Signal SentrySearchUpdated Nov 20, 05:30 UTCAM Drop
Models · scorecard

Kimi K3.1 Pro

What the vendor claims, next to what independent boards measured. The two are never mixed in one column.

At a glance

Maker
MoonshotAI
Price per 1M tokens
$0.253 in · $8.8 out
Context window
1.05M
Input → output
text, image, video → text
Added to OpenRouter
Oct 23, 2026

Source: OpenRouter, as of Nov 20, 06:00 UTC. Model page on OpenRouter

What the vendor claims

Quoted word for word from the vendor's own launch post or model card. Claims, not measurements.

Scores the vendor claims, each with its source and the quoted line
BenchmarkClaimedSource
GPQA DiamondThe source says: Idavidrein/gpqa · Diamond View evaluation results leaderboard 94.294.2%Hugging Face · Nov 4From Drop #067 · Thu, Nov 5, 2026 · Morning
Terminal-Bench 4.0The source says: K3.1 Pro scores 65.7%, ahead of GPT-6 Astra (58.2%) and narrowly behind Claude Opus 5.5 (66.4%).65.7%Moonshot AI · Oct 23From Drop #044 · Sat, Oct 24, 2026 · Evening
BenchCADSetting: with toolsThe source says: K3.1 Pro scores 92.7% with tools, approaching the performance of Claude Opus 5.5 (96.2%) and GPT-6 Astra (95.9%).92.7%Moonshot AI · Oct 23From Drop #044 · Sat, Oct 24, 2026 · Evening
OfficeQA Pro v2The source says: K3.1 Pro achieves state-of-the-art results on OfficeQA Pro v2 (64.4)64.4Moonshot AI · Oct 23From Drop #044 · Sat, Oct 24, 2026 · Evening
Kimi Hallu Bench Hard, claim hallucination rateThe source says: its claim-level hallucination rate fell from 23.4% for K3 to 8.3%8.3%Moonshot AI · Oct 23From Drop #044 · Sat, Oct 24, 2026 · Evening
Terminal-Bench 4.0Setting: max reasoning, Claude Code harnessThe source says: K3.1 Pro scores 65.7%, ahead of GPT-6 Astra (58.2%) and narrowly behind Claude Opus 5.5 (66.4%).65.7%Moonshot AI · Oct 23From Drop #043 · Sat, Oct 24, 2026 · Morning

Independent results

Measured by independent sources (Epoch AI, LMArena, OpenRouter's benchmark runs, τ²-bench, Vectara), not by the vendor. "Listed as" is the source's own name for the model, so you can check our match.

Independent benchmark results for this model, each with its source and date
BoardResultRank
Epoch AI · Epoch Capabilities IndexListed as: Kimi K3.1 ProSource: Epoch AI (CC BY), as of Nov 20, 2026. Source161.36Index17
LMArena · Text (style control)Listed as: Kimi K3.1 Pro (Max)LMArena (CC BY 4.0), as of Nov 18, 2026. Source1,487Arena score23
LMArena · WebDevListed as: Kimi K3.1 Pro (Max)LMArena (CC BY 4.0), as of Nov 18, 2026. Source1,684Arena score16
LMArena · AgentListed as: Kimi K3.1 Pro (Max)LMArena (CC BY 4.0), as of Nov 18, 2026. Source0.0388Score24
OpenRouter · GPQA DiamondListed as: Kimi K3.1 Provia Moonshot AI, its own providerSource: OpenRouter (openrouter.ai), licensed under CC BY 4.0, as of Nov 20, 2026. Source92.9%Accuracy13
OpenRouter · GPQA Diamond: cost per taskListed as: Kimi K3.1 Provia Moonshot AI, its own providerLower is better on this board.Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0, as of Nov 20, 2026. Source$0.11Cost per task37
OpenRouter · GPQA Diamond: time per taskListed as: Kimi K3.1 Provia Moonshot AI, its own providerLower is better on this board.Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0, as of Nov 20, 2026. Source152 sTime per task34
OpenRouter · τ²-bench airlineListed as: Kimi K3.1 Provia Moonshot AI, its own providerSource: OpenRouter (openrouter.ai), licensed under CC BY 4.0, as of Nov 20, 2026. Source76.4%Accuracy25
OpenRouter · τ²-bench airline: cost per taskListed as: Kimi K3.1 Provia Moonshot AI, its own providerLower is better on this board.Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0, as of Nov 20, 2026. Source$0.25Cost per task39
OpenRouter · τ²-bench airline: time per taskListed as: Kimi K3.1 Provia Moonshot AI, its own providerLower is better on this board.Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0, as of Nov 20, 2026. Source349 sTime per task43

Price history

OpenRouter's list price per 1M tokens in each of our snapshots.

