CF-Div2-Stepfun

Step 3.5 Flash 86.1% leads since February 2026

Only in system cards

Models solve 53 Codeforces Div. 2 problems from September 2024 to February 2025. An offline judge with rebuilt test cases scores C++, Python and Java submissions.

StepFun reports avg@8 accuracy per language and an estimated Codeforces rating. The judge flags 92.45% of known failed submissions.

Made by: StepFun
Released: February 2026
Kind: Competitive programming
Level: Competition
Scored: Checked automatically
Answers: Code
Tasks: All public

Strongest model tested: Gemini 3 Pro #55 on the capability index
Last in a system card: February 2026
Last model added: February 2026
Scores refreshed: November 12th, 2026

Models scored on its own leaderboard

System card reports it, from 1 lab

Step 3.5 Flash leads with 86.1% among models released by February 2026

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

Bars Table

The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

Source: Official CF-Div2-Stepfun leaderboard

#	Model	Score	Setting	Date	Source
1	Step 3.5 Flash	86.1%	C++; avg@8	Feb 2026	Official leaderboard
2	Gemini 3 Pro	83.5%	C++; avg@8	Nov 2025	Official leaderboard
3	DeepSeek-V3.2	81.6%	C++; avg@8	Dec 2025	Official leaderboard
4	GLM-4.7	74.1%	C++; avg@8	Dec 2025	Official leaderboard
5	Claude Opus 4.5	72.2%	C++; avg@8	Nov 2025	Official leaderboard
6	Kimi K2 Thinking	67.9%	C++; avg@8	Nov 2025	Official leaderboard
7	MiniMax-M2.1	59%	C++; avg@8	Dec 2025	Official leaderboard
8	MiMo-V2-Flash	46.9%	C++; avg@8	Dec 2025	Official leaderboard

Labs report scores for 1 model in their cards. We plot every source in the charts below.

2 models have held number one on the official leaderboard since its release in February 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind StepFun

Own leaderboard Passed 85% in Feb 2026, by Step 3.5 Flash

Step 3.5 Flash 86.1%

Source: Official CF-Div2-Stepfun leaderboard

Step 3.5 Flash on the official leaderboard passed 85% in February 2026

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card Best so far

Sources: Official CF-Div2-Stepfun leaderboard and labs’ model cards

Labs report it only in system cards

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.

One system card reports it

Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.

Date	Document	Score	As the document writes it	Section
Feb 11, 2026	Step 3.5 Flash technical report	86.1	CF-Div2-Stepfun-cpp, avg@8 (Tables 5 and 15). PaCoRe 93.3. Python 81.5, Java 77.1, estimated Codeforces C++ pass@8 rating 2489 (Table 15)	Capabilities

One lab claim next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.

Model	Lab says	Board says	Gap
Step 3.5 Flash	86.1% CF-Div2-Stepfun-cpp, avg@8 (Tables 5 and 15). PaCoRe 93.3. Python 81.5, Java 77.1, estimated Codeforces C++ pass@8 rating 2489 (Table 15)	86.1% Leaderboard, C++; avg@8	Same