Benchmark Almanac

DeepSeek-Prover-V2-671B

DeepSeek-Prover-V2-671B places in the top three on miniF2F.

DeepSeek Released April 30th, 2025 Family DeepSeek-Prover The lab's model card Compare with others
7
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
DeepSeek Apr 2025

DeepSeek-Prover-V2-671B

Open weights Mid-size

No Epoch Capabilities Index score yet
  • PutnamBench 6.99% #4 /12
  • miniF2F 88.9% #3 /5

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Math and science

BenchmarkScoreRankSource
PutnamBench 6.99% #4 of 12 Official leaderboard
miniF2F 88.9% #3 of 5 Lab model card
CombiBench 10% #3 of 3 Lab model card
FormalMATH 28.3% #1 of 1 Lab model card
FormalMATH Lite 61.9% #1 of 1 Official leaderboard
ProofNet 37.1% #1 of 1 Lab model card
ProverBench (DeepSeek) 59.1% #1 of 1 Lab model card

Its lab's numbers next to 3 leaderboards

Where the benchmark's own leaderboard, or Epoch AI's run, also has this model. Gaps mostly come from different harnesses, effort levels and task subsets. Every pair.

Benchmark Lab says Board says Gap
PutnamBench 7.40% PutnamBench 49 out of 658 problems solved 6.99% Leaderboard, pass@1024 +0.4 pts
CombiBench 10% CombiBench with-solution setting, CoT, Pass@16, 10 of 100 solved (Table 5). Version 1 reported 12 10% Leaderboard, without solution, pass@16 Same
FormalMATH 28.3% FormalMATH-All Pass@32, CoT (Table 6). FormalMATH-Lite Pass@32 56.00, Pass@3200 61.88 28.3% Leaderboard, sampling budget 32 Same

Its launch post

The benchmarks the lab chose to headline, with the scores it gave.

Its system card

Every result in the longer documents the lab published with it. 3 of them aren't in the launch post.