Skip to main content
AI Choice Engine

Model comparison

Claude Sonnet 5 vs Kimi K2.6

Anthropic against Moonshot AI, compared on context, price, and verified benchmark results.

Catalog record checked September 26, 2026Individual provider fields may changeEvidence confidence: High — see receipts below

Anthropic

Claude Sonnet 5

Balanced

vs

Moonshot AI

Kimi K2.6

Balanced · Open weights

AI model capability comparison
SpecificationClaude Sonnet 5Kimi K2.6
ProviderAnthropicMoonshot AI
TierBalancedBalanced
Context windowWinner: 1M262K
Max output128KNot verifiedUnverified
Input / 1M tokens$2Winner: $0.95
Output / 1M tokens$10Winner: $4
WeightsClosedOpen
ParametersNot disclosedUnverified1T total / 32B active (MoE, 384 experts)
Reasoning levelsadaptiveNot verifiedUnverified
Modalitiestext, imagetext, image, video
LicenseNot disclosedUnverifiedModified MIT
API model idclaude-sonnet-5kimi-k2.6
ReleasedJune 30, 2026April 20, 2026
Artificial Analysis Intelligence Index [max] (2026-09-26)38.2Not verifiedUnverified
Artificial Analysis Intelligence Index (2026-09-26)Not verifiedUnverified27
Terminal-Bench 2.1 (2026-06-30)80.4Not verifiedUnverified
Humanity's Last Exam (2026-06-30)57.4Not verifiedUnverified
SWE-bench Verified (2026-09-01)79.6Not verifiedUnverified
LiveBench (2026-09-05)76Not verifiedUnverified

Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

  • 2026-09-26
    Artificial Analysis

    Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.

    Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check measuredAt.

  • 2026-09-05
    LiveBench official leaderboard (benchmark-owned), xhigh effort

    Contamination-resistant general capability across reasoning, coding, math, data analysis, and language, with monthly question refreshes.

    Comparable with caveatRolling question set: observations months apart measure different question mixes. Record the measurement date and compare within ~1 month windows.

  • 2026-09-01
    vals.ai SWE-bench Verified leaderboard (independent, mini-swe-agent bash-only); not published by Anthropic; a 72.7 CosmicJS claim is unverified

    Real GitHub issue resolution: does the model's patch pass the hidden tests.

    Comparable with caveatPost-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.

  • 2026-06-30
    Anthropic announcement (vendor, with tools)

    Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.

    Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.

  • 2026-06-30
    Anthropic announcement table (vendor, default effort; via Vellum transcription)

    Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.

    Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.

Pricing tiers

Claude Sonnet 5: Standard $2/$10 per MTok; cache reads 10% of base input. Knowledge cutoff Jan 2026.

Kimi K2.6: $0.95/$4.00 per MTok on the Moonshot API; cached input $0.16. No documented hard output cap; evals ran 98,304-token generations.

BalancedRecord checked September 26, 2026

Claude Sonnet 5

Claude Sonnet 5 is Anthropic's best speed/intelligence balance for high-volume agentic work at $2/$10.

Best for

  • Everyday generation
  • High-volume agents
  • Cost-sensitive work

Watch out

A step below Opus 5.5 on the hardest tasks; pick Opus 5.5 when quality is paramount. Sonnet 5.5 is announced but not yet released.

BalancedOpen weightsRecord checked September 26, 2026

Kimi K2.6

Kimi K2.6 is Moonshot's open-weight volume workhorse — a 1T MoE with native image/video input at 256K context, the base Kimi K2.7-Code and K3 build on.

Best for

  • Open-weight volume work
  • Multimodal input on a budget
  • Self-hosting at mid size

Watch out

256K context is small next to K3's 1M; video input is experimental (official API only). No documented hard output cap.

When the cheaper one wins

Kimi K2.6 is cheaper on output at $4 per million tokens against $10 for Claude Sonnet 5 — about 2.5×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. These are standard-tier API rates, excluding batch and cache discounts.

Run the model picker

Evidence confidence: High

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 2/5 core specs verified on both sides — Not published for at least one side: max output, parameter count, reasoning levels.
  • 1 shared named benchmark with differing scores — Measured on: Artificial Analysis Intelligence Index.
  • Verified within the last 90 days — Newest catalog check was 2 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Related comparisons

Diving deeper on one model? Claude Sonnet 5 · Kimi K2.6

Common questions

Claude Sonnet 5 vs Kimi K2.6

Answered from the verified figures on this page rather than general guidance.

Is Claude Sonnet 5 or Kimi K2.6 cheaper for input?
Kimi K2.6 is cheaper at $0.95 per million input tokens, against $2 for Claude Sonnet 5 — roughly 2.1× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Claude Sonnet 5 has tiered pricing: Standard $2/$10 per MTok; cache reads 10% of base input. Knowledge cutoff Jan 2026. Kimi K2.6 has tiered pricing: $0.95/$4.00 per MTok on the Moonshot API; cached input $0.16. No documented hard output cap; evals ran 98,304-token generations.
Is Claude Sonnet 5 or Kimi K2.6 cheaper for output?
Kimi K2.6 is cheaper at $4 per million output tokens, against $10 for Claude Sonnet 5 — roughly 2.5× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Claude Sonnet 5 has tiered pricing: Standard $2/$10 per MTok; cache reads 10% of base input. Knowledge cutoff Jan 2026. Kimi K2.6 has tiered pricing: $0.95/$4.00 per MTok on the Moonshot API; cached input $0.16. No documented hard output cap; evals ran 98,304-token generations.
Which has the larger context window, Claude Sonnet 5 or Kimi K2.6?
Claude Sonnet 5 accepts 1M tokens against 262K for Kimi K2.6. This only matters if you routinely send very long documents or large codebases.
Should I use Claude Sonnet 5 or Kimi K2.6?
Both sit in the balanced tier, so the choice usually comes down to price and context rather than capability. Claude Sonnet 5 suits everyday generation; Kimi K2.6 suits open-weight volume work.
Can I self-host Claude Sonnet 5 or Kimi K2.6?
Kimi K2.6 publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. Claude Sonnet 5 is a closed model whose supported access paths are controlled by its provider.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Input price: Kimi K2.6 costs $0.95 per 1M tokens versus $2 for Claude Sonnet 5 — a 2.1x difference at the headline tier.
  • Context: Claude Sonnet 5 takes 1M against 262K for Kimi K2.6 — only decisive if your prompts approach the smaller window.
  • Measured capability: Claude Sonnet 5 leads Artificial Analysis Intelligence Index 38.2 to 27 (measured 2026-09-26).
  • Deployment: Kimi K2.6 publishes weights you can self-host; the other is API-only.
Run the model pickerEstimate stack costAll model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.