Update README.md
Browse files
README.md
CHANGED
|
@@ -112,12 +112,10 @@ We, over-caffinated researchers at VibeStud.io wanted to create a 50% pruned ver
|
|
| 112 |
| MiniMax-M2-THRIFT | **93.25%** | 1,319 | ✅ Complete |
|
| 113 |
| **Δ (Difference)** | **+0.53% ⬆️** | - | **THRIFT Better!** ✨ |
|
| 114 |
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
|
| 118 |
-
|
|
| 119 |
-
| MiniMax-M2-BF16 | **87.2%** | 90.7% | 95.56% | 82.86% | 85.16% | 85.82% | ✅ Complete |
|
| 120 |
-
| MiniMax-M2-THRIFT | 🔄 — | 🔄 | 🔄 | 🔄 | 🔄 | 🔄 | **In Progress** |
|
| 121 |
|
| 122 |
### 4) LiveCodeBench (Live Coding Problems)
|
| 123 |
|
|
|
|
| 112 |
| MiniMax-M2-THRIFT | **93.25%** | 1,319 | ✅ Complete |
|
| 113 |
| **Δ (Difference)** | **+0.53% ⬆️** | - | **THRIFT Better!** ✨ |
|
| 114 |
|
| 115 |
+
| Benchmark | MiniMax-M2-BF16 | MiniMax-M2-THRIFT | Change |
|
| 116 |
+
|-----------|------|------------|--------|
|
| 117 |
+
| **GSM8K** | 92.72% | 93.25% | **+0.53%** ⬆️ |
|
| 118 |
+
| **MATH-500 (Levels 1-4)** | 91.25% | 90.75% | -0.5% (near-parity) |
|
|
|
|
|
|
|
| 119 |
|
| 120 |
### 4) LiveCodeBench (Live Coding Problems)
|
| 121 |
|