EpistemeAI
/

VCoder-120b-1.0

Text Generation

text-generation-inference

8-bit precision

Model card Files Files and versions

legolasyiu commited on Oct 11

Commit

e8131ed

·

verified ·

1 Parent(s): 93d02a9

Update README.md

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -64,6 +64,8 @@ Debugged vibecoder dataset
 |        Tasks        | Version |      Filter      | n-shot |   Metric   | Vcoder-120B | gpt-oss-120 | DeepSeek-V3.2-Exp |
 |---------------------|---------|------------------|--------|------------|-------------|------------ |-------------------|
 | gsm8k (cot)         |    3    | flexible-extract |   5    | exact_match ↑ |    0.9557  |    0.88     |         -         |
 - Benchmark used [The Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/main)
 **Notes:**

 |        Tasks        | Version |      Filter      | n-shot |   Metric   | Vcoder-120B | gpt-oss-120 | DeepSeek-V3.2-Exp |
 |---------------------|---------|------------------|--------|------------|-------------|------------ |-------------------|
 | gsm8k (cot)         |    3    | flexible-extract |   5    | exact_match ↑ |    0.9557  |    0.88     |         -         |
+| AIME2025            |    3    | flexible-extract |   5    | exact_match ↑ |    0.98  |    0.98     |         -         |
 - Benchmark used [The Language Model Evaluation Harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/main)
 **Notes:**