  • Output now $8.8
  • Input now $0.253

Changed 8 times across our 55 snapshots.

Show the numbers
This model's OpenRouter price in each of our snapshots
SnapshotInput $/1MOutput $/1M
Nov 20, 06:04 UTC$0.253$8.8
Nov 19, 16:04 UTC$0.253$8.8
Nov 19, 04:04 UTC$0.253$8.8
Nov 18, 18:04 UTC$0.2403$8.4023
Nov 18, 04:03 UTC$0.2403$8.4023
Nov 17, 16:01 UTC$0.2403$8.4023
Nov 17, 04:04 UTC$0.2403$8.4023
Nov 16, 19:54 UTC$0.2403$8.4023
Nov 16, 04:05 UTC$2.3$11.5
Nov 15, 16:04 UTC$0.2403$8.4023
Nov 15, 04:03 UTC$0.2375$8.4114
Nov 14, 16:04 UTC$2$10
Nov 14, 04:05 UTC$2$10
Nov 13, 16:05 UTC$2$10
Nov 13, 04:04 UTC$0.2375$8.4114
Nov 12, 16:05 UTC$0.2375$8.7856
Nov 12, 04:04 UTC$2$10
Nov 11, 16:01 UTC$2$10
Nov 11, 04:04 UTC$2$10
Nov 10, 16:04 UTC$2$10
Nov 10, 04:05 UTC$2$10
Nov 9, 16:04 UTC$2$10
Nov 9, 04:04 UTC$2$10
Nov 8, 16:04 UTC$2$10
Nov 8, 04:03 UTC$2$10
Nov 7, 16:04 UTC$2$10
Nov 7, 04:04 UTC$2$10
Nov 6, 16:04 UTC$2$10
Nov 6, 04:04 UTC$2$10
Nov 5, 16:05 UTC$2$10
Nov 5, 10:05 UTC$2$10
Nov 4, 16:02 UTC$2$10
Nov 4, 04:04 UTC$2$10
Nov 3, 16:04 UTC$2$10
Nov 3, 13:26 UTC$2$10
Nov 2, 16:01 UTC$2$10
Nov 2, 04:04 UTC$2$10
Nov 1, 16:03 UTC$2$10
Nov 1, 04:04 UTC$2$10
Oct 31, 16:04 UTC$2$10
Oct 31, 04:04 UTC$2$10
Oct 30, 16:03 UTC$2$10
Oct 30, 04:04 UTC$2$10
Oct 29, 16:03 UTC$2$10
Oct 29, 04:04 UTC$2$10
Oct 28, 16:04 UTC$2$10
Oct 28, 09:22 UTC$2$10
Oct 27, 16:03 UTC$2$10
Oct 27, 04:03 UTC$2$10
Oct 26, 16:04 UTC$2$10
Oct 26, 04:03 UTC$2$10
Oct 25, 16:04 UTC$2$10
Oct 25, 06:03 UTC$2$10
Oct 24, 15:04 UTC$2$10
Oct 24, 03:03 UTC$2$10

Source: OpenRouter, as of Nov 20, 06:04 UTC

ValueOur calculation

Capability vs price

This model in colour, against every other model on the Epoch Capabilities Index that OpenRouter prices.

