Kimi K2.7 CodevsClaude Opus 4.8
Across 4 shared benchmarks, Claude Opus 4.8 leads overall: Kimi K2.7 Code wins 0, Claude Opus 4.8 wins 4, with 0 ties and an average score difference of -13.24.
Kimi K2.7 Code
Moonshot AI · 2026-06-12 · Coding model
Claude Opus 4.8
Anthropic · 2026-05-28 · Reasoning model
Kimi K2.7 Code0 wins(0%)(100%)4 winsClaude Opus 4.8
Benchmark scores
Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.
AI Agent - Tool Usage
Claude Opus 4.8 2/2| Benchmark | Kimi K2.7 Code | Claude Opus 4.8 | Diff |
|---|---|---|---|
| Terminal-Bench 2.1 | 67.0434 / 44Thinking (With Tools) | 78.9020 / 44Thinking High (With Tools) | -11.86 |
| MCP-Atlas | 7617 / 38Thinking (With Tools) | 82.206 / 38Deep Thinking (With Tools) | -6.20 |
Coding and Software Engineer
Claude Opus 4.8 1/1| Benchmark | Kimi K2.7 Code | Claude Opus 4.8 | Diff |
|---|---|---|---|
| DeepSWE | 3124 / 27Normal (With Tools) | 5913 / 27Deep Thinking (With Tools) | -28 |
General Knowledge
Claude Opus 4.8 1/1| Benchmark | Kimi K2.7 Code | Claude Opus 4.8 | Diff |
|---|---|---|---|
| LiveBench | 71.8930 / 115Normal (No Tools) | 78.794 / 115Deep Thinking (No Tools) | -6.90 |
Specs
| Field | Kimi K2.7 Code | Claude Opus 4.8 |
|---|---|---|
| Publisher | Moonshot AI | Anthropic |
| Release date | 2026-06-12 | 2026-05-28 |
| Model type | Coding model | Reasoning model |
| Architecture | MoE | Dense |
| Parameters | 1T | Not available |
| Context length | 256K | 1M |
| Max output | Not available | 125K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | Kimi K2.7 Code | Claude Opus 4.8 |
|---|---|---|
| Text input | $0.95 / 1M tokens | $5 / 1M tokens |
| Text output | $4 / 1M tokens | $25 / 1M tokens |
| Cache read | $0.19 / 1M tokens | $0.5 / 1M tokens |
| Cache write | Not public | $6.25 / 1M tokens |
Summary
- Claude Opus 4.8leads in:AI Agent - Tool Usage (2/2), Coding and Software Engineer (1/1), General Knowledge (1/1)
On average across the 4 shared benchmarks, Claude Opus 4.8 scores 13.24 higher.
Largest single-benchmark gap: DeepSWE — Kimi K2.7 Code 31 vs Claude Opus 4.8 59 (-28).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.