Claude Sonnet 5.5 vs Kimi K3
Claude Sonnet 5.5 leads Kimi K3 by 14.1 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Sonnet 5.5 wins 20 and Kimi K3 wins 1 of 21 shared benchmarks. Claude Sonnet 5.5 is cheaper for agent workloads.
Add more models to this comparison →Pillars
| Pillar | Claude Sonnet 5.5 | Kimi K3 |
|---|---|---|
| Agentic coding | 79 | 63 |
| Long-horizon autonomy | 75 | 65 |
| Knowledge-work agents | 57 | 42 |
| Computer use | 61 | 43 |
| Security & context learning | 61 | 53 |
Shared benchmarks
| Benchmark | Claude Sonnet 5.5 | Kimi K3 |
|---|---|---|
| APEX-Agentsindex | 75.5% | 47.8% |
| Vending-Bench 2index | $11,165 | $5,165 |
| FrontierSWEindex | 61.9% | 25.9% |
| ARC-AGI | 96.5% | 94.5% |
| ARC-AGI-2 | 83.9% | 60.4% |
| Chess Puzzles | 59.0% | 37.0% |
| CritPt | 31.4% | 23.4% |
| DTBench | 97.3% | 91.2% |
| FrontierCode | 52.1% | 44.2% |
| FrontierMath Tier 4 | 80.5% | 39.0% |
| FrontierMath Tiers 1-3 | 88.8% | 72.2% |
| GPQA Diamond | 95.6% | 93.1% |
| LMCA | 68.3% | 52.7% |
| MirrorCode | 97.8% | 54.4% |
| OTIS Mock AIME | 100.0% | 97.2% |
| ProofBench | 100.0% | 87.0% |
| SciCode | 61.0% | 59.5% |
| SimpleBench | 75.9% | 60.7% |
| SimpleQA Verified | 46.5% | 50.6% |
| WebDev Arena | 1786 | 1674 |
| WeirdML v3 | 19.9% | 7.5% |
Specs and price
| Claude Sonnet 5.5 | Kimi K3 | |
|---|---|---|
| Agent Index | 69 (#9) | 54.9 (#26) |
| Agent $/M | $0.84 | $1.39 |
| Input / output $/M | $2.00 / $10.00 | $3.00 / $15.00 |
| Context | 1M | 1M |
| Released | Sep 28, 2026 | Jul 16, 2026 |
| Weights | Closed | Open |
| API hosts | 5 | 29 |
Don’t pick one. Route.
Shogo can run Claude Sonnet 5.5 and Kimi K3 side by side and send each step of an agent to the one that’s cheaper for it.
Try both in Shogo