MonoMind monogramModelScale

Kimi K3

Current directory

Capability, route economics, service-level measurements and lifecycle evidence in one model-specific decision record.

Published Sep 14, 2026 · stale evidence · 5 benchmarks · 2 sources

Published benchmark evidence includes benchlm content observed outside the 8-day evidence window.

Source overall score
80.61
Blended $ / 1M (10:2)
$5.00
TTFT p50
Not reported

Six-axis evidence

Derived rank-percentiles · same axes and scale as Compare · throughput remains a separate runtime axis.

Kimi K3

AgenticCodingReasoningMathMultimodalThroughputKimi K3: 97.12230215827338 percentileKimi K3: 97.91666666666667 percentileKimi K3: 97.05882352941177 percentile
Exact capability values

Derived rank-percentile = 100 × (cohort size − rank) / (cohort size − 1). Only a published rank and its exact cohort size qualify; missing or single-entry cohorts remain gaps.

DomainScore / unitDerived rank-percentileRank / cohort sizeSource
Agentic73.64 score97.125 / 140BenchLM
Coding78.58 score97.924 / 145BenchLM
ReasoningNot reportedNot reportedNot reportedNot reported
MathNot reportedNot reportedNot reportedNot reported
Multimodal86.20 score97.062 / 35BenchLM
ThroughputNot reportedNot reportedNot reportedNot reported

Gaps are missing or ineligible evidence, never zero. Overall and Knowledge are not silently substituted for Math or runtime.

Runtime SLA evidence

A measured route and its conditions are required. Benchmark scores do not establish latency or throughput.

Time to first token (seconds)

Output throughput (tokens/second)

TTFT
Not reported
Throughput
Not reported
Measured at
Not reported
Region
Not reported
Percentile
Not reported
Concurrency
Not reported
Streaming
Not reported
Runtime source
Not reported

Identity, limits & route

Provider
Moonshot AI
Access
Unknown
Context
1,050,000
Maximum output
Not reported
Maximum input
Not reported
Input modalities
Not reported
Output modalities
Not reported
Representative route
benchlm:kimi-3
Price source
BenchLM source · observed Aug 30, 2026

Lifecycle & sunset

Release
2026-07-16
Provider lifecycle status
Not reported
Sunset
Not reported
Replacement
Not reported
Directory status
current

Directory presence is not a provider support or retirement promise.

Open the full lifecycle radar

Endpoint & itemized price matrix

Source-shaped price fields stay separate from the blended scenario above.

The first matrix preserves prices recorded with these benchmark results. Current catalog facts are shown separately below and may differ.

Host / routeInput $/1MOutput $/1MCache readCache writeLong contextContext windowMax outputAvailabilitySource / observed
moonshot-aibenchlm:kimi-3$3.00$15.00$0.30Not reportedNot reported1,050,000Not reportedRoute not verifiedPrice evidence: primaryBenchLM sourceAug 30, 2026

Current catalog · exact matching routes

Catalog catalog_a1fde82f709fd08cad5c8dd8_6747580c · published Sep 13, 2026. Matches require the same offer ID, provider and source model ID. A provider route expiry is not a model retirement or proof that the endpoint is offline.

No exact current catalog route facts are reported for this profile. Historical prices above remain benchmark-pinned evidence.

No current exact binding: benchlm:kimi-3.

Workload-aware cost example

Derived scenario · 10M input + 2M output tokens / month

Source input price
$3.00 / 1M
Source output price
$15.00 / 1M
Benchmark-pinned monthly cost
$60.00
Current exact-route monthly cost
Not reported
Current example catalog revision
catalog_a1fde82f709fd08cad5c8dd8_6747580c
Current price observation
Not reported
Formula
10 × input price + 2 × output price
Blended price
(10 × input price + 2 × output price) ÷ 12

Excludes cache, retries, tool calls and long-context tiers. Unknown required prices make the example unavailable. This is a price estimate, not a verified route-availability claim.

