Path |
Digest |
Size |
evals/__init__.py |
sha256=7oUo37WQzvHsLhB4VEnibIkm6jbkz-4ec8txTN7yQE4
|
743 |
evals/api.py |
sha256=WAmyNL414UtwBD2mGBdjVMiK672k0cwigMYptZUYh2s
|
2965 |
evals/base.py |
sha256=ZUNdA-qPl5MhVss0dR3IyZTa1_QF5iIeZ6d9LTKaZH8
|
1900 |
evals/data.py |
sha256=RcxpX-MHnINAQLktJI7PzBVdjdwbcp-QhLlawPaZaaU
|
6080 |
evals/eval.py |
sha256=yeaFjgRY85tiemKbupgBj3uw0n10ayZzfmkNUd-AeOo
|
4941 |
evals/formatting.py |
sha256=XbSASxVJRum_yCW-V9UBS0qWzEksdVP7agpp2iDbArw
|
1137 |
evals/metrics.py |
sha256=5odum3XhHTn6hXLEcPxACvAVHvxe6hoAkZK_0nmgKa8
|
2559 |
evals/record.py |
sha256=-1T8uRNKEY3NmWd3XPaJfEG6gdX2Bn4QKhof6Ad6c2Q
|
22181 |
evals/registry.py |
sha256=f3HBeP-dK9MHHUDcBKJiHw1OZMs2zhH8aBeinIReJxA
|
10499 |
evals/registry_test.py |
sha256=jRaRfLS3YVTngdo1zaqjf6Q-m56b0x5JH-_slIGHjYk
|
883 |
evals/cli/oaieval.py |
sha256=HgyHuMvchKuGzDFWd-IUh8-mvkIMEbr1bepLadHdv2A
|
8966 |
evals/cli/oaievalset.py |
sha256=xzd8VkBw3ltnHQZ3bJMis6nEjHizL3MW73EyOHiL8a4
|
4280 |
evals/completion_fns/__init__.py |
sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU
|
0 |
evals/completion_fns/cot.py |
sha256=WpOy86QVfqSUcTfY0kAoGrM66Tu8sL5fpK3-jGYAPps
|
2678 |
evals/completion_fns/langchain_llm.py |
sha256=PSP46s1KcKjJAxKdMsOJCoMpOqqrcGh3e36T1Io40k8
|
3367 |
evals/completion_fns/langchain_math.py |
sha256=GrwAnvvvTgDYsnTpd0X94xA2tVz5enS2vA2sQdcrsT8
|
1068 |
evals/completion_fns/openai.py |
sha256=2mQgfhqupdrzXZwsBEn__-XkIKS6FcWr6ru2ifsngqo
|
4941 |
evals/completion_fns/retrieval.py |
sha256=2qDrJW5JR4e11LSHptHnF-5FmuDAb-O7gJMNE2qmdy4
|
4422 |
evals/elsuite/lambada.py |
sha256=lvN1rTIiisx10IzWzDY5KXAt8KUcG-XEAuHi4MkNPDY
|
1334 |
evals/elsuite/multiple_choice.py |
sha256=NMQqmdsxnMU_Ru_BOj2hao2yDowjz7j0UmiFBUIPxnQ
|
2641 |
evals/elsuite/translate.py |
sha256=-9qi_Hg63MWyKjvxEEzJriNRwgSUVR7szL1pqaFt4GQ
|
2682 |
evals/elsuite/utils.py |
sha256=jBN5dsKT9r0jpXDCpPD1O4_x5fNEbKELLQ4cJcE5kOc
|
6413 |
evals/elsuite/utils_test.py |
sha256=wijL19SzlwzO5WW91_R-0nkZC-ZRy44IMg9QhNnJEx8
|
784 |
evals/elsuite/basic/fuzzy_match.py |
sha256=wD5K3lOT52Vxw2sBZbHaOWe7utOQyw_Q2DqPYztqGiE
|
1986 |
evals/elsuite/basic/fuzzy_match_test.py |
sha256=05v0a0KuvqeG4o-m5PvSfxR8TprqiwziEwdC4mkuMMk
|
1538 |
evals/elsuite/basic/includes.py |
sha256=PFOE-jWwMDXQXm03ZxdhvtnbKi-aYrpmCLi1S5B_MUo
|
1823 |
evals/elsuite/basic/includes_test.py |
sha256=ASM_zmRQBmB-JYSpIBaoedw09TzOlUyaUyV5fVxyEms
|
1698 |
evals/elsuite/basic/json_validator.py |
sha256=mHD0eKAjpUX53ilB9qyqqX3rUidl-KdFL0b2WNNAwes
|
1397 |
