#33Moonshot· released 2026-01-27

MoonshotAI: Kimi K2.5.

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued pretraining over approximately 15T mixed...

View on OpenRouter ↗
Context
262K
Input $/1M
$0.60
Output $/1M
$3.00
Modality
text · image
Arena Elo
1476
LMArena — human blind votes
AA Index
62.0
Artificial Analysis composite
LiveBench
76.8
Contamination-resistant
GPQA
80.6%
Grad-level science reasoning
MMLU-Pro
79.7%
Broad knowledge
SWE-bench
69.5%
Real GitHub bugs (Verified)
Terminal-Bench
59.4%
Agentic shell tasks
ARC-AGI
10.8%
Abstract reasoning
Aider Polyglot
75.6%
Multi-language code editing
Speed
74 tok/s
Median output speed

Profile

MoonshotAI: Kimi K2.5 is Moonshot's entry at position #33 on the current aggregated leaderboard. Its strongest signals are graduate-level science reasoning, real-world software engineering, unattended agentic work. Every figure below is aggregated from the public sources listed on the homepage and refreshed on each pipeline run.

The score spread is comparatively complete for this model, but the standing advice still applies: treat gaps of a few points as ties and validate on your own workload before committing.

How this model's position is computed is documented in the methodology; what each benchmark actually measures is in the benchmark guide. See a figure that disagrees with its source? Report it — accepted corrections apply on the next refresh.

Nearby on the leaderboard