File size: 21,668 Bytes
7432dd9 1e5a203 7432dd9 1e5a203 583f840 89d9d44 1e5a203 0851de6 583f840 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 |
---
license: agpl-3.0
tags:
- merge
- wizardlm
- wizardmath
pipeline_tag: text-generation
model-index:
- name: WizardLM-Math-70B-TIES-v0.1
results:
- task:
type: text-generation
name: Text Generation
dataset:
name: AI2 Reasoning Challenge (25-Shot)
type: ai2_arc
config: ARC-Challenge
split: test
args:
num_few_shot: 25
metrics:
- type: acc_norm
value: 68.52
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: HellaSwag (10-Shot)
type: hellaswag
split: validation
args:
num_few_shot: 10
metrics:
- type: acc_norm
value: 86.87
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: MMLU (5-Shot)
type: cais/mmlu
config: all
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 69.24
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: TruthfulQA (0-shot)
type: truthful_qa
config: multiple_choice
split: validation
args:
num_few_shot: 0
metrics:
- type: mc2
value: 53.61
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: Winogrande (5-shot)
type: winogrande
config: winogrande_xl
split: validation
args:
num_few_shot: 5
metrics:
- type: acc
value: 82.72
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1
name: Open LLM Leaderboard
- task:
type: text-generation
name: Text Generation
dataset:
name: GSM8k (5-shot)
type: gsm8k
config: main
split: test
args:
num_few_shot: 5
metrics:
- type: acc
value: 27.37
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/WizardLM-Math-70B-TIES-v0.1
name: Open LLM Leaderboard
---
## Examples
There are three killers in a room. Someone enters the room and kills one of them. Nobody leaves the room. How many killers are left in the room? Explain your reasoning step by step.
```
Initially, there are three killers in the room. Let's call them Killer A, Killer B, and Killer C.
Step 1: Someone enters the room and kills one of the killers. We don't know who this person is or which killer they killed. However, we know that one killer is dead.
Step 2: Now, we have two killers left in the room. These two killers are the ones who were not killed by the person who entered the room.
Step 3: The person who entered the room is not a killer, as they are not included in the initial three killers. However, they have killed one of the killers, so they are not innocent either.
Step 4: Since the person who entered the room is not a killer, we can conclude that there are only two killers left in the room after the incident.
So, the final answer is: There are 2 killers left in the room.
The answer is: there are 2 killers left in the room.
```
Answered wrong!
Mark is faster than Mary , Mary is faster than Joe. Is Joe faster than Mark? Let's think step by step
```
irst, we know that Mark is faster than Mary. This means that if they were to race, Mark would finish before Mary. We can represent this relationship as:
Mark > Mary
Next, we know that Mary is faster than Joe. This means that if Mary and Joe were to race, Mary would finish before Joe. We can represent this relationship as:
Mary > Joe
Now, we want to find out if Joe is faster than Mark. To do this, we can use the transitive property, which states that if A > B and B > C, then A > C. In our case, A represents Mark, B represents Mary, and C represents Joe. So, we can apply the transitive property to our relationships:
Since Mark > Mary and Mary > Joe, we can conclude that Mark > Joe.
So, the final answer is: No, Joe is not faster than Mark.
The answer is: No, Joe is not faster than Mark.
```
If I lay 2 wet shirts out in the sun flat on the ground to dry and it takes 5 hours until they are dry, how long would it take to dry 4 shirts of the same type that way simultanously?
```
First, we need to understand the relationship between the number of shirts and the time it takes to dry them. Since the shirts are laid out flat on the ground, they have the same surface area exposed to the sun. This means that the drying time is directly proportional to the number of shirts.
Step 1: Identify the given information.
- Time to dry 2 shirts: 5 hours
- Number of shirts: 2
Step 2: Set up a proportion to represent the relationship between the number of shirts and the time it takes to dry them.
- Let x be the time it takes to dry 4 shirts.
- We can write the proportion as:
(2 shirts / 5 hours) = (4 shirts / x)
Step 3: Solve for x.