evals/elsuite/basic/json_validator_test.py |
sha256=xhHj-K-6neqS40sSQ4LqCfJ4Gq4lpgfsAF-AhshggAc
|
1334 |
evals/elsuite/basic/match.py |
sha256=quwRjbgg0iJoOdYT5VKJJcCnqELsadbOUxjbqwD0XCE
|
2273 |
evals/elsuite/basic/match_test.py |
sha256=BZshSH9BDTOtP14LZaf8VwZswo34S9If9dkmoa3kBX4
|
2123 |
evals/elsuite/modelgraded/base.py |
sha256=NYhV7T2kdbFA56_uBjLw3XRbSe8nyLvcHn1UIRqYddQ
|
624 |
evals/elsuite/modelgraded/classify.py |
sha256=futWdDYf3-lrE-WLSIXEp1PkMLqZ-G1ToRdbMUZnDCo
|
4573 |
evals/elsuite/modelgraded/classify_utils.py |
sha256=tZhFQy4wmwHwPOEvtzBwg2-F5DnOdeJ6QhY7LQlJoFc
|
7590 |
evals/elsuite/test/match.py |
sha256=8bkTTPI1SAev5wHXd0A89Oq7-7oubgvvVAhotfW24OQ
|
780 |
evals/prompt/base.py |
sha256=z4IeAmJj4TwBH3M3qvNKDr5YXAeRV-1-bcrRwJMyRJk
|
4093 |
evals/registry/completion_fns/cot.yaml |
sha256=eGDwB6KiN6AxS4LwIA8ONfOioCZga1egxcDR1mxKLPU
|
391 |
evals/registry/completion_fns/langchain_chains.yaml |
sha256=Cm6VrHDIvQVqNg3Eh7ebOyMXC5N2nMIBSO-kmbmhJQk
|
103 |
evals/registry/completion_fns/langchain_llms.yaml |
sha256=KmL943C6UNCXfjE-2CY-8DhJJh8SCviy_548ZDQ2Isg
|
719 |
evals/registry/eval_sets/chinese-numbers.yaml |
sha256=gDiyYCN7X_rZmtH-TXXBmal5aqCCFs-V2tazIlCWyLg
|
201 |
evals/registry/eval_sets/coqa-ex.yaml |
sha256=kOyFu83Fh2VBrrD83AMT4AMgTTve5FG1wlNYS38csqg
|
141 |
evals/registry/eval_sets/css-selectors.yaml |
sha256=IwktpVcqPotOwZKs-uPnlwSZM-m7V4rQ-Bh_lkZC31o
|
78 |
evals/registry/eval_sets/logiqa-logical-reasoning-plus.yaml |
sha256=iXY6Sa8yf1UD4kESj4eziq5Q1NqTtQ9yYcBlnqDfSKk
|
150 |
evals/registry/eval_sets/manga-translation.yaml |
sha256=HrC10EPvVZv_2kSUVcZIpf3BuA8S_DiOnm_GwJTr4R8
|
119 |
evals/registry/eval_sets/mazes.yaml |
sha256=Vd6WrN4DCfN8KNFIZq_o9v9Eqd0zs9ggPBkJYKA2W8o
|
151 |
evals/registry/eval_sets/pointer-value-retrieval.yaml |
sha256=HU81uB0pFbdG7pNiaAyztN6C3MepVJ27GX-rz-AHLEU
|
329 |
evals/registry/eval_sets/raven-matrices.yaml |
sha256=UqT0EgTFkkgNFranko2ZKt2C3VnvO0h7qiQYXoPMj-Q
|
1652 |
evals/registry/eval_sets/stock-options.yaml |
sha256=yBJqN0dGruSdHHLJZnrcOhfDlz5O4O2wKZVz_dn560g
|
560 |
evals/registry/eval_sets/test-all.yaml |
sha256=jb65tfvToqqHVu9fECZ_XT334OKEnwYVOft5lKKVo0A
|
454 |
evals/registry/eval_sets/test-basic.yaml |
sha256=HMxZrJDF8Fdmi88QdZQCj-ZD_tbWSDUKDzAaCTCXC8U
|
113 |
evals/registry/eval_sets/test-modelgraded.yaml |
sha256=SVV6kEQ7LWZmECjugz5NM_VDmVwFEZKO0uFviEOHTUk
|
312 |
evals/registry/eval_sets/ukraine-gec.yaml |
sha256=vErhW0PQdRrNyWtk8_2vwrWlxnGhTGbZ7NH0E9ob2zQ
|
613 |
evals/registry/eval_sets/word-associations.yaml |
