The Model Index
Up to four models

Qwen3.6-Max-Preview vs Kimi K2.6

On the index (GPT-4 = 100), Qwen3.6-Max-Preview scores 155 and Kimi K2.6 152. 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 Qwen3.6-Max-Preview
Presets
Qwen3.6-Max-Preview
155138–172
WeightsClosed
ReleasedApr 2026
Price in / out–
Context–
Core tests taken2 of 9
Kimi K2.6
152136–169
WeightsOpen
ReleasedApr 2026
Price in / out$0.65 / $3.41
Context262K
Core tests taken4 of 9

Qwen3.6-Max-Preview and Kimi K2.6 are too close to call (3 points apart, within the uncertainty), ahead on 0 of 2 shared core tests.

Test by testthird-party results

Qwen3.6-Max-PreviewKimi K2.6
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA VerifiedSimpleQA VerifiedMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)FrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGSWE-bench VerifiedSWE-bench VerifiedSWE-benchSWE-benchAGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKCorpFin v2CorpFin v2
Every result as a table
TestQwen3.6-Max-PreviewKimi K2.6
Reasoning & knowledge
GPQA Diamond (Epoch AI)87.4%90.8%
SimpleQA Verified52.0%34.9%
Maths
AIME-style maths (OTIS mock)91.1%96.1%
FrontierMath (2025 set)23.1%39.0%
FrontierMath tier 4 (2025 set)4.2%14.6%
Coding
SWE-bench Verified76.6%76.6%
SWE-bench72.8%76.2%
Agents
DTBench87.2%90.9%
LMCA42.5%37.3%
Mystery game puzzles19.0%18.0%
Professional work
CorpFin v266.5%66.7%

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

This page as a chartDownload PNG