Pairwise benchmark snapshot · Aug 16, 2026
This page compares Claude Haiku 4.5 (Anthropic) and MoonshotAI: Kimi K2.5 (Moonshot) using the latest snapshots we have as of Aug 16, 2026. On preference Elo, MoonshotAI: Kimi K2.5 is ahead by 77 points (1,515 vs 1,438; seed-bootstrap (Aug 1, 2026)). On SWE-bench coding, MoonshotAI: Kimi K2.5 resolves 71.3% versus 58.2% (seed-bootstrap (Aug 1, 2026)). Claude Haiku 4.5 streams faster (175 tok/s) while MoonshotAI: Kimi K2.5 is the cheaper output token ($2.85/1M). MoonshotAI: Kimi K2.5 has the larger context window (262k tokens). Every cell below is a dated snapshot from a named public source — we do not invent missing scores, and we do not run SWE-bench ourselves.
Anthropic
Claude Haiku 4.5Anthropic cheap/fast Claude SKU. Official Claude Platform list price $1/$5 per 1M tokens (Anthropic Haiku page).
Moonshot
MoonshotAI: Kimi K2.5Auto-discovered from OpenRouter (moonshotai/kimi-k2.5). Preview until a second source matches.
Instant pairwise benchmark recalculation across 400+ LLMs
Category wins across intelligence, speed, and pricing efficiency.
Preference Elo, Coding proficiency, SWE-bench & LiveBench accuracy
Generation throughput and time to first token responsiveness
Cost per million tokens and max context window length
Each spoke is a skill. Farther from the center is better (0–100th percentile). Tap any dot to inspect details.
77 pts advantage
103 tok/s faster
$2.15/1M cheaper
Simulate monthly production API costs based on published $/1M tokens.
MoonshotAI: Kimi K2.5 is estimated to save $47.30/month ($568/year).
Higher SWE-bench (71.3%).
Lower output list price ($2.85/1M).
Lower TTFT (95 ms).
Larger window (262k).
Both accept images. Defaulting to the higher-Elo side (MoonshotAI: Kimi K2.5).
| Target Workload | Recommended Pick | Evaluation Rationale |
|---|---|---|
| Repo / coding agents | MoonshotAI: Kimi K2.5 | Higher SWE-bench (71.3%). |
| High-volume chat | MoonshotAI: Kimi K2.5 | Lower output list price ($2.85/1M). |
| Voice / low-latency UI | Claude Haiku 4.5 | Lower TTFT (95 ms). |
| Long-document RAG | MoonshotAI: Kimi K2.5 | Larger window (262k). |
| Screenshots / vision | MoonshotAI: Kimi K2.5 | Both accept images. Defaulting to the higher-Elo side (MoonshotAI: Kimi K2.5). |
$1/$5 hosted Claude vs a cheap long-context open sibling. The alternative-to-Sonnet pair that is honest.
Huge window, cheap hosted lists. The Haiku alternative that is actually open-weight.
Official Anthropic list $1/$5. This is the SKU behind “cheapest Claude alternative” that is still Claude.
No comments posted on this matchup yet. Be the first to share an evaluation note!
The real PNG is generated at /compare/claude-haiku-4-5-vs-kimi-k2-5/opengraph-image for crawlers.
Verified head-to-head card