- To solve for x, we can cross-multiply:
2 shirts * x = 5 hours * 4 shirts
- Simplify the equation:
2x = 20 shirt-hours
- Now, divide both sides by 2 to isolate x:
x = 10 hours
So, it would take 10 hours to dry 4 shirts of the same type simultaneously.
The answer is: 10.
```
Wrong, should be 5
explain step by step 25-4*2+3=?
```
First, we need to follow the order of operations (PEMDAS/BODMAS), which stands for Parentheses/Brackets, Exponents/Orders, Multiplication and Division, and Addition and Subtraction. This means we should perform the operations inside the parentheses first, then the exponents, then the multiplication and division, and finally the addition and subtraction.
Here's the given expression: 25 - 4 * 2 + 3
Step 1: Perform the multiplication operation inside the parentheses.
25 - (4 * 2) + 3
Step 2: Perform the multiplication operation.
25 - (8) + 3
Step 3: Now, we have a subtraction operation and an addition operation. Since they have the same precedence, we can perform them from left to right.
25 - 8 + 3
Step 4: Perform the subtraction operation.
17 + 3
Step 5: Perform the addition operation.
20
So, the final answer is 20.
The answer is: the final answer is 20.
```
## Prompt template
```
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"
```
or for CoT (❗For the simple math questions, we do NOT recommend to use the CoT prompt.)
```
"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: Let's think step by step."
```
## Eval
```python
{
"all": {
"acc": 0.6868282613819305,
"acc_stderr": 0.030371866427473967,
"acc_norm": 0.695311288530275,
"acc_norm_stderr": 0.030984285786669577,
"mc1": 0.36964504283965727,
"mc1_stderr": 0.01689818070697388,
"mc2": 0.5360987678643523,
"mc2_stderr": 0.014938153988985473
},
"harness|arc:challenge|25": {
"acc": 0.6424914675767918,
"acc_stderr": 0.014005494275916573,
"acc_norm": 0.6851535836177475,
"acc_norm_stderr": 0.01357265770308495
},
"harness|hellaswag|10": {
"acc": 0.6836287592113125,
"acc_stderr": 0.004641092001425294,
"acc_norm": 0.8686516630153356,
"acc_norm_stderr": 0.0033709059327855567
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.33,
"acc_stderr": 0.04725815626252605,
"acc_norm": 0.33,
"acc_norm_stderr": 0.04725815626252605
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6222222222222222,
"acc_stderr": 0.04188307537595852,
"acc_norm": 0.6222222222222222,
"acc_norm_stderr": 0.04188307537595852
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.8026315789473685,
"acc_stderr": 0.03238981601699397,
"acc_norm": 0.8026315789473685,
"acc_norm_stderr": 0.03238981601699397
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.72,
"acc_stderr": 0.04512608598542127,
"acc_norm": 0.72,
"acc_norm_stderr": 0.04512608598542127
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.7471698113207547,
"acc_stderr": 0.026749899771241214,
"acc_norm": 0.7471698113207547,
"acc_norm_stderr": 0.026749899771241214
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.8194444444444444,
"acc_stderr": 0.032166008088022675,
"acc_norm": 0.8194444444444444,
"acc_norm_stderr": 0.032166008088022675
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.48,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.57,
"acc_stderr": 0.04975698519562428,
"acc_norm": 0.57,
"acc_norm_stderr": 0.04975698519562428
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.33,
"acc_stderr": 0.04725815626252604,
"acc_norm": 0.33,
"acc_norm_stderr": 0.04725815626252604
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6647398843930635,
"acc_stderr": 0.03599586301247077,
"acc_norm": 0.6647398843930635,
"acc_norm_stderr": 0.03599586301247077
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.35294117647058826,
"acc_stderr": 0.047551296160629475,
"acc_norm": 0.35294117647058826,
"acc_norm_stderr": 0.047551296160629475
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.74,
"acc_stderr": 0.04408440022768079,
"acc_norm": 0.74,
"acc_norm_stderr": 0.04408440022768079
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.6893617021276596,
"acc_stderr": 0.03025123757921317,
"acc_norm": 0.6893617021276596,
"acc_norm_stderr": 0.03025123757921317
