Kimi K3 Benchmarks, Specs and Pricing: How It Ranks vs Frontier and Open Models

Published and last checked July 16, 2026. This analysis separates independent evaluation data from Moonshot AI’s launch claims and reflects the public evidence available on launch day.

Kimi K3 launches as the #4 tested configuration and effectively the #3 model family on Artificial Analysis Intelligence Index v4.1. Its 57.1 score trails Claude Fable 5 with Opus 4.8 fallback at 59.9 and GPT-5.6 Sol Max at 58.9, while sitting only 0.54 points behind Sol xhigh. Moonshot’s 2.8-trillion-parameter model also brings native image and video understanding, a 1,048,576-token context window and unusually competitive coding and agent scores.

That is the compelling version of the launch. The careful version matters just as much: Moonshot’s detailed benchmark table mixes Kimi Code, Claude Code and Codex harnesses; several K3 results were not yet visible on the referenced public leaderboards; and the promised model weights are not available today. Kimi K3 looks like a serious frontier challenger, but its broadest claims still need reproducible, third-party testing.

What you need to know

• Independent result: Artificial Analysis gives Kimi K3 Max a 57.1 score: #4 among tested configurations and effectively #3 when only the best configuration per model family is counted.
• Scale: Moonshot reports 2.8 trillion total parameters, with 16 of 896 experts selected in its Stable LatentMoE architecture. The company has not disclosed an active-parameter count.
• Context and modality: K3 accepts text, images and video and offers a 1,048,576-token context window.
• API price: $0.30 per million cached input tokens, $3 per million uncached input tokens and $15 per million output tokens.
• Availability: K3 is live through Kimi products and the Kimi API. Only Max reasoning is available at launch.
• Open-weight status: Moonshot promises full weights by July 27, 2026. Until those files and a license appear, K3 is planned open-weight—not currently downloadable open source.

Evidence key: “Independent” means a result run by Artificial Analysis rather than the model maker. “Official” means a specification or score published by Moonshot, OpenAI or Anthropic and not necessarily independently reproduced. “Pending” or “provisional” marks a future release, a missing artifact or a result whose public reproduction was not available at publication.

Kimi K3 specifications and pricing

Moonshot describes K3 as its most capable model and the first “open 3T-class” system. It combines Kimi Delta Attention (KDA), Attention Residuals (AttnRes) and Stable LatentMoE. KDA is intended to make attention scale more efficiently across long sequences, while AttnRes selectively retrieves representations from earlier layers instead of accumulating them uniformly through depth. Moonshot claims the overall design improves scaling efficiency by about 2.5 times over Kimi K2, but that figure is vendor-reported and the supporting technical report is still forthcoming. The model-specific K3 API quickstart separately confirms image and video inputs, the one-million-token window and the launch-time request limits.

Kimi K3 API pricing

Moonshot says its official API sees a cache-hit rate above 90% on coding workloads. Treat that as a service-side observation, not a guaranteed rate for every application. Your result will depend on prompt stability, agent design and how often the reusable prefix changes.

How the list price compares

At list price, K3 input is 40% cheaper than Sol and its output is 50% cheaper. Against Fable 5, both K3 rates are 70% lower. Those comparisons describe token prices, not completed-task cost: Artificial Analysis shows why K3’s substantially higher output-token use must be included in any budget model.

Independent benchmark: where Kimi K3 ranks

The strongest launch-day evidence is Artificial Analysis’s independent Kimi K3 evaluation. Its v4.1 index combines nine evaluations across agentic work, terminal use, scientific reasoning, knowledge and long-context reasoning rather than relying on one coding leaderboard. The published methodology weights agents at 34%, coding at 24%, scientific reasoning at 24% and general capability at 18%.

K3’s 0.54-point gap from Sol xhigh is too small to treat as a decisive capability difference. Artificial Analysis estimates the overall index’s 95% confidence interval at less than roughly one point. The 1.78-point gap from Sol Max and 2.75-point gap from the Fable configuration are clearer, although still not a substitute for workload-specific testing. The index is text-only and English-only; it cannot establish a multimodal or multilingual ranking by itself.

