Update README.md
Browse files
README.md
CHANGED
|
@@ -67,9 +67,9 @@ Debugged vibecoder dataset
|
|
| 67 |
| Tasks | Version | n-shot | Metric | VibeCoder-20b-0.02-D*_RL | gpt-oss-20 | Qwen 3 235B |
|
| 68 |
|---------------------------|----------|--------|----------------|---------------------------|-------------|--------------|
|
| 69 |
| gsm8k_cot | 3 | 3 | exact_match ↑ | 0.8452 | 0.78 | 0.82 |
|
| 70 |
-
| humaneval | 1 | 0 | exact_match ↑ | 0.933
|
| 71 |
| mmlu_college_biology | 1 | 0 | exact_match ↑ | 1.000 | — | — |
|
| 72 |
-
| mmlu_HS_computer_science | 1 | 0 | exact_match ↑ | 1.000
|
| 73 |
| computer_security | 1 | 2 | acc ↑ | 0.8528 | — | — |
|
| 74 |
| college_computer_science | 1 | 2 | acc ↑ | 0.8528 | — | — |
|
| 75 |
|
|
|
|
| 67 |
| Tasks | Version | n-shot | Metric | VibeCoder-20b-0.02-D*_RL | gpt-oss-20 | Qwen 3 235B |
|
| 68 |
|---------------------------|----------|--------|----------------|---------------------------|-------------|--------------|
|
| 69 |
| gsm8k_cot | 3 | 3 | exact_match ↑ | 0.8452 | 0.78 | 0.82 |
|
| 70 |
+
| humaneval | 1 | 0 | exact_match ↑ | 0.933 | 0.73 | 0.92 |
|
| 71 |
| mmlu_college_biology | 1 | 0 | exact_match ↑ | 1.000 | — | — |
|
| 72 |
+
| mmlu_HS_computer_science | 1 | 0 | exact_match ↑ | 1.000 | — | — |
|
| 73 |
| computer_security | 1 | 2 | acc ↑ | 0.8528 | — | — |
|
| 74 |
| college_computer_science | 1 | 2 | acc ↑ | 0.8528 | — | — |
|
| 75 |
|