.90 |
Long Context
MiniMax M2.5 1/1| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| AA-LCR | 69.505 / 15Thinking (No Tools) | 6512 / 15Thinking (No Tools) | +4.50 |
Math and Reasoning
Kimi K2.5 1/1| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| AIME2025 | 86.3049 / 107Thinking (No Tools) | 96.1021 / 107Thinking (No Tools) | -9.80 |
Productivity Knowledge
Kimi K2.5 1/1| Benchmark | MiniMax M2.5 | Kimi K2.5 | Diff |
|---|---|---|---|
| GDPval-AA | 3617 / 21Thinking (No Tools) | 4015 / 21Thinking (No Tools) | -4 |
Specs
| Field | MiniMax M2.5 | Kimi K2.5 |
|---|---|---|
| Publisher | MiniMaxAI | Moonshot AI |
| Release date | 2026-02-12 | 2026-01-27 |
| Model type | Reasoning model | Multimodal model |
| Architecture | MoE | MoE |
| Parameters | 229B | 1T |
| Context length | 128K | 256K |
| Max output | Not available | 16K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | MiniMax M2.5 | Kimi K2.5 |
|---|---|---|
| Text input | $0.3 / 1M tokens | $0.6 / 1M tokens |
| Text output | $2.4 / 1M tokens | $3 / 1M tokens |
| Cache read | Not public | $0.1 / 1M tokens |
Summary
- MiniMax M2.5leads in:Claw-style Agent Evaluation (2/2), Coding and Software Engineer (2/2), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Long Context (1/1)
- Kimi K2.5leads in:General Knowledge (5/5), Math and Reasoning (1/1), Productivity Knowledge (1/1)
On average across the 14 shared benchmarks, Kimi K2.5 scores 1.56 higher.
Largest single-benchmark gap: HLE — MiniMax M2.5 19.40 vs Kimi K2.5 50.20 (-30.80).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.