See key specs and per-benchmark scores for each model/mode. Scroll horizontally for all columns. 当前对比 2 个模型的评测数据与核心参数。
Claude Opus 4.8
Anthropic
Kimi K2.7 Code
Moonshot AI
Each axis is a category average, normalized to a 100-point radar.
Relative edge: 编程与软件工程 +28.0 / Relative gap: none clear
Relative edge: none clear / Relative gap: 编程与软件工程 -28.0
Method: for each model and benchmark, the chart first averages all scores in the current mode scope instead of taking the best score, then averages those benchmark scores within each category. Only benchmarks with at least two selected models scored are included; missing values are not counted as zero.
Best overall
Claude Opus 4.8 · 74.72
Best single
Claude Opus 4.8 · MCP-Atlas 82.20
Modality coverage
Kimi K2.7 Code · 3 modalities
Head to head
4
Benchmarks
4
Wins
0
Losses
+13.24
Average diff
Compare benchmark results across thinking modes and tool usage.
Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology
Complete scores for each model/mode across selected benchmarks.
4 benchmarks with comparable scores. Each model shows its best score; mode label is displayed below.
| Benchmark | Claude Opus 4.8 | Kimi K2.7 Code |
|---|---|---|
LiveBench 综合评估 | 78.79Deep Thinking Mode | 71.89Standard Mode |
DeepSWE 编程与软件工程 | 59.00Deep Thinking Mode ｜ Tools | 31.00Standard Mode ｜ Tools |
MCP-Atlas AI Agent - 工具使用 | 82.20Thinking Level · High ｜ Tools | 76.00Thinking Enabled ｜ Tools |
Terminal-Bench 2.1 AI Agent - 工具使用 | 78.90Thinking Level · High ｜ Tools | 67.04Thinking Enabled ｜ Tools |
Side-by-side input/output token pricing
Licensing, MoE architecture, and multi-modality support.
| Features & specs | Claude Opus 4.8Anthropic | Kimi K2.7 CodeMoonshot AI |
|---|---|---|
Core specsRelease | 2026-05-28 | 2026-06-12 |
Context length | 1M | 256K |
Parameters | — | 1T |
Active parameters | Not provided | 32B |
Max output | 128000 | Not provided |
MoE | No | Yes |
LicenseCode Open Source | Closed Source | Open Source · Modified MIT |
Weights Open Source | Closed Source | Open Source · Modified MIT |
Commercial use | 不开源 | 免费商用授权 |
Local deploymentWeight size | Not provided | 595GB |
VRAM for weights | Not provided | ≈ 595 GB (weights only, excludes KV cache) |
Weights | Not provided | Hugging Face |
Source repo | Not provided | GitHub |
Modality supportText Input/Output | / | / |
Image Input/Output | / | / |
Video Input/Output | Not provided | / |
ResourcesPaper / report | Introducing Claude Opus 4.8 | Kimi K2.7 Code |
DataLearner blog | Anthropic发布Claude Opus 4.8：定价不变，编程与智能体能力小幅提升， | Not provided |
