The Model Index
Up to four models

Claude Sonnet 5.5 vs Kimi K3.1 Pro

On the index (GPT-4 = 100), Claude Sonnet 5.5 scores 187 and Kimi K3.1 Pro 179. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to Claude Sonnet 5.5
Presets
Claude Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9
Kimi K3.1 Pro
179163–195
WeightsOpen
ReleasedOct 2026
Price in / out$0.24 / $8.4
Context1.05M
Core tests taken4 of 9

Claude Sonnet 5.5 leads Kimi K3.1 Pro by 8 points, ahead on 4 of 4 shared core tests, at 1.8× the price.

Test by testthird-party results

Claude Sonnet 5.5Kimi K3.1 Pro
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)ProofBench v1.1ProofBench v1.1Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGTerminal-Bench 4.0Terminal-Bench 4.0IOIIOIVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSAPEX-AgentsAPEX-AgentsBioMysteryBenchBioMysteryBenchSRE BenchSRE BenchTerminal-Bench-ScienceTerminal-Bench-ScienceDTBenchDTBenchFurniture assemblyFurniture assemblyLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKHLAB-Vals-1.1HLAB-Vals-1.1Legal Research BenchLegal Research BenchTax Agent BenchTax Agent BenchNOVEL PROBLEMSMysteryMechanismMysteryMechanism
Every result as a table
TestClaude Sonnet 5.5Kimi K3.1 Pro
Reasoning & knowledge
GPQA Diamond (Epoch AI)95.6%94.2%
SimpleQA Verified46.5%62.2%
Maths
FrontierMath (tiers 1-3)88.8%78.3%
AIME-style maths (OTIS mock)100.0%100.0%
ProofBench v1.1100.0%91.0%
Chess puzzles59.0%45.0%
FrontierMath (tier 4)80.5%65.8%
Coding
Terminal-Bench 4.064.1%63.6%
IOI83.1%81.9%
Vibe Code Bench v1.192.4%84.9%
Agents
APEX-Agents75.5%65.5%
BioMysteryBench81.1%75.6%
SRE Bench30.1%27.1%
Terminal-Bench-Science47.1%31.4%
DTBench97.3%93.3%
Furniture assembly75.0%55.8%
LMCA68.3%57.6%
Mystery game puzzles65.0%42.0%
Professional work
HLAB-Vals-1.110.4%11.7%
Legal Research Bench48.1%37.5%
Tax Agent Bench42.0%24.9%
Novel problems
MysteryMechanism49.1%26.1%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG