Anthropic: Claude Haiku Latest vs MoonshotAI: Kimi K2.5
Side-by-side comparison of specs, pricing, benchmark scores, and task rankings. Updated 2026-11-07.
| Anthropic: Claude Haiku Latest | MoonshotAI: Kimi K2.5 | |
|---|---|---|
| Vendor | ~anthropic | moonshotai |
| Quality Score | 100 | 100 |
| Benchmark Score | - | 64.3 |
| Input Price | $0.10/M | $0.53/M |
| Output Price | $0.50/M | $3.33/M |
| Context Window | 1,000,000 | 262,144 |
| Max Output | 128,000 | 65,536 |
| Tool Calling | ✓ | ✓ |
| Structured Output | ✓ | ✓ |
| Reasoning Mode | ✓ | ✓ |
| Vision | ✓ | ✓ |
| Audio | - | - |
| Benchmark Scores | ||
| ai_index | - | 62.9 |
| eqbench | - | 55.2 |
The verdict
For a sample job of 1 million input tokens and 250,000 output tokens, Claude Haiku Latest costs $0.23 and Kimi K2.5 costs $1.36, so Claude Haiku Latest is about 6.1 times cheaper for the same work.
Claude Haiku Latest reads up to 1,000,000 tokens at once, roughly 1,500 pages of text, against about 393 pages for Kimi K2.5.
Across the 19 tasks where they differ, Claude Haiku Latest scores higher on 3 (Code Completion, JSON Extraction, Bulk Data Labeling), Kimi K2.5 on 16 (SQL Generation, Code Review, Code Refactoring and others).
Claude Haiku Latest was released in April 2026 and Kimi K2.5 in January 2026.
Pick Claude Haiku Latest if you need lower cost or long documents; pick Kimi K2.5 if you need the stronger all-round task scores.
Costs use current list prices per million tokens; page counts assume about 0.75 words per token and 500 words per page.
Who wins by task?
| Task | Anthropic: Claude Haiku Latest | MoonshotAI: Kimi K2.5 |
|---|---|---|
| SQL Generation | 133 | 142 |
| Code Review | 132 | 145 |
| Code Completion | 131 | 131 |
| Code Refactoring | 136 | 145 |
| Bug Fixing | 136 | 149 |
| Unit Test Generation | 124 | 132 |
| Code Documentation | 131 | 135 |
| Regex Writing | 119 | 127 |
| CI/CD Pipelines | 120 | 128 |
| Frontend Component Design | 122 | 131 |
| Data Analysis | 124 | 136 |
| ETL Scripting | 128 | 136 |
| JSON Extraction | 131 | 131 |
| Bulk Data Labeling | 129 | 128 |
| OCR / Document Parsing | 131 | 133 |
| Table Extraction from PDFs | 131 | 133 |
| Long-Document Summarization | 137 | 146 |
| Short-Form Summarization | 123 | 127 |
| Blog Post Writing | 121 | 130 |
Scores reflect capability match + benchmark data + pricing for each task. Methodology →