Scatter chart of 29 models, capability against the price of a sample task. Best value at its price: Claude Haiku 5.5, GPT-6.1 Terra, Gemini 4 Carbon, GPT-6.2 Astra.155160165170175$0.001$0.01$0.10$1.00Price of the sample task (log scale)Epoch Capabilities IndexGPT-6.2 Astra (OpenAI): index 174.17, $0.16 per sample taskClaude Fable 5.2 (Anthropic): index 173.5, $0.16 per sample taskGemini 4 Carbon (Google): index 169.78, $0.04 per sample taskGPT-6 Astra (OpenAI): index 169.2, $0.20 per sample taskClaude Opus 5.5 (Anthropic): index 168.7, $0.08 per sample taskGPT-6.1 Sol (OpenAI): index 168.63, $0.04 per sample taskGPT-6.1 Terra (OpenAI): index 167.72, $0.02 per sample taskClaude Fable 5.1 (Anthropic): index 167.09, $0.20 per sample taskClaude Sonnet 5.5 (Anthropic): index 166.59, $0.04 per sample taskGemini 4 Argon (Google): index 166.57, $0.04 per sample taskClaude Opus 5 (Anthropic): index 164.74, $0.10 per sample taskClaude Fable 5 (Anthropic): index 164.21, $0.20 per sample taskGPT-6 Sol (OpenAI): index 163.82, $0.04 per sample taskGPT-5.6 Sol (OpenAI): index 163.05, $0.08 per sample taskGPT-5.5 Pro (OpenAI): index 162.77, $0.66 per sample taskMuse Wonder (Meta): index 161.74, $0.08 per sample taskGPT-5.6 Terra (OpenAI): index 160.78, $0.044 per sample taskGPT-5.4 Pro (OpenAI): index 160.32, $0.66 per sample taskClaude Haiku 5.5 (Anthropic): index 160.29, $0.002 per sample taskGPT-5.5 (OpenAI): index 160.19, $0.11 per sample taskClaude Opus 4.8 (Anthropic): index 159.91, $0.10 per sample taskDeepSeek V4.1 Flash 1017 (DeepSeek): index 159.4, $0.0027 per sample taskGemini 3.8 Flash (Google): index 158.83, $0.017 per sample taskKimi K3 (MoonshotAI): index 158.6, $0.034 per sample taskGemini 3.7 Flash (Google): index 158.38, $0.015 per sample taskMuse Spark 1.3 (Meta): index 158.25, $0.021 per sample taskGPT-5.4 (OpenAI): index 157.87, $0.055 per sample taskGrok 4.6 (xAI): index 157.82, $0.032 per sample taskKimi K3.1 Pro (MoonshotAI): index 161.36, $0.02 per sample taskKimi K3.1 ProScatter chart of 29 models, capability against the price of a sample task. Best value at its price: Claude Haiku 5.5, GPT-6.1 Terra, Gemini 4 Carbon, GPT-6.2 Astra.155160165170175$0.001$0.01$0.10$1.00Price of the sample task (log scale)Epoch Capabilities IndexGPT-6.2 Astra (OpenAI): index 174.17, $0.16 per sample taskClaude Fable 5.2 (Anthropic): index 173.5, $0.16 per sample taskGemini 4 Carbon (Google): index 169.78, $0.04 per sample taskGPT-6 Astra (OpenAI): index 169.2, $0.20 per sample taskClaude Opus 5.5 (Anthropic): index 168.7, $0.08 per sample taskGPT-6.1 Sol (OpenAI): index 168.63, $0.04 per sample taskGPT-6.1 Terra (OpenAI): index 167.72, $0.02 per sample taskClaude Fable 5.1 (Anthropic): index 167.09, $0.20 per sample taskClaude Sonnet 5.5 (Anthropic): index 166.59, $0.04 per sample taskGemini 4 Argon (Google): index 166.57, $0.04 per sample taskClaude Opus 5 (Anthropic): index 164.74, $0.10 per sample taskClaude Fable 5 (Anthropic): index 164.21, $0.20 per sample taskGPT-6 Sol (OpenAI): index 163.82, $0.04 per sample taskGPT-5.6 Sol (OpenAI): index 163.05, $0.08 per sample taskGPT-5.5 Pro (OpenAI): index 162.77, $0.66 per sample taskMuse Wonder (Meta): index 161.74, $0.08 per sample taskGPT-5.6 Terra (OpenAI): index 160.78, $0.044 per sample taskGPT-5.4 Pro (OpenAI): index 160.32, $0.66 per sample taskClaude Haiku 5.5 (Anthropic): index 160.29, $0.002 per sample taskGPT-5.5 (OpenAI): index 160.19, $0.11 per sample taskClaude Opus 4.8 (Anthropic): index 159.91, $0.10 per sample taskDeepSeek V4.1 Flash 1017 (DeepSeek): index 159.4, $0.0027 per sample taskGemini 3.8 Flash (Google): index 158.83, $0.017 per sample taskKimi K3 (MoonshotAI): index 158.6, $0.034 per sample taskGemini 3.7 Flash (Google): index 158.38, $0.015 per sample taskMuse Spark 1.3 (Meta): index 158.25, $0.021 per sample taskGPT-5.4 (OpenAI): index 157.87, $0.055 per sample taskGrok 4.6 (xAI): index 157.82, $0.032 per sample taskKimi K3.1 Pro (MoonshotAI): index 161.36, $0.02 per sample taskKimi K3.1 Pro

1 model on the index has no OpenRouter price and is not plotted.