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.40350877192982454,
"acc_stderr": 0.046151869625837026,
"acc_norm": 0.40350877192982454,
"acc_norm_stderr": 0.046151869625837026
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.6068965517241379,
"acc_stderr": 0.040703290137070705,
"acc_norm": 0.6068965517241379,
"acc_norm_stderr": 0.040703290137070705
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.4312169312169312,
"acc_stderr": 0.0255064816981382,
"acc_norm": 0.4312169312169312,
"acc_norm_stderr": 0.0255064816981382
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.5,
"acc_stderr": 0.04472135954999579,
"acc_norm": 0.5,
"acc_norm_stderr": 0.04472135954999579
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.43,
"acc_stderr": 0.049756985195624284,
"acc_norm": 0.43,
"acc_norm_stderr": 0.049756985195624284
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.8193548387096774,
"acc_stderr": 0.021886178567172527,
"acc_norm": 0.8193548387096774,
"acc_norm_stderr": 0.021886178567172527
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5320197044334976,
"acc_stderr": 0.03510766597959217,
"acc_norm": 0.5320197044334976,
"acc_norm_stderr": 0.03510766597959217
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.71,
"acc_stderr": 0.045604802157206845,
"acc_norm": 0.71,
"acc_norm_stderr": 0.045604802157206845
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.8121212121212121,
"acc_stderr": 0.03050193405942914,
"acc_norm": 0.8121212121212121,
"acc_norm_stderr": 0.03050193405942914
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.8888888888888888,
"acc_stderr": 0.022390787638216773,
"acc_norm": 0.8888888888888888,
"acc_norm_stderr": 0.022390787638216773
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.927461139896373,
"acc_stderr": 0.018718998520678185,
"acc_norm": 0.927461139896373,
"acc_norm_stderr": 0.018718998520678185
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.7230769230769231,
"acc_stderr": 0.022688042352424994,
"acc_norm": 0.7230769230769231,
"acc_norm_stderr": 0.022688042352424994
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.3333333333333333,
"acc_stderr": 0.028742040903948492,
"acc_norm": 0.3333333333333333,
"acc_norm_stderr": 0.028742040903948492
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.8109243697478992,
"acc_stderr": 0.02543511943810537,
"acc_norm": 0.8109243697478992,
"acc_norm_stderr": 0.02543511943810537
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.4304635761589404,
"acc_stderr": 0.04042809961395634,
"acc_norm": 0.4304635761589404,
"acc_norm_stderr": 0.04042809961395634
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8862385321100917,
"acc_stderr": 0.0136136148002328,
"acc_norm": 0.8862385321100917,
"acc_norm_stderr": 0.0136136148002328
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5879629629629629,
"acc_stderr": 0.03356787758160831,
"acc_norm": 0.5879629629629629,
"acc_norm_stderr": 0.03356787758160831
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.9166666666666666,
"acc_stderr": 0.019398452135813895,
"acc_norm": 0.9166666666666666,
"acc_norm_stderr": 0.019398452135813895
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.8776371308016878,
"acc_stderr": 0.02133174182974679,
"acc_norm": 0.8776371308016878,
"acc_norm_stderr": 0.02133174182974679
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.8161434977578476,
"acc_stderr": 0.025998379092356513,
"acc_norm": 0.8161434977578476,
"acc_norm_stderr": 0.025998379092356513
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.8473282442748091,
"acc_stderr": 0.03154521672005472,
"acc_norm": 0.8473282442748091,
"acc_norm_stderr": 0.03154521672005472
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.8512396694214877,
"acc_stderr": 0.03248470083807194,
"acc_norm": 0.8512396694214877,
"acc_norm_stderr": 0.03248470083807194
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.8148148148148148,
"acc_stderr": 0.03755265865037181,
"acc_norm": 0.8148148148148148,
"acc_norm_stderr": 0.03755265865037181
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.803680981595092,
"acc_stderr": 0.031207970394709225,
"acc_norm": 0.803680981595092,
"acc_norm_stderr": 0.031207970394709225
