Benchmark profile
Apex
A high-difficulty mathematical reasoning benchmark reported in DeepSeek-V4 model evaluations.
Data verifiedBenchmark score on Apex — July 23, 2026
BenchLM mirrors the published score view for Apex. Qwen3.7 Max leads the public snapshot at 44.5% , followed by DeepSeek V4 Pro (Max) (38.3%) and DeepSeek V4 Flash (Max) (33.0%). BenchLM does not use these results to rank models overall.
Qwen3.7 Max
Alibaba
qwen3-7-max
DeepSeek V4 Pro (Max)
DeepSeek
deepseek-v4-pro-max
DeepSeek V4 Flash (Max)
DeepSeek
deepseek-v4-flash-max
Benchmark score table (9 models)
ScoreThe published Apex snapshot places Qwen3.7 Max first at 44.5%. The third row is 11.5 points behind. The broader top-10 range is 44.1 points, so the table still separates the published systems.
9 models have been evaluated on Apex. The benchmark falls in the Math category. This category carries a 5% weight in BenchLM.ai's overall scoring system. Apex is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About Apex
Year
2026
Tasks
Advanced mathematical reasoning
Format
Pass@1 math benchmark
Difficulty
Frontier math reasoning
BenchLM stores Apex as a display-only provider-table reference for exact first-party model comparisons.
BenchLM freshness & provenance
Version
Apex 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
FAQ
What does Apex measure?
A high-difficulty mathematical reasoning benchmark reported in DeepSeek-V4 model evaluations.
Which model scores highest on Apex?
Qwen3.7 Max by Alibaba currently leads with a score of 44.5% on Apex.
How many models are evaluated on Apex?
9 AI models have been evaluated on Apex on BenchLM.
Choose a model with this week’s evidence
Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.
One email each week. Unsubscribe anytime.