Compare / head-to-head
Claude Sonnet 4.5vs
Kimi K2
Claude Sonnet 4.5 leads 4 of 4 shared benchmarks. Claude Sonnet 4.5 has the larger context window (200K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
4 – 0
Claude Sonnet 4.5 leads
Cheaper per token
—
list price, input + output
Larger context
Claude Sonnet 4.5
200K tokens
Providers
2 providers
Anthropic · Moonshot AI
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Kimi K2
Moonshot AI · released 2025-07-11
text
- Context
- 128K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 18 · 7 core
Quality
Benchmark matrix
4 shared · 32 only Claude Sonnet 4.5 · 14 only Kimi K2| Benchmark | Claude Sonnet 4.5 | Kimi K2 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| AIME 2025 | 84.2% ↗matharena ⚠ | 49.5% ↗ | +34.7 pt | Claude Sonnet 4.5 |
| GSO Opt@1 (GSO) | 12.7% ↗ | 2% ↗ | +10.7 pt | Claude Sonnet 4.5 |
| SimpleBench (SimpleBench) | 54.3% ↗ | 26.3% ↗ | +28 pt | Claude Sonnet 4.5 |
| WeirdML (Håvard Tveit Ihle) | 47.7% ↗ | 39.4% ↗ | +8.3 pt | Claude Sonnet 4.5 |
| Only Claude Sonnet 4.5 reports · 32 | ||||
| SWE-bench Verified | 77.2% ↗ | not reported | — | — |
| GPQA Diamond | 83.4% ↗ | not reported | — | — |
| Humanity's Last Exam (no tools) | 17.7% ↗ | not reported | — | — |
| LMArena Elo | 1456.6 ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 13.6% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 12% ↗epoch run | not reported | — | — |
| EBR-bench (Epoch AI run) | 2.4% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 23.9% ↗epoch run | not reported | — | — |
| GDPval-AA | 1276 ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 33.6% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1393 ↗ | not reported | — | — |
| MATH Level 5 (Epoch AI run) | 97.7% ↗epoch run | not reported | — | — |
| MCP Atlas | 43.8% ↗ | not reported | — | — |
| MMMLU | 89.5% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 63.4% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 68.9% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 17% ↗epoch run | not reported | — | — |
| OSWorld-Verified | 61.4% ↗ | not reported | — | — |
| OSWorld-Verified (XLANG) | 62.9% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 77.8% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 36.1% ↗ | not reported | — | — |
| SimpleQA Verified | 30.7% ↗epoch run | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 71.3% ↗epoch run | not reported | — | — |
| tau2-bench Airline (Sierra) | 72% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 25.3% ↗ | not reported | — | — |
| Tau2-bench Retail | 86.2% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 72.4% ↗ | not reported | — | — |
| Tau2-bench Telecom | 98% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 84.9% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 51% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 3838.74 ↗ | not reported | — | — |
| Only Kimi K2 reports · 14 | ||||
| MMLU-Pro | not reported | 81.1% ↗ | — | — |
| Aider-Polyglot | not reported | 60% ↗ | — | — |
| GPQA-Diamond | not reported | 75.1% ↗ | — | — |
| Humanity's Last Exam (Text Only) | not reported | 4.7% ↗ | — | — |
| IFEval (Prompt Strict) | not reported | 89.8% ↗ | — | — |
| LiveCodeBench v6 (Aug 24 - May 25) | not reported | 53.7% ↗ | — | — |
| MMLU-Redux | not reported | 92.7% ↗ | — | — |
| SimpleQA | not reported | 31% ↗ | — | — |
| SWE-bench Multilingual (Agentic Coding, single attempt) | not reported | 47.3% ↗ | — | — |
| SWE-bench Verified (Agentic Coding, single attempt) | not reported | 65.8% ↗ | — | — |
| Tau2 airline | not reported | 56.5% ↗ | — | — |
| Tau2 retail | not reported | 70.6% ↗ | — | — |
| Tau2 telecom | not reported | 65.8% ↗ | — | — |
| TerminalBench (Inhouse Framework) | not reported | 30% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Sonnet 4.5 minus Kimi K2 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude Sonnet 4.5 | Kimi K2 | Edge |
|---|---|---|---|
| Context window | 200K tokens | 128K tokens | Claude Sonnet 4.5 |
| Max output | 64K tokens | — | — |
| Input price / 1M | $3 ↗ | — | — |
| Output price / 1M | $15 ↗ | — | — |
| Cached input / 1M | $0.3 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | — | — |
| Modalities | text · vision | text | Claude Sonnet 4.5 |
| Released | 2025-09-29 | 2025-07-11 | — |
| Cited benchmark scores | 43 | 18 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Sonnet 4.5 vs …
Models sharing the most benchmarksMore matchups
Kimi K2 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Sonnet 4.5 and Kimi K2 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.