sha256=-kzg3KpCJ76ow4nIpeNyZUfYZs5HvLSIWzOiWtGApIg
|
189 |
evals/registry/evals/2d_movement.yaml |
sha256=5xZc5b6HGLIv4DS6K_wslJkYKRK7Sd4jK8HJMvy0IrU
|
284 |
evals/registry/evals/3d_globe_movement.yaml |
sha256=k4XnJBvQvh2KkXbnyeJJOBd7cBF7NFX-inDhC7iHllw
|
365 |
evals/registry/evals/3d_object_manipulation.yaml |
sha256=kTJPnY3pnxjTQP5svuMGzjojB5ynrWAWTIXc83_UsJw
|
386 |
evals/registry/evals/Chinese_character_riddles.yaml |
sha256=5hPKiSJnWjRUGisXVBbB6xeWzfZFuSjQyMOf32I-rNM
|
358 |
evals/registry/evals/GPT-model-text-detection.yaml |
sha256=tKg4jmc1hLZBr6CqinRfeo3uHn1bWchcYV01E6Yygd4
|
336 |
evals/registry/evals/Unfamiliar-Chinese-Character.yaml |
sha256=HTG-D0gBq3CrnrxDjmuUzm9eDWjdET3HprifANgO1KY
|
319 |
evals/registry/evals/aba-mrpc-true-false.yaml |
sha256=_ZCUqH1W9JQ0NlgVXwokEJgj8ZpfhdmltAxSdChk4Zw
|
215 |
evals/registry/evals/abstract-causal-reasoning.yaml |
sha256=bkertrXb8Qf8fwmC_riVhUw6s7qNURYcyxqYOJZKECI
|
863 |
evals/registry/evals/abstract2title.yaml |
sha256=3aBU6pyfnsASZ1EPSgzANlyC1PtzwH7en5kZyx9F6Do
|
469 |
evals/registry/evals/accounting_audit.yaml |
sha256=TTRJpPC45TGI0e_u4kELJeQwR4ChjY4bEPCgN4HHmO8
|
195 |
evals/registry/evals/actors-sequence.yaml |
sha256=4o29cUKQ1ntK1ynVab205f6dJ4nbtCPWgxMJdotGSkE
|
297 |
evals/registry/evals/adultery_state_laws.yaml |
sha256=HL5YJB7PuXh0ImtrSq5PhMFyuaKWFhD3qhKKo2DkMdc
|
351 |
evals/registry/evals/afrikaans-lexicon.yaml |
sha256=WjgDUyJumDZNL86rvvF4I0YqZ-ntH_NaJ5_yPPjtp-4
|
288 |
evals/registry/evals/aime_evaluation.yaml |
sha256=Yd9aFJHfedeMdJPms7AhNIfrNyVUfyPNp2pGhmHNGjY
|
286 |
evals/registry/evals/algebra-word-problems.yaml |
sha256=VdIXJEgkgR32E4miONd3dkwBXuNNIHHzCe8K58wTKLA
|
457 |
evals/registry/evals/allergen-information.yaml |
sha256=Cnb9Jpdj-qQ4Zg_FICsqUyvvdtN29A-UmAGqGUuavbg
|
418 |
evals/registry/evals/alternate-numeral-systems.yaml |
sha256=E6X3ham4vLeJ5i05nAGy6RL5U4Us1Kijj6QRfviTNXY
|
345 |
evals/registry/evals/ambiguous-sentences.yaml |
sha256=ozJ_VpMlF6IDq4I-RIzeqcGO7lKAyUvcejSW6WJPGo4
|
451 |
evals/registry/evals/anagrams.yaml |
sha256=lCnZNEHDZ-EJDEFPzFIbyD6UoWFjj5CTnkGWyDJ2kCU
|
229 |
evals/registry/evals/arc.yaml |
sha256=lS4iTw1LcYmCZPxYaRMUFoxgCB04c2nYhyNYUT-hneQ
|
143 |
evals/registry/evals/arithmetic-expression.yaml |
sha256=lXYJSPdSqqrtiRtTOjKPIszQilBKoby2aJgfXAJL73M
|
864 |
evals/registry/evals/arithmetical_puzzles.yaml |
sha256=l23_PDIloFOL4TS9Es5X4URw8p29kgI7n6g8NkD3WKU
|
330 |
evals/registry/evals/ascii-digit-recognition.yaml |
sha256=zQgi67H21q5-nyhatvPxPyijVSDLBIjyfVxmHCqm7oE
|
284 |
