This website uses cookies for authentication, support chat, and analytics. Only authentication cookies are turned on by default.
Animate this data
Bar chart race of deepseek-v4-pro_max, gemini-4-argon_high, gpt-6-astra_max and 7 more, by GPQA Diamond.
Create it free
Takes a free account

deepseek-v4-pro_max

Chess Puzzles
19 %
Critpt
13 %
Dtbench
91 %
FrontierMath Tier 4 V2
2 %
FrontierMath Tiers 1 3 V2
45 %
GPQA Diamond
90 %
Lmca
41 %
OTIS Mock AIME 2024 2025
97 %
Proofbench
16 %
SciCode
50 %
SimpleQA Verified
47 %
SWE bench Verified
78 %
WeirdML
49 %
Training Compute
9,702,000,000,000.00T FLOP
deepseek-v4-pro_max benchmark results.

Chess Puzzles Monthly

Chess Puzzles score.

Chess Puzzles Yearly

Chess Puzzles score.

Critpt Monthly

Critpt score.

Critpt Yearly

Critpt score.

Dtbench Monthly

Dtbench score.

Dtbench Yearly

Dtbench score.

FrontierMath Tier 4 V2 Monthly

FrontierMath Tier 4 V2 score.

FrontierMath Tier 4 V2 Yearly

FrontierMath Tier 4 V2 score.

FrontierMath Tiers 1 3 V2 Monthly

FrontierMath Tiers 1 3 V2 score.

FrontierMath Tiers 1 3 V2 Yearly

FrontierMath Tiers 1 3 V2 score.

GPQA Diamond Monthly

GPQA Diamond score.

GPQA Diamond Yearly

GPQA Diamond score.

Lmca Monthly

Lmca score.

Lmca Yearly

Lmca score.

OTIS Mock AIME 2024 2025 Monthly

OTIS Mock AIME 2024 2025 score.

OTIS Mock AIME 2024 2025 Yearly

OTIS Mock AIME 2024 2025 score.

Proofbench Monthly

Proofbench score.

Proofbench Yearly

Proofbench score.

SciCode Monthly

SciCode score.

SciCode Yearly

SciCode score.

SimpleQA Verified Monthly

SimpleQA Verified score.

SimpleQA Verified Yearly

SimpleQA Verified score.

SWE bench Verified Monthly

SWE bench Verified score.

SWE bench Verified Yearly

SWE bench Verified score.

WeirdML Monthly

WeirdML score.

WeirdML Yearly

WeirdML score.