Use your own workload

History, conflicts & limitations

  1. Reported release date

    Recorded in the published model identity.

  2. First directory observation

    Revision benchmark_358fa7e2426809dd5b0ef6eebfb01e75. This is not necessarily the model release date.

  3. Last directory observation

    Revision benchmark_042b43f31b19a868c704a9e1f77b2223.

  4. BenchLM evidence observed

    Data from BenchLM.ai

  5. BenchLM evidence observed

    Data from BenchLM.ai

  • No route conflict is flagged in this snapshot; absence of a flag is not independent agreement.
  • Cache write, long-context rates and runtime conditions remain Not reported until qualified evidence is published.
  • Validate the selected route price, context limits, and evidence freshness before choosing.
Benchmark ledger and provenance

Public overall score 80.61 at source rank #5.

Profile benchmark revision
benchmark_042b43f31b19a868c704a9e1f77b2223
Publication cache revision
benchmark_042b43f31b19a868c704a9e1f77b2223+cache-20260914003702000-f621b422-e42a-47ce-9dda-29d7a3dde9a1
Benchmark-pinned price catalog
catalog_a1fde82f709fd08cad5c8dd8_6747580c
Current catalog context
catalog_a1fde82f709fd08cad5c8dd8_6747580c
Current catalog published
2026-09-13T20:33:39.353Z
Published
2026-09-14T00:37:02.000Z
Checked
2026-09-14T00:37:02.000Z
Generated
2026-09-14T00:37:02.000Z
Fallback
none
Verified alias
Canonical profile
Model key
source:benchlm:kimi-3

BenchLM · retained

Source content observed
2026-08-30T02:15:58.000Z
Source published
2026-08-29T16:34:49.708Z
Last attempted
2026-09-14T00:38:19.104Z
Last successfully verified
2026-08-30T02:15:58.000Z
Content hash
sha256:93e32b81e518ece89faa6ea4a32e4697d33bcb2e948c0f9d41d3bff11d7bc9eb
Retained from
benchmark_493ec3486292e24d894f626fae7a72d6
Latest failure
source_policy_rejected at 2026-09-14T00:38:19.104Z

LiteLLM · verified

Source content observed
2026-09-13T12:00:01.864Z
Source published
Not reported
Last attempted
2026-09-14T00:38:50.983Z
Last successfully verified
2026-09-14T00:38:50.983Z
Content hash
sha256:b0e4eb602920d79596dc648e174fd4f58bffb9c6ca7d38269d412a66c061dd3c
Retained from
Not retained
Latest failure
No recorded failure

LMArena · verified

Source content observed
2026-09-13T12:05:01.866Z
Source published
Not reported
Last attempted
2026-09-14T00:43:48.635Z
Last successfully verified
2026-09-14T00:43:48.635Z
Content hash
sha256:c5f20996733cf3fca0c500a1ba805738c50dfe6e2a8b7afb120783bfcb00f4e9
Retained from
Not retained
Latest failure
No recorded failure

OpenRouter · pinned

Source content observed
2026-09-13T20:33:39.353Z
Source published
Not reported
Last attempted
Not reported
Last successfully verified
Not reported
Content hash
sha256:7e4207886128c1130f91baf8e492b92a089d47af5a032158b7d243e9342e0be9
Retained from
Not retained
Latest failure
No recorded failure
BenchmarkScoreRankWeightLast UpdatedSource
benchlm:category:agentic73.64 score#5Not publishedAug 29, 2026BenchLMsupported · public-leaderboard
benchlm:category:coding78.58 score#4Not publishedAug 29, 2026BenchLMsupported · public-leaderboard
benchlm:category:knowledge83.80 score#7Not publishedAug 29, 2026BenchLMsupported · public-leaderboard
benchlm:category:multimodalGrounded86.20 score#2Not publishedAug 29, 2026BenchLMsupported · public-leaderboard
benchlm:overall:raw80.61 score#5Not publishedAug 29, 2026BenchLMsupported · public-leaderboard