evals/registry/evals/ascii-wordart.yaml |
sha256=AZLx11-sq0Nub2RIyJCawUuq4hCZwSFMQluLjGS38v8
|
280 |
evals/registry/evals/asl-classifiers.yaml |
sha256=u3TCo54qfVsRfRoKooIzpjmFEHI5cab5YnG0eGcRh9g
|
281 |
evals/registry/evals/astro_eval.yaml |
sha256=3Fm4nylWPZVFjkRVzgSogahfUte9CVMGtOg7Glky63I
|
316 |
evals/registry/evals/atpl_exams.yaml |
sha256=PjetzkE4PdrHuvunXnJLe0Aw7kft98WENILx7-4jJ-s
|
171 |
evals/registry/evals/automata-and-complexity.yaml |
sha256=Q6UtKYsOomv6lxUwR4Fo_nVBGX4p1bLzD18Eo5-8ubc
|
350 |
evals/registry/evals/backgammon.yaml |
sha256=RtCMyTIiEG3wWiDI0Ku4MUak5k1w08U-KcyYu0s1D0Y
|
646 |
evals/registry/evals/balance-chemical-equation.yaml |
sha256=JUYOEqKVRE7s0TrT6v1HTC88T64FCM-nSKh1iPKrxWM
|
230 |
evals/registry/evals/banking77.yaml |
sha256=9UTQ8G1nrm3rb0t_sHb7NiTnlsU2wKr4TgDUcbbwkSk
|
196 |
evals/registry/evals/base64-decode.yaml |
sha256=edEyYzLygwDa1FoG5taxZEvoEaSgKG2dQnYjee-Qdbo
|
328 |
evals/registry/evals/beam-analysis.yaml |
sha256=qI7h5fSH_KqQvm9uQaSV_JH3m-3r81C1VqnhaqwAsOk
|
272 |
evals/registry/evals/belarusian-grammar.yaml |
sha256=Z-avBl1ogsDezJ7gnvoCKU5nyg7JDKSTw7rUxAPr_qI
|
332 |
evals/registry/evals/belarusian-lexicon.yaml |
sha256=4uSi5Ww0WEh2UbOEMSH_1Ee1XlT-GImixeznovUilYE
|
310 |
evals/registry/evals/belarusian-numerals.yaml |
sha256=6ajmHxK84PgFsJLDhg2Rim7xwD5jkcOxtINnH2qTsBw
|
290 |
evals/registry/evals/belarusian-orthography.yaml |
sha256=YaAJwZxTuhP6IbrxoEx-PslMZiYmaJmoIOjBgU8DrI0
|
327 |
evals/registry/evals/belarusian-proverbs.yaml |
sha256=A-z5rBngQ3qv54JD94KwBL1nR8Tunl9aYZJYz8-bFZg
|
292 |
evals/registry/evals/belarusian-rhyme.yaml |
sha256=pjw2TTPXRgR0xDaV0evQiXpreY-sn2ot98JisOf2B_0
|
283 |
evals/registry/evals/belarusian-russian-translation.yaml |
sha256=48fRNOugbGM_JTZlFr_F80G8EQ_ZHR_pzpameaC2ysc
|
361 |
evals/registry/evals/belarusian-syllable-count.yaml |
sha256=MixFjPxo8l0hzDBQgbIKbd33wS-5lqYaL2X96FmxNXs
|
311 |
evals/registry/evals/belarusian-synonyms.yaml |
sha256=mg3gz8-ozo8886_BxWxNctJjiHCk0Wukorzsy63VbYM
|
305 |
evals/registry/evals/belarusian-word-analogy-inflection.yaml |
sha256=Je9s7lwktzmRT0k2MV-6_6e0t-LxasXbLXiWREwyxaw
|
397 |
evals/registry/evals/benjaminmoore_to_hex.yaml |
sha256=k2hknzSH1vkZ6J7ZHeFYK08ikXDyBwZW5_L8ypvc0Ig
|
218 |
evals/registry/evals/bias_detection.yaml |
sha256=SpsE8M17AA6ih5TqzTRN0-wptb3OCe7M4rvAAE1VlL0
|
394 |
evals/registry/evals/bigrams.yaml |
sha256=HUYlZmKS9TjC93GyTIpUyhTSiVf_tXXutkzr0EMmkZk
|
159 |
evals/registry/evals/bitwise.yaml |
sha256=W9UpPIttZ0dV9R7TbPjwnytpTU2larrQQLnZD3EwT94
|