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.48214285714285715,
"acc_stderr": 0.047427623612430116,
"acc_norm": 0.48214285714285715,
"acc_norm_stderr": 0.047427623612430116
},
"harness|hendrycksTest-management|5": {
"acc": 0.8446601941747572,
"acc_stderr": 0.03586594738573975,
"acc_norm": 0.8446601941747572,
"acc_norm_stderr": 0.03586594738573975
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8846153846153846,
"acc_stderr": 0.020930193185179333,
"acc_norm": 0.8846153846153846,
"acc_norm_stderr": 0.020930193185179333
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.72,
"acc_stderr": 0.045126085985421276,
"acc_norm": 0.72,
"acc_norm_stderr": 0.045126085985421276
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8620689655172413,
"acc_stderr": 0.012331009307795663,
"acc_norm": 0.8620689655172413,
"acc_norm_stderr": 0.012331009307795663
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7745664739884393,
"acc_stderr": 0.022497230190967558,
"acc_norm": 0.7745664739884393,
"acc_norm_stderr": 0.022497230190967558
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.5452513966480447,
"acc_stderr": 0.016653875777523995,
"acc_norm": 0.5452513966480447,
"acc_norm_stderr": 0.016653875777523995
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7581699346405228,
"acc_stderr": 0.024518195641879334,
"acc_norm": 0.7581699346405228,
"acc_norm_stderr": 0.024518195641879334
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7845659163987139,
"acc_stderr": 0.023350225475471442,
"acc_norm": 0.7845659163987139,
"acc_norm_stderr": 0.023350225475471442
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.8364197530864198,
"acc_stderr": 0.02058146613825712,
"acc_norm": 0.8364197530864198,
"acc_norm_stderr": 0.02058146613825712
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.5177304964539007,
"acc_stderr": 0.02980873964223777,
"acc_norm": 0.5177304964539007,
"acc_norm_stderr": 0.02980873964223777
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.5658409387222947,
"acc_stderr": 0.012659033237067253,
"acc_norm": 0.5658409387222947,
"acc_norm_stderr": 0.012659033237067253
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.7683823529411765,
"acc_stderr": 0.025626533803777562,
"acc_norm": 0.7683823529411765,
"acc_norm_stderr": 0.025626533803777562
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.7532679738562091,
"acc_stderr": 0.0174408203674025,
"acc_norm": 0.7532679738562091,
"acc_norm_stderr": 0.0174408203674025
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.7272727272727273,
"acc_stderr": 0.04265792110940588,
"acc_norm": 0.7272727272727273,
"acc_norm_stderr": 0.04265792110940588
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.8,
"acc_stderr": 0.02560737598657916,
"acc_norm": 0.8,
"acc_norm_stderr": 0.02560737598657916
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8955223880597015,
"acc_stderr": 0.021628920516700643,
"acc_norm": 0.8955223880597015,
"acc_norm_stderr": 0.021628920516700643
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.93,
"acc_stderr": 0.0256432399976243,
"acc_norm": 0.93,
"acc_norm_stderr": 0.0256432399976243
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5240963855421686,
"acc_stderr": 0.03887971849597264,
"acc_norm": 0.5240963855421686,
"acc_norm_stderr": 0.03887971849597264
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8654970760233918,
"acc_stderr": 0.026168221344662297,
"acc_norm": 0.8654970760233918,
"acc_norm_stderr": 0.026168221344662297
},
"harness|truthfulqa:mc|0": {
"mc1": 0.36964504283965727,
"mc1_stderr": 0.01689818070697388,
"mc2": 0.5360987678643523,
"mc2_stderr": 0.014938153988985473
},
"harness|winogrande|5": {
"acc": 0.8271507498026835,
"acc_stderr": 0.010626964529971855
},
"harness|gsm8k|5": {
"acc": 0.27369219105382864,
"acc_stderr": 0.012281003490963456
}
}
```
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__WizardLM-Math-70B-TIES-v0.1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |64.72|
|AI2 Reasoning Challenge (25-Shot)|68.52|
|HellaSwag (10-Shot) |86.87|
|MMLU (5-Shot) |69.24|
|TruthfulQA (0-shot) |53.61|
|Winogrande (5-shot) |82.72|
|GSM8k (5-shot) |27.37|
|