Cost and token use across the three leaders

K3 used far more output tokens to complete the evaluation—about 1.9 times Sol’s total and 1.5 times Fable’s—yet its lower token prices kept the evaluation bill slightly below Sol and far below the Fable configuration. That is promising price-performance, not proof that K3 will be cheaper in every deployment: agent loops, cache reuse, retries and output length can move real costs sharply. For deeper context on the two proprietary leaders, see Kingy AI’s analyses of GPT-5.6 Sol’s benchmarks and specifications and Claude Fable 5’s benchmark and pricing picture.

Kimi K3 vs Grok 4.5, Muse Spark 1.1 and Gemini 3.1 Pro

The composite score hides important reversals. The table below uses Artificial Analysis’s standardized results for four frontier models that are easy to omit when focusing only on the top three. K3 leads all three alternatives on the overall, agentic and coding indices, but Gemini remains stronger on scientific knowledge, factual reliability and visual reasoning.

The practical read: K3 is the stronger candidate for coding agents and long-horizon tool work in this group. Gemini is the safer counterexample to any “K3 wins everything” claim; it leads on GPQA, AA-Omniscience and MMMU-Pro. Muse is materially cheaper and edges K3 on Humanity’s Last Exam, while Grok’s lower overall score still comes with better knowledge reliability. Model selection should follow the task profile, not the composite rank alone.

Moonshot’s coding results are impressive—and not apples to apples

On Moonshot’s table, K3 leads Program Bench by 0.2 points over Sol and SWE Marathon by three points. It lands within 0.5 points of Sol on Terminal-Bench 2.1, while Fable leads FrontierSWE and Sol leads DeepSWE. This is not a story of K3 winning every coding benchmark; it is a story of the model staying competitive across several different kinds of long-horizon software work.

The testing conditions limit stronger conclusions. K3 uses the Kimi Code harness on DeepSWE, Program Bench, Terminal-Bench and FrontierSWE. Sol often uses Codex, while Fable and other Claude models use Claude Code or Terminus depending on the test. Fable’s safeguards can route some sessions to Opus 4.8, so its rows describe the production configuration rather than the underlying Fable model alone. On Terminal-Bench, Moonshot selects the best reported harness for several competitors. SWE Marathon mixes Claude Code for K3 and the Anthropic models with Codex for Sol. At publication time, the public DeepSWE and Program Bench pages also did not yet show a K3 entry that independently reproduced Moonshot’s number.

Moonshot says its K3 runs use Max reasoning, temperature 1.0 and top-p 1.0. The public API quickstart showed top-p 0.95 when checked on launch day. Even that small configuration mismatch is enough reason for evaluators to publish exact prompts, harness versions, tool permissions, token budgets and retry rules before treating a reproduction as definitive.

Agent and vision evaluations

Moonshot’s broader table suggests K3 is strongest when coding, browsing, tools and visual reasoning meet. On its reported agent evaluations, K3 scores 1,668 Elo on GDPval-AA v2, behind Fable at 1,760 and Sol at 1,748 but above Claude Opus 4.8 at 1,600. It reaches 1,548 on AA-Briefcase, second to Fable’s 1,583 and ahead of Sol’s 1,495. K3 also leads the compared group on Automation Bench at 30.8 and BrowseComp at 91.2, while Fable leads JobBench at 57.4.

Do not combine Moonshot’s 30.8 Automation Bench figure with Artificial Analysis’s separate AutomationBench-AA result, where K3 scores 52.7. The names are similar, but the implementations and scales differ. The first is part of Moonshot’s launch table; the second is an independent AA workflow evaluation.

