Kimi K2.5vsKimi K2 Thinking
Kimi K2.5 and Kimi K2 Thinking are tied across 6 shared benchmarks: Kimi K2.5 leads on 3, Kimi K2 Thinking leads on 3, with 0 ties and an average score difference of -7.35.
Kimi K2.5
Moonshot AI · 2026-01-27 · Multimodal model
Kimi K2 Thinking
Moonshot AI · 2025-11-06 · Reasoning model
Kimi K2.53 wins(50%)(50%)3 winsKimi K2 Thinking
Benchmark scores
Grouped by capability, sorted by largest gap within each. 6 shared benchmarks.
Coding and Software Engineer
Kimi K2.5 2/2| Benchmark | Kimi K2.5 | Kimi K2 Thinking | Diff |
|---|---|---|---|
| SWE-bench Verified | 76.8030 / 116Thinking (With Tools) | 71.3056 / 116Thinking (With Tools) | +5.50 |
| LiveCodeBench | 8529 / 250Thinking (No Tools) | 83.1040 / 250Thinking (No Tools) | +1.90 |
General Knowledge
Even 2/2| Benchmark | Kimi K2.5 | Kimi K2 Thinking | Diff |
|---|---|---|---|
| LiveBench | 69.0741 / 117Thinking (No Tools) | 61.5965 / 117Thinking (No Tools) | +7.48 |
| MMLU Pro | 78.5071 / 176Thinking (No Tools) | 84.6035 / 176Thinking (No Tools) | -6.10 |
Claw-style Agent Evaluation
Kimi K2 Thinking 1/1| Benchmark | Kimi K2.5 | Kimi K2 Thinking | Diff |
|---|---|---|---|
| Claw Bench | 81.7018 / 29Thinking (With Tools) | 82.5017 / 29Thinking (With Tools) | -0.80 |
Writing and Creative Capabilities
Kimi K2 Thinking 1/1| Benchmark | Kimi K2.5 | Kimi K2 Thinking | Diff |
|---|---|---|---|
| Creative Writing | 1,57643 / 106Normal (No Tools) | 1,62835 / 106Normal (No Tools) | -52.10 |
Specs
| Field | Kimi K2.5 | Kimi K2 Thinking |
|---|---|---|
| Publisher | Moonshot AI | Moonshot AI |
| Release date | 2026-01-27 | 2025-11-06 |
| Model type | Multimodal model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 1T | 1T |
| Context length | 256K | 256K |
| Max output | 16K | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Kimi K2.5 | Kimi K2 Thinking |
|---|---|---|
| Text input | $0.6 / 1M tokens | $0.6 / 1M tokens |
| Text output | $3 / 1M tokens | $2.5 / 1M tokens |
| Cache read | $0.1 / 1M tokens | $0.3 / 1M tokens |
| Cache write | Not public | $0.6 / 1M tokens |
Summary
- Kimi K2.5leads in:Coding and Software Engineer (2/2)
- Kimi K2 Thinkingleads in:Claw-style Agent Evaluation (1/1), Writing and Creative Capabilities (1/1)
- Tied in:General Knowledge
On average across the 6 shared benchmarks, Kimi K2 Thinking scores 7.35 higher.
Largest single-benchmark gap: Creative Writing — Kimi K2.5 1,576 vs Kimi K2 Thinking 1,628 (-52.10).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.