Codesota · Papers2026-04-24
§ 01 · Benchmark results
12 results reproduced from this paper.
View:
Sorted instantly in-page
Results
10
SOTA rows
2
Models
2
Datasets
0
| # | Model | Vendor | Benchmark | Value | SOTA | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | DeepSeek-V4-Pro Max | DeepSeek | GPQA Diamond | 90.1% | — | source ↗ | |
| 02 | DeepSeek-V4-Flash Max | DeepSeek | GPQA Diamond | 88.1% | — | source ↗ | |
| 03 | DeepSeek-V4-Pro Max | DeepSeek | MMLU-Pro | 87.5% | — | source ↗ | |
| 04 | DeepSeek-V4-Flash Max | DeepSeek | MMLU-Pro | 86.2% | — | source ↗ | |
| 05 | DeepSeek-V4-Pro Max | DeepSeek | BrowseComp | 83.4% | #1 | — | source ↗ |
| 06 | DeepSeek-V4-Pro Max | DeepSeek | SWE-Bench Verified | 80.6% | #1 | — | source ↗ |
| 07 | DeepSeek-V4-Flash Max | DeepSeek | SWE-Bench Verified | 79.0% | — | source ↗ | |
| 08 | DeepSeek-V4-Flash Max | DeepSeek | BrowseComp | 73.2% | — | source ↗ | |
| 09 | DeepSeek-V4-Pro Max | DeepSeek | HLE | 37.7% | — | source ↗ | |
| 10 | DeepSeek-V4-Flash Max | DeepSeek | HLE | 34.8% | — | source ↗ |
Benchmark trail
§ 02 · Models
2 models from this paper.
Read next
Three places to go from here.
Index
All papers
All tracked papers in the registry, with benchmark result, model, and leaderboard linkage where available.
Replacement
Papers with Code is dead — alternatives
What replaced PWC for each use case: LLMs, OCR, speech, vision, robotics.
Top hub
LLM benchmarks
Every frontier LLM benchmark, scored.