Moonshot AI · Benchmarks

Kimi K3.1 Pro benchmarks

Kimi K3.1 Pro has 6 published scores in this dataset, from a Moonshot AI release dated 2026-10-23. Its composite index is 94.4, which places it 2nd of 22 ranked models and 1st among 15 open-weight models. Its strongest area is agentic (index 100.0) and its weakest is reasoning (index 88.7). Its best placing is on Humanity's Last Exam (with tools), where its 70.0 ranks 1st of 17 models with a published score.

Open weightsOfficial page

Category profile

Index 0–100: each score relative to the best published score on that test.

ReasoningCodingAgenticKnowledge
Reasoning
88.7#3 of 16 · 2 tests
Coding
93.11 test · not ranked
Agentic
100.0#1 of 8 · 2 tests
Knowledge
95.91 test · not ranked

Model facts

Lab
Moonshot AI
Type
Open weights
Released
2026-10-23
Context
1M
License
Not yet published

Kimi K3.1 Pro hardware requirements and cost

Moonshot AI has not published Kimi K3.1 Pro's parameter count, so memory needs are unknown.

Lighter or stronger open models

Open models ranked just above and below on the composite index, with their 4-bit memory needs.

Kimi K3.1 Pro speed and pricing

Measured figures link to their source; estimates are labelled.

API output speed
31 tok/sArtificial Analysis median · Artificial Analysis
Time to first token
5.66 sOpenRouter model page provider stats
API price per 1M tokens
$2.00 in · $10.00 outlab's own endpoint on OpenRouter · OpenRouter endpoints API
Compare speed and price across all models

Score by test

Rank is among every model with a published score on that test.

GPQA Diamond94.2%no tools, max effort (vendor-reported)#3 of 19 · 1.9 behind GPT-6 AstraHumanity's Last Exam51.1%HLE-Full (2,500 q), no tools, max effort (vendor-reported)#7 of 23 · 13.3 behind Claude Opus 5.5Humanity's Last Exam (with tools)70.0%HLE-Full (2,500 q), with tools, max effort (vendor-reported)#1 of 17 · top scoreTerminal-Bench 4.065.7%Terminal-Bench 4.0, Claude Code harness, max effort#3 of 16 · 4.9 behind Claude Sonnet 5.5BrowseComp92.1%max effort (vendor-reported)#1 of 8 · top scoreMMMU-Pro84.1%MMMU-Pro (not original MMMU), no tools (vendor-reported)#5 of 9 · 3.6 behind Claude Opus 5.5

Nearby in the composite ranking

Models with the closest composite index.

  1. 1Claude Opus 5.598.4
  2. 2Kimi K3.1 Pro94.4
  3. 3Claude Sonnet 5.591.9
  4. 4GPT-6 Astra91.4
  5. 5Claude Fable 5.191.2

Head-to-head comparisons

Side-by-side pages built from the tests both models report.

No head-to-head page for Kimi K3.1 Pro yet. Compare it on the rankings dashboard.

Sources

ModelTestScoreSettingSource
Kimi K3.1 ProGPQA Diamond94.2no tools, max effort (vendor-reported)DataCamp (relaying Moonshot's release table)
Kimi K3.1 ProHumanity's Last Exam51.1HLE-Full (2,500 q), no tools, max effort (vendor-reported)DataCamp (relaying Moonshot's release table)
Kimi K3.1 ProHumanity's Last Exam (with tools)70.0HLE-Full (2,500 q), with tools, max effort (vendor-reported)DataCamp (relaying Moonshot's release table)
Kimi K3.1 ProTerminal-Bench 4.065.7Terminal-Bench 4.0, Claude Code harness, max effortMoonshot AI blog: Kimi K3.1 Pro
Kimi K3.1 ProBrowseComp92.1max effort (vendor-reported)DataCamp (relaying Moonshot's release table)
Kimi K3.1 ProMMMU-Pro84.1MMMU-Pro (not original MMMU), no tools (vendor-reported)DataCamp (relaying Moonshot's release table)

Scores are published results from model cards, lab reports, and public leaderboards, each linked to its source. Settings such as thinking mode or test version differ between sources and are shown next to each score. OpenLLM Buddy catalog models are uncensored fine-tunes; their scores are those of the official base model. Data collected 2026-10-30. How the index works