Native vision also appears useful rather than decorative. Moonshot reports K3 at 81.6 on MMMU-Pro versus 81.2 for Fable and 83.0 for Sol. With Python tools, K3 reaches 91.3 on CharXiv RQ, between Fable’s 93.5 and Sol’s 89.1; on MathVision with Python, K3 and Sol tie at 97.8 behind Fable at 98.6. K3’s 91.1 on OmniDocBench leads Fable at 89.8 and Sol at 85.8. These are still vendor-collected comparisons, and some visual tests are averaged over only three runs. They support a serious multimodal capability claim, not a universal vision crown.

Speed, latency, verbosity and real cost

K3’s API begins streaming quickly, but the final answer does not arrive in two seconds. Artificial Analysis measures a 1.99-second time to the first streamed chunk, followed by about 32.24 seconds of reasoning before the first answer token. On its standardized 500-token performance workload, total response time is about 42.30 seconds.

What representative K3 requests cost

For the 100K-input, 10K-output example, GPT-5.6 Sol’s listed rates produce an $0.80 token bill and Fable 5’s produce $1.50, before tool charges or provider-specific caching. Near the context limit, Sol applies long-context multipliers above 272K input tokens, which makes a simple headline-rate multiplication misleading. These calculations are estimates, not task-cost guarantees: K3’s high reasoning-token use can erase part of its list-price advantage.

Is Kimi K3 really open source?

Not yet. Moonshot says it will release the full weights by July 27, 2026. As of launch day, there is no K3 checkpoint in the company’s public model repository, no K3 license, no model card and no full technical report. “Open 3T-class model” therefore describes the announced destination, not an artifact developers can download and audit today.

If Moonshot ships the same evaluated model under usable terms, K3 will reset the open-weight performance ceiling. Its 57.1 score is 6.0 points above GLM-5.2 Max, the current open-weight leader on Artificial Analysis. The broader field below distinguishes downloadable models from K3’s promised release and separates permissive licenses from restricted community terms.

This table also explains why “best” is not synonymous with “largest.” Qwen3.6 27B is far easier to deploy than a multi-trillion-parameter MoE, even though its composite score is lower. MiniMax M3 is downloadable but not permissively licensed in the same way as GLM, DeepSeek, Qwen or Inkling. K3 belongs at the top of this table only provisionally until Moonshot publishes the checkpoint, serving recipe and legal terms.

There are two catches. The first is release integrity: the eventual checkpoint, serving recipe and license must match the system Artificial Analysis tested closely enough for others to reproduce it. The second is infrastructure. A sparse 2.8T model does not activate every parameter for every token, but Moonshot has not disclosed the active-parameter total and recommends 64-plus-accelerator supernodes. For most teams, “open weight” will mean access through specialist inference providers rather than a rack under the office stairs. See our guide to the best open-weight AI models in 2026 and our GLM-5.2 benchmark analysis for the currently deployable field.

Strengths, limitations and deployment verdict

Where Kimi K3 looks strongest

• Near-frontier general capability: A 57.1 independent index score places K3 fourth by configuration and effectively third by model family.
• Long-horizon coding: Its consistency across Program Bench, Terminal-Bench, FrontierSWE and SWE Marathon makes a credible case for repository-scale and tool-heavy work.
• Vision inside the agent loop: Native visual input, a million-token window and strong chart, document and multimodal scores fit browser, frontend, research and document workflows.
• API economics: K3 completed the Artificial Analysis suite at a slightly lower reported cost than Sol despite using substantially more output tokens.
• Potential weight access: A faithful release would give researchers and infrastructure providers unusual control over a near-frontier model.

