Codesota · Papers2026-02-11
§ 01 · Benchmark results
22 results reproduced from this paper.
View:
Sorted instantly in-page
Results
20
SOTA rows
1
Models
3
Datasets
0
| # | Model | Vendor | Benchmark | Value | SOTA | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | Step-3.5-Flash PaCoRe | — | AIME 2025 | 99.9% | #1 | — | source ↗ |
| 02 | Step-3.5-Flash | — | AIME 2025 | 97.3% | — | source ↗ | |
| 03 | Step-3.5-Flash Base | — | HellaSwag | 90.2% | — | source ↗ | |
| 04 | Step-3.5-Flash Base | — | BIG-Bench Hard | 88.2% | — | source ↗ | |
| 05 | Step-3.5-Flash Base | — | GSM8K | 88.2% | — | source ↗ | |
| 06 | Step-3.5-Flash | — | Tau2-Bench | 88.2% | — | source ↗ | |
| 07 | Step-3.5-Flash Base | — | MMLU | 85.8% | — | source ↗ | |
| 08 | Step-3.5-Flash PaCoRe | — | GPQA Diamond | 85.0% | — | source ↗ | |
| 09 | Step-3.5-Flash PaCoRe | — | MMLU-Pro | 84.8% | — | source ↗ | |
| 10 | Step-3.5-Flash | — | MMLU-Pro | 84.4% | — | source ↗ | |
| 11 | Step-3.5-Flash | — | GPQA Diamond | 83.5% | — | source ↗ | |
| 12 | Step-3.5-Flash Base | — | WinoGrande | 79.1% | — | source ↗ | |
| 13 | Step-3.5-Flash | — | SWE-Bench Verified | 74.4% | — | source ↗ | |
| 14 | Step-3.5-Flash Base | — | MATH | 66.8% | — | source ↗ | |
| 15 | Step-3.5-Flash Base | — | MMLU-Pro | 62.3% | — | source ↗ | |
| 16 | Step-3.5-Flash | — | BrowseComp | 51.6% | — | source ↗ | |
| 17 | Step-3.5-Flash Base | — | GPQA Diamond | 41.7% | — | source ↗ | |
| 18 | Step-3.5-Flash Base | — | SimpleQA | 31.6% | — | source ↗ | |
| 19 | Step-3.5-Flash PaCoRe | — | HLE | 27.9% | — | source ↗ | |
| 20 | Step-3.5-Flash | — | HLE | 23.1% | — | source ↗ |
Benchmark trail
§ 02 · Models
3 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.