CodeForces
CodeForces - competitive programming rating evaluated on custom query set.
Category
STEM & Reasoning
Max Score
—
Score Type
elo
Active
Yes
Model Scores
Scores for CodeForces
| Model | Score | Date | Verified |
|---|---|---|---|
| Qwen3.5-122B-A10B |
59.21%
|
01.02.2026 | Verified |
| Qwen3.5-35B-A3B |
57.07%
|
01.02.2026 | Unverified |
| Qwen3.5-27B |
53.23%
|
01.02.2026 | Unverified |
| Qwen3-235B-A22B |
60.58%
|
01.02.2026 | Unverified |
| GPT-5-mini 2025-08-07 |
60.99%
|
01.02.2026 | Unverified |
| Gemma4-31B-it |
60.70%
|
02.07.2026 | Verified |
| Gemma4-26B-A4B |
47.84%
|
02.07.2026 | Verified |
| Gemma4-12B |
46.09%
|
02.07.2026 | Verified |
| Gemma4-E4B |
24.70%
|
02.07.2026 | Verified |
| Gemma3-27B |
110.00
|
02.07.2026 | Unverified |
| GPT-OSS-120B |
70.01%
|
08.08.2025 | Verified |
| GPT-OSS-20B |
63.08%
|
05.08.2025 | Verified |
| GPT-5.4 |
90.98%
|
26.06.2026 | Verified |
| Gemini 3.1 Pro |
87.53%
|
26.06.2026 | Verified |
| DeepSeek-V4-Pro |
92.12%
|
26.06.2026 | Verified |
| Gemma4-E2B |
15.56%
|
02.07.2026 | Verified |
| DeepSeek-V4-Flash |
87.53%
|
26.06.2026 | Verified |
| DeepSeek-V4.1-Flash |
100.00%
|
10.09.2026 | Verified |