The Model Index
Up to four models

o4-mini vs Qwen3.6 27B

On the index (GPT-4 = 100), o4-mini scores 141 and Qwen3.6 27B 141. 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 o4-mini
Presets
o4-mini
141126–157
WeightsClosed
ReleasedApr 2025
Price in / out–
Context–
Core tests taken5 of 9
Qwen3.6 27B
141125–158
WeightsOpen
ReleasedApr 2026
Price in / out$0.32 / $3.2
Context262K
Core tests taken2 of 9

o4-mini and Qwen3.6 27B are too close to call (0 points apart, within the uncertainty), ahead on 1 of 2 shared core tests.

Test by testthird-party results

o4-miniQwen3.6 27B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)MATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)AGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKCorpFin v2CorpFin v2MortgageTaxMortgageTaxTaxEval v2TaxEval v2
Every result as a table
Testo4-miniQwen3.6 27B
Reasoning & knowledge
GPQA Diamond (Epoch AI)79.6%85.9%
Maths
FrontierMath (tiers 1-3)36.1%35.1%
AIME-style maths (OTIS mock)81.7%91.1%
Agents
DTBench77.6%78.1%
LMCA26.5%34.5%
Mystery game puzzles5.0%7.0%
Professional work
CorpFin v259.0%62.3%
MortgageTax64.8%68.3%
TaxEval v274.8%71.3%
Task length · METR38 sec

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

This page as a chartDownload PNG