Kimi K3vsKimi K2.6
Across 12 shared benchmarks, Kimi K3 leads overall: Kimi K3 wins 12, Kimi K2.6 wins 0, with 0 ties and an average score difference of +44.55.
Kimi K3
Moonshot AI · 2026-07-16 · Reasoning model
Kimi K2.6
Moonshot AI · 2026-04-20 · Reasoning model
Kimi K312 wins(100%)(0%)0 winsKimi K2.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 12 shared benchmarks.
AI Agent - Tool Usage
Kimi K3 4/4| Benchmark | Kimi K3 | Kimi K2.6 | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 88.304 / 49Max (With Tools) | 53.5648 / 49Thinking (No Tools) | +34.74 |
| MCPMark-Verified | 94.501 / 3Max (With Tools) | 72.803 / 3Thinking (With Tools) | +21.70 |
| MCP-Atlas | 84.204 / 41Max (With Tools) | 69.4030 / 41Thinking (With Tools) | +14.80 |
| OSWorld-Verified | 84.802 / 26Max (With Tools) | 73.1015 / 26Thinking (With Tools) | +11.70 |
Coding and Software Engineer
Kimi K3 3/3| Benchmark | Kimi K3 | Kimi K2.6 | Diff |
|---|---|---|---|
| Program Bench | 77.801 / 7Max (With Tools) | 48.304 / 7Thinking (With Tools) | +29.50 |
| Kimi Code Bench 2.0 | 72.901 / 3Max (With Tools) | 50.903 / 3Thinking (With Tools) | +22 |
| MLS Bench | 48.302 / 5Max (With Tools) | 26.705 / 5Thinking (With Tools) | +21.60 |
AI Agent - Information Search
Kimi K3 1/1| Benchmark | Kimi K3 | Kimi K2.6 | Diff |
|---|---|---|---|
| BrowseComp | 91.201 / 55Max (With Tools + Internet) | 83.2014 / 55Thinking (With Tools + Internet) | +8 |
General Evaluation
Kimi K3 1/1| Benchmark | Kimi K3 | Kimi K2.6 | Diff |
|---|---|---|---|
| GPQA Diamond | 93.5015 / 270最高（无工具） | 90.5041 / 270Thinking (No Tools) | +3 |
General Knowledge
Kimi K3 1/1| Benchmark | Kimi K3 | Kimi K2.6 | Diff |
|---|---|---|---|
| HLE | 5616 / 189Max (With Tools) | 5421 / 189Thinking (With Tools + Internet) | +2 |
Text Embedding
Kimi K3 1/1| Benchmark | Kimi K3 | Kimi K2.6 | Diff |
|---|---|---|---|
| Context Arena | 71.7559 / 126最高（无工具） | 51.8886 / 126Normal (No Tools) | +19.87 |
Writing and Creative Capabilities
Kimi K3 1/1| Benchmark | Kimi K3 | Kimi K2.6 | Diff |
|---|---|---|---|
| Creative Writing | 2,0712 / 99Normal (No Tools) | 1,72521 / 99Normal (No Tools) | +345.70 |
Specs
| Field | Kimi K3 | Kimi K2.6 |
|---|---|---|
| Publisher | Moonshot AI | Moonshot AI |
| Release date | 2026-07-16 | 2026-04-20 |
| Model type | Reasoning model | Reasoning model |
| Architecture | MoE | MoE |
| Parameters | 2.8T | 1T |
| Context length | 1M | 256K |
| Max output | 1M | Not available |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Kimi K3 | Kimi K2.6 |
|---|---|---|
| Text input | ¥20 / 1M tokens | $0.95 / 1M tokens |
| Text output | ¥100 / 1M tokens | $4 / 1M tokens |
| Cache read | ¥2 / 1M tokens | $0.16 / 1M tokens |
| Cache write | Not public | $0.95 / 1M tokens |
Summary
- Kimi K3leads in:AI Agent - Tool Usage (4/4), Coding and Software Engineer (3/3), AI Agent - Information Search (1/1), General Evaluation (1/1), General Knowledge (1/1), Text Embedding (1/1), Writing and Creative Capabilities (1/1)
On average across the 12 shared benchmarks, Kimi K3 scores 44.55 higher.
Largest single-benchmark gap: Creative Writing — Kimi K3 2,071 vs Kimi K2.6 1,725 (+345.70).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.