Claude Sonnet 5.5 vs Kimi K3
| Spec | Claude Sonnet 5.5 | Kimi K3 |
|---|---|---|
| Respan Index | 73.4 (#6) | 52.8 (#35) |
| Blended price per 1M | $4 | $2.52 |
| Context window | 1M | 1.0M |
| Input / output per 1M | $2 / $10 | $0.192 / $9.5 |
| Max output | 128K | 1.0M |
| Input | text, vision | text, vision |
| Released | 2026-09-28 | 2026-07-16 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude Sonnet 5.5 | Kimi K3 |
|---|---|---|
| Coding | 78.8 Claude Sonnet 5.5 | 38.8 Kimi K3 |
| Agents | 80.1 Claude Sonnet 5.5 | 61.8 Kimi K3 |
| Reasoning | 79.0 Claude Sonnet 5.5 | 54.8 Kimi K3 |
| Knowledge & language | 48.6 Claude Sonnet 5.5 | 52.9 Kimi K3 |
| Human preference | 60.2 Claude Sonnet 5.5 | 57.7 Kimi K3 |
Benchmarks both report
Claude Sonnet 5.5 leads on 21 of the 28 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Sonnet 5.5 | Kimi K3 |
|---|---|---|
| LMArena WebDev (LMArena) | 1772 | 1659 |
| LMArena Elo | 1473 | 1488 |
| LMArena Agent (LMArena) | 0.1556 | -0.0015 |
| MirrorCode (Epoch AI) | 97.8% | 54.4% |
| SAGE 1.1 (Vals AI) | 88% | 86.8% |
| Chess Puzzles (Epoch AI) | 59% | 37% |
| Vending-Bench 2 (Andon Labs) | 11165.28 | 5165.04 |
| Humanity's Last Exam (no tools) | 56.9% | 43.5% |
| APEX-Agents (Mercor) | 75.5% | 47.8% |
| FrontierMath Tier 4 v2 (Epoch AI) | 80.5% | 39% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 88.8% | 72.2% |
| FrontierSWE V2 (Proximal Labs) | 61.9% | 25.9% |
| Furniture Assembly (Epoch AI) | 75% | 34.2% |
| GPQA Diamond | 95.6% | 93.5% |
| LiveBench Agentic Coding (LiveBench) | 56.3% | 62.2% |
| LiveBench Coding (LiveBench) | 91.4% | 81.4% |
| LiveBench Data Analysis (LiveBench) | 78.6% | 78.7% |
| LiveBench Instruction Following (LiveBench) | 70.5% | 71.4% |
| LiveBench Language (LiveBench) | 83.4% | 85.5% |
| LiveBench Mathematics (LiveBench) | 96.7% | 84.4% |
| LiveBench Reasoning (LiveBench) | 91.6% | 90.7% |
| Mystery Game Puzzles (Epoch AI) | 65% | 26% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 97.2% |
| SAGE (Vals AI) | 51.8% | 52.8% |
| SimpleQA Verified | 46.5% | 50.6% |
| Terminal-Bench 4.0 (Vals AI) | 64.1% | 17.2% |
| SimpleBench (SimpleBench) | 75.9% | 60.7% |
| Humanity's Last Exam (with tools) | 64.5% | 56% |
FAQ
Is Claude Sonnet 5.5 better than Kimi K3?
Claude Sonnet 5.5 scores 73.4 on the Respan Index (#6), ahead of Kimi K3 at 52.8 (#35). Claude Sonnet 5.5 leads on 21 of the 28 benchmarks both report.
Which is cheaper, Claude Sonnet 5.5 or Kimi K3?
Claude Sonnet 5.5 lists at $2 input and $10 output per 1M tokens; Kimi K3 at $0.192 and $9.5. Kimi K3 is 1.6x cheaper per token at list price.
Which has the larger context window?
Claude Sonnet 5.5 accepts 1M tokens and Kimi K3 1.0M tokens.
Compare other models
- vsClaude Sonnet 5.5 vs Claude Sonnet 5
- vsKimi K3 vs Kimi K2.6
- vsClaude Sonnet 5.5 vs Gemini 3.8 Flash
- vsClaude Sonnet 5.5 vs Grok 4.7
- vsClaude Sonnet 5.5 vs GPT-6.2 Astra
- vsClaude Sonnet 5.5 vs Claude Fable 5.1
- vsClaude Sonnet 5.5 vs Claude Opus 5.5
- vsKimi K3 vs Grok 4.7
- vsKimi K3 vs Qwen3.8-Max
- vsKimi K3 vs Inkling 2 Small