Show the numbers
Each model's capability index and sample-task price
ModelEpoch Capabilities IndexSample taskBest value
GPT-6.2 AstraOpenAI174.17$0.16Yes
Claude Fable 5.2Anthropic173.5$0.16
Gemini 4 CarbonGoogle169.78$0.04Yes
GPT-6 AstraOpenAI169.2$0.20
Claude Opus 5.5Anthropic168.7$0.08
GPT-6.1 SolOpenAI168.63$0.04
GPT-6.1 TerraOpenAI167.72$0.02Yes
Claude Fable 5.1Anthropic167.09$0.20
Claude Sonnet 5.5Anthropic166.59$0.04
Gemini 4 ArgonGoogle166.57$0.04
Claude Opus 5Anthropic164.74$0.10
Claude Fable 5Anthropic164.21$0.20
GPT-6 SolOpenAI163.82$0.04
GPT-5.6 SolOpenAI163.05$0.08
GPT-5.5 ProOpenAI162.77$0.66
Muse WonderMeta161.74$0.08
Kimi K3.1 ProMoonshotAI161.36$0.02
GPT-5.6 TerraOpenAI160.78$0.044
GPT-5.4 ProOpenAI160.32$0.66
Claude Haiku 5.5Anthropic160.29$0.002Yes
GPT-5.5OpenAI160.19$0.11
Claude Opus 4.8Anthropic159.91$0.10
DeepSeek V4.1 Flash 1017DeepSeek159.4$0.0027
Gemini 3.8 FlashGoogle158.83$0.017
Kimi K3MoonshotAI158.6$0.034
Gemini 3.7 FlashGoogle158.38$0.015
Muse Spark 1.3Meta158.25$0.021
GPT-5.4OpenAI157.87$0.055
Grok 4.6xAI157.82$0.032

Our calculation: Epoch AI's index against the sample-task price (undefined tokens in, undefined out, at each model's OpenRouter list price; the formula is under the price chart).

Source: Epoch AI (CC BY), as of Nov 20, 2026Source

Source: OpenRouter, as of Nov 20, 06:00 UTC

In the Drops

Models

Kimi K3.1 Pro Highspeed lands on Amazon Bedrock with zero data retention

AWS says Moonshot AI's K3.1 Pro Highspeed keeps a 1-million-token context and, per Moonshot, runs 2–3 times faster than K3.1 Pro. Data stays inside AWS and isn't shared with Moonshot; a Flex tier costs half the Standard price.

Why it matters: Teams wanting an open-weight model for agent loops can try it by swapping a model ID; check whether Flex latency suits background jobs.

From Drop #079 · Wed, Nov 11, 2026 · Morning
Models

Moonshot posts open weights for Kimi K3.1 Pro, a 1M-token-context agentic model

Moonshot's model card says K3.1 Pro is post-trained from Kimi K3, swaps in sparse attention layers for long context, and ships under its own Kimi K3.1 Pro License. It recommends vLLM, SGLang or TokenSpeed for serving.

Why it matters: Another frontier-class model you can host yourself. Read the custom license before deploying, and note the card's rule to pass back the full assistant message, reasoning included.

From Drop #067 · Thu, Nov 5, 2026 · Morning
ModelsFollowing since the Morning Dropin 2 Drops

Kimi K3.1 Pro draws 994 HN points; Moonshot claims 65.7% on Terminal-Bench 4.0

Moonshot's launch post says K3.1 Pro scores 65.7% on Terminal-Bench 4.0, ahead of GPT-6 Astra's 58.2% and behind Claude Opus 5.5's 66.4%, and that it removed cyber-related training data for the open-weight release.

Why it matters: The vendor's own numbers put an open-weight model, with weights due by Nov 4, near closed models on agentic coding. Independent checks are still to come.

From Drop #044 · Sat, Oct 24, 2026 · Evening