What should stop an immediate migration

• Key artifacts are missing: The weights, license, model card, safety documentation and technical report are not public yet.
• Detailed comparisons are vendor-run: Mixed harnesses and unpublished K3 leaderboard entries make several coding wins provisional.
• Only Max reasoning ships today: Teams cannot yet trade quality for latency and cost with low or high effort modes.
• High token use: Artificial Analysis recorded 130 million output tokens for K3, making generation discipline and cache design important.
• Knowledge reliability is not class-leading: K3’s 18.4 AA-Omniscience Index trails Grok 4.5 at 26.4 and Gemini 3.1 Pro Preview at 32.9.
• The headline index is narrow by design: It is an English-only, text-only suite and cannot settle multimodal or multilingual performance.
• Operational sensitivity: Moonshot warns that K3 expects its full thinking history to be preserved. Switching models mid-session or using an incompatible harness can destabilize quality.
• Excessive proactivity: Moonshot says K3 may make unexpected decisions when instructions are ambiguous. High-impact tools need strict permissions, confirmations and explicit behavioral boundaries.
• User experience gap: The company itself acknowledges that K3 still trails Fable 5 and GPT-5.6 Sol in overall user experience.

Verdict: Kimi K3 deserves an immediate controlled pilot for coding agents, deep research, visual document work and long-context automation. It does not yet justify a blanket replacement of Fable 5 or GPT-5.6 Sol. Run the same internal tasks through the same harness, cap tool permissions, record token and retry costs, and score completion quality—not just benchmark rank. Delay regulated self-hosting or a strategic open-source commitment until Moonshot publishes the checkpoint, license, model card and technical report.

Frequently asked questions

What is Kimi K3?

Kimi K3 is Moonshot AI’s 2.8-trillion-parameter Mixture-of-Experts model for reasoning, coding, knowledge work and native visual understanding. It supports a 1,048,576-token context window and is available through Kimi products and the Kimi API.

How does Kimi K3 compare with Claude Fable 5 and GPT-5.6 Sol?

Artificial Analysis Intelligence Index v4.1 scores K3 Max at 57.1, GPT-5.6 Sol Max at 58.9 and Fable 5 Max with Opus 4.8 fallback at 59.9. K3 is fourth by configuration because Sol xhigh also ranks above it, but effectively third when only the best setting from each model family is counted.

How much does the Kimi K3 API cost?

The launch rate is $0.30 per million cached input tokens, $3 per million uncached input tokens and $15 per million output tokens. Actual workload cost will depend heavily on cache hits, output length and agent retries.

Is Kimi K3 open source or open weight?

Neither description is accurate in the present tense on July 16. Moonshot has promised full model weights by July 27, but the checkpoint and license are not yet public. “Planned open-weight” is the precise description until that release can be inspected.

Can Kimi K3 process images and video?

Yes. K3 accepts image and video input alongside text, and its launch table reports results on MMMU-Pro, CharXiv, MathVision, ZeroBench, OmniDocBench and other multimodal evaluations. Output is text.

Can most companies self-host Kimi K3?

Probably not economically on ordinary infrastructure. Sparse routing means only a subset of experts is selected per token, but the model still contains 2.8 trillion total parameters. Moonshot recommends supernodes with at least 64 accelerators, and it has not yet disclosed the active-parameter count or final distribution formats.

Should teams switch from GPT-5.6 Sol or Fable 5?

Not without an internal bake-off. K3 is close on the independent composite, cheaper than Sol across the Artificial Analysis evaluation run and strong on several agent tests. Sol and the Fable configuration still score higher overall, while K3 has launch-day reproducibility and UX caveats. Route representative production tasks through identical tools and score accuracy, intervention rate, latency and total cost.

Sources and evidence standard

Primary launch specifications, pricing, availability, benchmark settings and limitations come from Moonshot AI’s Kimi K3 launch post, the official K3 API quickstart and the company’s launch announcement on X. The independent composite score, sub-evaluations, token use, speed and cost come from Artificial Analysis’s K3 profile, its v4.1 leaderboard and its published methodology. Comparator values were checked against the AA profiles for Grok 4.5, Muse Spark 1.1 and Gemini 3.1 Pro Preview, plus official model cards and licenses for the open-weight field. Moonshot’s detailed benchmark scores remain vendor-reported unless explicitly identified as independent. Any claim dependent on the future weight release should be rechecked on or after July 27, 2026.