Compare / head-to-head
Kimi K2.6vsKimi K2.7 Code
Kimi K2.7 Code leads 7 of 11 shared benchmarks. Both offer a 256K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
4 – 7
Kimi K2.7 Code leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 256K tokens
Provider uptime (30d)
100%
Moonshot AI
Kimi K2.6
Moonshot AI · released 2026-04-20
textvision
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 14 · 8 core
Kimi K2.7 Code
Moonshot AI · released 2026-06-12
textvision
- Context
- 256K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 11 · 5 core
Quality
Benchmark matrix
11 shared · 3 only Kimi K2.6 · 0 only Kimi K2.7 Code| Benchmark | Kimi K2.6 | Kimi K2.7 Code | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 11 | ||||
| GPQA Diamond | 90.8% ↗epoch | 87.9% ↗epoch | +2.9 pt | Kimi K2.6 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 25.6% ↗epoch | 12.2% ↗epoch | +13.4 pt | Kimi K2.6 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 57.2% ↗epoch | 54% ↗epoch | +3.2 pt | Kimi K2.6 |
| Kimi Claw 24/7 Bench | 42.9% ↗ | 46.9% ↗ | -4 pt | Kimi K2.7 Code |
| Kimi Code Bench v2 | 50.9% ↗ | 62% ↗ | -11.1 pt | Kimi K2.7 Code |
| MCP-Atlas | 69.4% ↗ | 76% ↗ | -6.6 pt | Kimi K2.7 Code |
| MCPMark-Verified | 72.8% ↗ | 81.1% ↗ | -8.3 pt | Kimi K2.7 Code |
| MLS-Bench-Lite | 26.7% ↗ | 35.1% ↗ | -8.4 pt | Kimi K2.7 Code |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 96.1% ↗epoch | 95.6% ↗epoch | +0.5 pt | Kimi K2.6 |
| ProgramBench | 48.3% ↗ | 53.6% ↗ | -5.3 pt | Kimi K2.7 Code |
| SimpleQA Verified | 34.9% ↗epoch | 36.5% ↗epoch | -1.6 pt | Kimi K2.7 Code |
| Only Kimi K2.6 reports · 3 | ||||
| AIME 2026 | 95.8% ↗matharena ⚠ | not reported | — | — |
| LMArena Elo | 1454.9 ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 76.7% ↗epoch | not reported | — | — |
| Only Kimi K2.7 Code reports · 0 | ||||
| Kimi K2.7 Code reports nothing Kimi K2.6 does not. | ||||
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Kimi K2.6 minus Kimi K2.7 Code in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Kimi K2.6 | Kimi K2.7 Code | Edge |
|---|---|---|---|
| Context window | 256K tokens | 256K tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-04-20 | 2026-06-12 | — |
| Cited benchmark scores | 14 | 11 | — |
Reliability
Moonshot AI status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Kimi K2.6 vs …
Models sharing the most benchmarksMore matchups
Kimi K2.7 Code vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Kimi K2.6 and Kimi K2.7 Code on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.