Claude Opus 4.6 Max

Released2026-02-05
Price per 1M$5.00 in · $25.00 out
Overall score57.9 · rank 153
Context window1,000,000 tokens
ProviderAnthropic
WeightsProprietary
ConfigurationMax

Scores

DimensionScoreRankBenchmarks
Overall: Balanced 57.9 153 17
Overall: Coding 57.7 150 11
Overall: Reasoning 58.4 144 13
Overall: Agentic work 57.9 158 10
Overall: Frontend 55.3 152 2
Coding 58.6 116 1
Agents 57.3 125 2
Reasoning 59.3 143 7
Math 57.8 80 4
Knowledge 57.3 56 2
Frontend 53.7 96 1
Value vs price+1.0214

Evidence

Coding 58.6 ±3.0

BenchmarkResultSourceDate
MirrorCode 33.3% Epoch AI 2026-10-21

Agents 57.3 ±1.8

BenchmarkResultSourceDate
APEX-Agents 46.3% Epoch AI 2026-11-11
tau2-bench Banking Knowledge 27.3% tau2-bench 2026-05-06

Reasoning 59.3 ±3.3

BenchmarkResultSourceDate
ARC-AGI-2 (ARC Prize verified) 68.8% ARC Prize 2026-11-11
ARC-AGI-1 (ARC Prize verified) 93.0% ARC Prize 2026-11-11
GPQA Diamond 88.4% Epoch AI 2026-08-06
EnigmaEval 7.6% Epoch AI 2026-11-11
ARC-AGI-3 0.5% ARC Prize 2026-11-11
Chess Puzzles 21.0% Epoch AI 2026-10-13
Mystery Game Puzzles 25.0% Epoch AI 2026-07-25

Math 57.8 ±1.3

BenchmarkResultSourceDate
FrontierMath Tier 4 26.8% Epoch AI 2026-06-11
FrontierMath Tiers 1-3 66.0% Epoch AI 2026-06-11
ProofBench 50.0% Epoch AI 2026-11-11
OTIS Mock AIME 2024-2025 91.1% Epoch AI 2026-08-06
FrontierMath Tiers 1-3 (2025 set) 40.7% Epoch AI 2026-02-12
FrontierMath Tier 4 (2025 set) 22.9% Epoch AI 2026-02-12

Knowledge 57.3 ±1.2

BenchmarkResultSourceDate
Humanity's Last Exam 34.4% Epoch AI 2026-11-11
SimpleQA Verified 47.0% Epoch AI 2026-08-27

Frontend 53.7 ±0.8

BenchmarkResultSourceDate
Vibe Code Bench v1.1 57.6% Vals AI 2026-11-09

Names matched to this model

claude-opus-4-6-max

Compare Claude Opus 4.6 Max with other models