Hugging Face's logo

ricursiveAI
/
Ripple-65B-Base-Preview

Safetensors
ricursive
custom_code
Model card Files
xet
 Community
dzhang50 commited on
Commit
511b0d0
·
verified ·
1 Parent(s): 9902561

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -99,13 +99,13 @@ Therefore, our results represent a best-effort attempt at a fair comparison.
99
  | Pre-training tokens | 12T | 20T | **45T** | N/A | 23.8T |
100
  | **Knowledge** | | | | | |
101
  | MMLU | 89.6 | *92.0* | *91.3* | ***92.6*** | *92.4* |
102
- | MMLU-Pro | 84.2 | 86.8 | *87.3* | ***88.0*** | *76.5* |
103
  | GPQA Diamond | 85.2 | 87.0 | 87.2 | 89.0 | **90.6** |
104
  | **Math** | | | | | |
105
  | AIME 2024 | 97.1 | *94.2* | *97.5* | ***97.9*** | *96.7* |
106
  | AIME 2025 | 98.3 | *94.2* | *91.7* | ***100.0*** | *99.6* |
107
  | AIME 2026 | 95.0 | *95.4* | 97.1 | ***98.3*** | 97.7 |
108
- | HMMT Feb 2026 | 90.5 | *80.3* | *78.8* | ***93.9*** | **93.9** |
109
  | **Coding & Agentic** | | | | | |
110
  | Terminal-Bench 2.1 (self-reported) | **80.5** | 56.4 | 63.8 | 76.4 | 80.1 |
111
  | Terminal-Bench 2.1 (Terminus 2) | **80.5** | *55.1* | *56.2* | *78.7* | *70.8* |
@@ -113,13 +113,13 @@ Therefore, our results represent a best-effort attempt at a fair comparison.
113
  | SWE-bench Pro v1.0 | 61.42 | *46.9* | 54.3 | *58.2* | **66.1** |
114
  | SWE-bench Pro v2.0 Hard | **79.1** | *30.7* | *2.0* | *52.3* | 76.5 |
115
  | DeepSWE 1.1 | 44.2 | *0.2* | *1.8* | **60.0** | 43.3 |
116
- | SciCode (Inspect AI) | 39.4 | 44.6 | *47.0* | **58.5** | 49.2 |
117
  | τ³-bench banking | 31.27 | 22.6 | 23.7 | *14.4* | **36.1** |
118
  | AutomationBench (Public) | 36.4 | *8.4* | *14.6* | *42.4* | 39.3 |
119
  | MCP Atlas | 71.67 | *62.2* | 76.0 | **89.2** | 80.8 |
120
  | **Safety** | | | | | |
121
  | FORTRESS Adversarial | 83.8 | *79.3* | 78.0 | **94.2** | *92.1* |
122
- | FORTRESS Benign | 95.5 | *89.1* | **95.9** | *88.1* | *86.4* |
123
  | StrongREJECT | 97.5 | *98.2* | **98.6** | *94.7* | *95.8* |
124
  | **Instruction Following** | | | | | |
125
  | IFBench | 79.2 | **81.7** | 79.8 | *78.6* | 79.6 |
 
99
  | Pre-training tokens | 12T | 20T | **45T** | N/A | 23.8T |
100
  | **Knowledge** | | | | | |
101
  | MMLU | 89.6 | *92.0* | *91.3* | ***92.6*** | *92.4* |
102
+ | MMLU-Pro | 84.2 | 86.8 | *87.3* | ***87.9*** | *76.5* |
103
  | GPQA Diamond | 85.2 | 87.0 | 87.2 | 89.0 | **90.6** |
104
  | **Math** | | | | | |
105
  | AIME 2024 | 97.1 | *94.2* | *97.5* | ***97.9*** | *96.7* |
106
  | AIME 2025 | 98.3 | *94.2* | *91.7* | ***100.0*** | *99.6* |
107
  | AIME 2026 | 95.0 | *95.4* | 97.1 | ***98.3*** | 97.7 |
108
+ | HMMT Feb 2026 | 90.5 | *80.3* | 86.3 | ***93.9*** | ***93.9*** |
109
  | **Coding & Agentic** | | | | | |
110
  | Terminal-Bench 2.1 (self-reported) | **80.5** | 56.4 | 63.8 | 76.4 | 80.1 |
111
  | Terminal-Bench 2.1 (Terminus 2) | **80.5** | *55.1* | *56.2* | *78.7* | *70.8* |
 
113
  | SWE-bench Pro v1.0 | 61.42 | *46.9* | 54.3 | *58.2* | **66.1** |
114
  | SWE-bench Pro v2.0 Hard | **79.1** | *30.7* | *2.0* | *52.3* | 76.5 |
115
  | DeepSWE 1.1 | 44.2 | *0.2* | *1.8* | **60.0** | 43.3 |
116
+ | SciCode (Inspect AI) | 39.4 | 44.6 | 46.1 | **58.5** | 49.2 |
117
  | τ³-bench banking | 31.27 | 22.6 | 23.7 | *14.4* | **36.1** |
118
  | AutomationBench (Public) | 36.4 | *8.4* | *14.6* | *42.4* | 39.3 |
119
  | MCP Atlas | 71.67 | *62.2* | 76.0 | **89.2** | 80.8 |
120
  | **Safety** | | | | | |
121
  | FORTRESS Adversarial | 83.8 | *79.3* | 78.0 | **94.2** | *92.1* |
122
+ | FORTRESS Benign | 95.5 | *89.1* | **95.9** | *82.6* | *86.4* |
123
  | StrongREJECT | 97.5 | *98.2* | **98.6** | *94.7* | *95.8* |
124
  | **Instruction Following** | | | | | |
125
  | IFBench | 79.2 | **81.7** | 79.8 | *78.6* | 79.6 |