Moonshot AI · 2026-01-27 · Multimodal model
Grouped by capability, sorted by largest gap within each. 11 shared benchmarks.
| Benchmark | Kimi K2.6 | Kimi K2.5 | Diff |
|---|---|---|---|
| SWE-Bench Pro - Public | 58.603 / 36Thinking (With Tools) | 50.7025 / 36Thinking (With Tools) | +7.90 |
| LiveCodeBench | 89.606 / 118Thinking (No Tools) | 8514 / 118Thinking (No Tools) | +4.60 |
| SWE-bench Multilingual | 76.702 / 17Thinking (With Tools) | 738 / 17Thinking (No Tools) | +3.70 |
| SWE-bench Verified | 80.209 / 103Thinking (With Tools) | 76.8022 / 103Thinking (With Tools) | +3.40 |
| Benchmark | Kimi K2.6 | Kimi K2.5 | Diff |
|---|---|---|---|
| HLE | 547 / 149Thinking (With Tools + Internet) | 50.2017 / 149Thinking (With Tools) | +3.80 |
| GPQA Diamond | 90.5014 / 175Thinking (No Tools) | 87.6031 / 175Thinking (No Tools) | +2.90 |
| Benchmark | Kimi K2.6 | Kimi K2.5 | Diff |
|---|---|---|---|
| IMO-AnswerBench | 865 / 17Thinking (No Tools) | 81.8012 / 17Thinking (No Tools) | +4.20 |
| AIME 2026 | 96.401 / 14Thinking (No Tools) | 92.5010 / 14Thinking (No Tools) | +3.90 |
| Benchmark | Kimi K2.6 | Kimi K2.5 | Diff |
|---|---|---|---|
| BrowseComp | 83.208 / 43Thinking (With Tools + Internet) | 60.6027 / 43Thinking (With Tools + Internet) | +22.60 |
| Benchmark | Kimi K2.6 | Kimi K2.5 | Diff |
|---|---|---|---|
| Terminal Bench 2.0 | 66.708 / 43Thinking (With Tools) | 50.8030 / 43Thinking (With Tools) | +15.90 |
| Benchmark | Kimi K2.6 | Kimi K2.5 | Diff |
|---|---|---|---|
| Claw Bench | 80.9019 / 29Thinking (With Tools) | 81.7018 / 29Thinking (With Tools) | -0.80 |
| Field | Kimi K2.6 | Kimi K2.5 |
|---|---|---|
| Publisher | Moonshot AI | Moonshot AI |
| Release date | 2026-04-20 | 2026-01-27 |
| Model type | Reasoning model | Multimodal model |
| Architecture | MoE | MoE |
| Parameters | 10000.0 | 10000.0 |
| Context length | 256K | 256K |
| Max output | Not available | 16384 |
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Kimi K2.6 | Kimi K2.5 |
|---|---|---|
| Text input | $0.95 / 1M tokens | 0.6 美元/100 万tokens |
| Text output | $4 / 1M tokens | 3 美元/100 万tokens |
| Cache read | $0.16 / 1M tokens | 0.1 美元/100 万tokens |
| Cache write | $0.95 / 1M tokens | Not public |
On average across the 11 shared benchmarks, Kimi K2.6 scores 6.55 higher.
Largest single-benchmark gap: BrowseComp — Kimi K2.6 83.20 vs Kimi K2.5 60.60 (+22.60).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.
