Update .eval_results/ngen4-official-benchmarks.yaml
Browse files
.eval_results/ngen4-official-benchmarks.yaml
CHANGED
|
@@ -278,3 +278,37 @@
|
|
| 278 |
source:
|
| 279 |
url: https://tnsaai.com/models/ngen4
|
| 280 |
name: TNSA NGen-4 Evaluations
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 278 |
source:
|
| 279 |
url: https://tnsaai.com/models/ngen4
|
| 280 |
name: TNSA NGen-4 Evaluations
|
| 281 |
+
|
| 282 |
+
- dataset:
|
| 283 |
+
id: TIGER-Lab/MMLU-Pro
|
| 284 |
+
task_id: mmlu_pro
|
| 285 |
+
value: 89.6
|
| 286 |
+
date: '2026-04-06'
|
| 287 |
+
source:
|
| 288 |
+
url: https://tnsaai.com/models/ngen4
|
| 289 |
+
name: TNSA NGen-4 Evaluations
|
| 290 |
+
- dataset:
|
| 291 |
+
id: Idavidrein/gpqa
|
| 292 |
+
task_id: diamond
|
| 293 |
+
value: 90.1
|
| 294 |
+
date: '2026-04-06'
|
| 295 |
+
source:
|
| 296 |
+
url: https://tnsaai.com/models/ngen4
|
| 297 |
+
name: TNSA NGen-4 Evaluations
|
| 298 |
+
- dataset:
|
| 299 |
+
id: SWE-bench/SWE-bench_Verified
|
| 300 |
+
task_id: swe_bench_%_resolved
|
| 301 |
+
value: 72.7
|
| 302 |
+
date: '2026-04-06'
|
| 303 |
+
source:
|
| 304 |
+
url: https://tnsaai.com/models/ngen4
|
| 305 |
+
name: TNSA NGen-4 Evaluations
|
| 306 |
+
- dataset:
|
| 307 |
+
id: harborframework/terminal-bench-2.0
|
| 308 |
+
task_id: terminal_bench
|
| 309 |
+
value: 42.5
|
| 310 |
+
date: '2026-04-06'
|
| 311 |
+
source:
|
| 312 |
+
url: https://tnsaai.com/models/ngen4
|
| 313 |
+
name: TNSA NGen-4 Evaluations
|
| 314 |
+
|