Kimi K2 Thinking
Context 256K tokens
Top 4 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Platform | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Novita | OpenRouter | $0.600 | $2.50 | |
| 2 | Google Vertex AI | Google Vertex AI | $0.600 | $2.50 | |
| 3 | OpenRouter | $0.600 | $2.50 | ||
| 4 | AWS Bedrock | AWS Bedrock | $0.720 | $3.00 |
Composite
3 of 7 inputs · 2 from the model family6 radar axes: DesignArena's two boards share one45.3
AA Coding —Coding Agent v1.4 —AA Intelligence 22.0AA Agentic —Epoch ECI 145.8Software ECI 144.3DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
21 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
- Software ECI · attached
Agentic
Terminal-Bench Hard (AA)7431.1%
Terminal-Bench Hard (AA) pinned revision 74221fb ↗ · Published board — Tests a pinned 44-task hard subset of terminal-based work using Terminus 2.
τ²-Bench Airline (OpenRouter run)4768.7%
τ²-Bench Airline (OpenRouter run) published 2026-09-15 ↗ · Published board — Multi-turn service agents making tool calls under strict policy constraints. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Coding
SWE-bench Verifiedno percentile63.4%
SWE-bench Verified published 2026-09-10 ↗ · mini-SWE-agent — A 500-instance human-filtered subset of SWE-bench created with OpenAI, served as the default Verified leaderboard view.
Efficiency
GPQA Diamond (OpenRouter run) — measured cost per task35$0.046
GPQA Diamond (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running GPQA Diamond for this configuration.
τ²-Bench Airline (OpenRouter run) — measured cost per task52$0.045
τ²-Bench Airline (OpenRouter run) — measured cost per task published 2026-09-15 ↗ · Published board — Mean USD OpenRouter actually spent per task while running τ²-Bench Airline for this configuration.
Instruction-following
IFBench (AA single-turn)8268.1%
IFBench (AA single-turn) published 2026-09-10 ↗ · Published board — Tests precise single-turn instructions with deterministic rule checks.
Knowledge
Humanity's Last Exam (AA text-only)7623.8%
Humanity's Last Exam (AA text-only) published 2026-09-10 ↗ · Published board — Tests expert-level knowledge on AA's text-only Humanity's Last Exam subset.
AA-Omniscience Index62-21.4
AA-Omniscience Index published 2026-09-10 ↗ · Published board — Tests factual reliability while rewarding correct answers and penalizing hallucinations.
UGI NatInt10054.4
UGI NatInt published 2026-09-10 ↗ · Published board — A private-question evaluation of general knowledge and reasoning across textbook, popular-culture and world-model topics.
Long-context
AA-LCR v1.17172.0%
AA-LCR v1.1 v1.1 ↗ · Published board — Tests reasoning across multiple long documents with corrected answer keys and grading.
Math
AIME 2025 (AA) v20259694.7%
AIME 2025 (AA) v2025 ↗ · Published board — Advanced mathematical problem solving on AIME I and II 2025.
Reasoning
SimpleBench6939.6%
SimpleBench published 2026-09-10 ↗ · Published board — A multiple-choice text benchmark of over 200 questions covering spatio-temporal reasoning, social intelligence, and linguistic adversarial robustness, on which a non-specialized human baseline outperforms every tested LLM.
AA Intelligence Index7422.0
AA Intelligence Index published 2026-09-19 ↗ · Published board — Artificial Analysis publishes this board without a version number; we keep the date each result was retained.
Science
CritPt (AA)722.6%
CritPt (AA) published 2026-09-10 ↗ · Published board — Tests research-level physics reasoning with Python, symbolic and numerical answers.
GPQA Diamond (AA)7483.8%
GPQA Diamond (AA) published 2026-09-10 ↗ · Published board — Tests graduate-level biology, physics and chemistry knowledge on the Diamond subset.
GPQA Diamond (OpenRouter run)6283.4%
GPQA Diamond (OpenRouter run) published 2026-09-15 ↗ · Published board — Graduate-level science questions that resist retrieval and reward careful reasoning. (OpenRouter's own reproducible run, as published on openrouter.ai/benchmarks.)
Tool-use
τ²-Bench Telecom (AA)8993.0%
τ²-Bench Telecom (AA) published 2026-09-10 ↗ · Published board — Tests dual-control telecom agents that coordinate tool use with a simulated user.
Uncensored
UGI Willingness101.80
UGI Willingness published 2026-09-10 ↗ · Published board — A private-question evaluation of how far a model follows challenging instructions before refusing or deviating.
UGI9352.7
UGI published 2026-09-10 ↗ · Published board — A private-question suite combining sensitive-topic knowledge with willingness to follow controversial instructions.
Writing
EQ-Bench Creative Writing v3911,628 Elo
EQ-Bench Creative Writing v3 v3 ↗ · Published board — A LLM-judged creative writing benchmark with vocabulary and GPT-slop controls.
EQ-Bench Longform Creative Writing v1.119269.0
EQ-Bench Longform Creative Writing v1.11 ↗ · Published board — LLM-judged benchmark in which models plan and write a short story/novella over 8x 1000-word turns, scored 0-100 across 14 rubric dimensions.
UGI Writing10059.3
UGI Writing published 2026-09-10 ↗ · Published board — A maintainer-owned writing evaluation considering intelligence, style, repetition and length adherence, informed by human preferences.
Unusual results
2 threshold-crossing signals flagged · 20 eligible benchmark families
How flags are calculated
Heuristic screen, not statistical significance: benchmark families are correlated and source uncertainty is unknown. Peer evidence needs ≥ 20 independently measured matched configurations from ≥ 10 distinct model families. A flag needs a directed population z-score of magnitude ≥ 1.5 and a gap of ≥ 1.5 from the leave-one-benchmark-family-out mean z in the same direction, over ≥ 5 other benchmark families.
- unusually strong UGI Writing published 2026-09-10
Why
Observed: 59.28 pointsPeer mean 31.68366 · peer sd 10.68331 · n 71 · families 70Directed z 2.583 · baseline z 0.783 · gap 1.8 · profile n 1959.28 pointsmeasuredobserved 2026-09-10huggingface.co ↗Evidence
Axis: UGI Writing · published 2026-09-10 · Published boardExact value:59.28pointsObserved: 2026-09-10T22:04:13Z · publication date: not recordedObservation id:public:c0d87084c25aeb3a4628c9b5 - unusually strong UGI NatInt published 2026-09-10
Why
Observed: 54.36 pointsPeer mean 26.4323 · peer sd 11.33206 · n 74 · families 73Directed z 2.464 · baseline z 0.789 · gap 1.675 · profile n 1954.36 pointsmeasuredobserved 2026-09-10huggingface.co ↗Evidence
Axis: UGI NatInt · published 2026-09-10 · Published boardExact value:54.36pointsObserved: 2026-09-10T22:04:13Z · publication date: not recordedObservation id:public:2b564afef1463809a32ee5b6
Missing coverage · 123 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Token offers by platform · 4 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
4 offers within the active global filters; “—” means the catalog is active but no public token price is available.
OpenRouter (2)
| Novita | globalnovita/bf16 | $0.600 raw in $/1M | $2.50 raw out $/1M | |
| globalgoogle-vertex | $0.600 raw in $/1M | $2.50 raw out $/1M |
Google Vertex AI (1)
| Google Vertex AI | global | $0.600 raw in $/1M | $2.50 raw out $/1M |
AWS Bedrock (1)
| AWS Bedrock | eu-central-1EU | $0.720 raw in $/1M | $3.00 raw out $/1M |