The Model Index
Up to four models

Kimi K3.1 Pro vs GPT-6 Sol

On the index (GPT-4 = 100), Kimi K3.1 Pro scores 179 and GPT-6 Sol 178. 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 Kimi K3.1 Pro
Presets
Kimi K3.1 Pro
179163–195
WeightsOpen
ReleasedOct 2026
Price in / out$0.24 / $8.4
Context1.05M
Core tests taken4 of 9
GPT-6 Sol
178162–194
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken6 of 9

Kimi K3.1 Pro and GPT-6 Sol are too close to call (1 point apart, within the uncertainty), ahead on 2 of 4 shared core tests, and costs 1.8× less.

Test by testthird-party results

Kimi K3.1 ProGPT-6 Sol
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 WORKLegal Research BenchLegal Research BenchTax Agent BenchTax Agent BenchNOVEL PROBLEMSMysteryMechanismMysteryMechanism
Every result as a table
TestKimi K3.1 ProGPT-6 Sol
Reasoning & knowledge
GPQA Diamond (Epoch AI)94.2%94.3%
SimpleQA Verified62.2%60.7%
Maths
FrontierMath (tiers 1-3)78.3%89.8%
AIME-style maths (OTIS mock)100.0%100.0%
ProofBench v1.191.0%83.0%
Chess puzzles45.0%56.0%
FrontierMath (tier 4)65.8%90.0%
Coding
Terminal-Bench 4.063.6%44.4%
IOI81.9%82.6%
Vibe Code Bench v1.184.9%87.8%
Agents
APEX-Agents65.5%54.3%
BioMysteryBench75.6%74.8%
SRE Bench27.1%30.5%
Terminal-Bench-Science31.4%30.0%
DTBench93.3%97.3%
Furniture assembly55.8%58.3%
LMCA57.6%59.1%
Mystery game puzzles42.0%56.0%
Professional work
Legal Research Bench37.5%28.8%
Tax Agent Bench24.9%15.0%
Novel problems
MysteryMechanism26.1%30.2%

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

This page as a chartDownload PNG