245 |
evals/registry/evals/blackfoot-numerals-modern.yaml |
sha256=0QNFT4GJamP5Kvreavv42w8mnogmAZ9_zN504ZlpwYs
|
366 |
evals/registry/evals/body-movement.yaml |
sha256=nlEjre06H21u93S_oHFAm1uYRTvlojYL1puWv25N3Iw
|
282 |
evals/registry/evals/born-first.yaml |
sha256=zL7RlHv7jflXma9RrHDQwvZPRDjXJAZc5RiHaH8RpxQ
|
246 |
evals/registry/evals/brazilian-lexicon.yaml |
sha256=hiSgYM7MlWOXX7BKzX7H-rhXb9wiD0j0y62RcJKSShY
|
288 |
evals/registry/evals/brazilian_laws.yaml |
sha256=ZwiorA3kDrgVEIm1RAT3QF2d9cPB9vQAD67MJqcAotA
|
269 |
evals/registry/evals/building_floorplan.yaml |
sha256=Jzt2ys0DPfVy2XyiCmkP3Ka7bF72Jf8MJqZRE1u-zsM
|
205 |
evals/registry/evals/bulgarian-lexicon.yaml |
sha256=UMpkdIdBPK0mBwfpRpk9D4dMvH1c26dCQ9TzduBy-FM
|
305 |
evals/registry/evals/canto_wu_pronunciation.yaml |
sha256=tcnhfq1hvs1abMpIJd5s9gs-RhHFLm2QGdODzUWCx7Q
|
333 |
evals/registry/evals/canto_wu_pronunciation_fewshot.yaml |
sha256=zGd6J2Qi5zf6uvdDTDvhi6ldZJw53jj7Hi6hi7ZTvTU
|
355 |
evals/registry/evals/cardinal-directions.yaml |
sha256=d1V5mwh88tYyeVtiAvuqepBb8UqLTvWGPmT2eYjyOvY
|
207 |
evals/registry/evals/categorize_with_distractors.yaml |
sha256=QrtPUEoKJBkR5v5FysenEo5uTCdKwd0g82SzjcsCj8k
|
573 |
evals/registry/evals/chess-piece-count.yaml |
sha256=6Mahpe1u23NIw9W3SH4ulhCWslD9WXcXc_Dn7nAkdt8
|
309 |
evals/registry/evals/chess.yaml |
sha256=cZlCJBQPAZAFdbRlAhyVjV0w8U9uXr8cualpsi0RS_k
|
230 |
evals/registry/evals/chinese-lantern-riddles.yaml |
sha256=xuPtMDW2Vya57TlCtnyAPJTogHw-DaLGde8aqnkQBg4
|
302 |
evals/registry/evals/chinese-remainder-theorem.yaml |
sha256=ddeZPhfbhj_yKNz0debthE8B2nqQRJN7Vgp-Yvia4aQ
|
346 |
evals/registry/evals/chinese_ancient_masterpieces_dynasty.yaml |
sha256=O2NzRX39qDxV7QkgaAOo1BpiM9q1OLdeF8mX5twP9lE
|
348 |
evals/registry/evals/chinese_ancient_poetry.yaml |
sha256=1HFecHae2BNVwwibh9sqJSrEuoLTpzdQ6Ew_lWOE5dE
|
324 |
evals/registry/evals/chinese_chu_ci.yaml |
sha256=0s1Hkz6BTlS2awh1d0FX4_efGUhenb2qjhckiray44c
|
256 |
evals/registry/evals/chinese_famous_novel.yaml |
sha256=5iEk0PqQ0tZ12TjkmDPkc77rq1tD7ot1jauEAZwc0G0
|
280 |
evals/registry/evals/chinese_hard_translations.yaml |
sha256=A68cXlFNiKOoKCX9_HQ7iAj8fu5Vwem6xXBw9BZYT8Q
|
338 |
evals/registry/evals/chinese_homonym.yaml |
sha256=TC5x7kLrqO2Xlb44z6qw9a0snRHj4SO_YvXbOZ26DLw
|
354 |
evals/registry/evals/chinese_homophonic.yaml |
sha256=qcBXsqwEevewNe41pr3J0gcc1uYW2Wmzhn0NwHVJwxQ
|
334 |
evals/registry/evals/chinese_idioms.yaml |
sha256=p_ycOf8dYHmmfvUw4TxiZJHMtRshLFH10uTlGm0YUi8
|
401 |
evals/registry/evals/chinese_modern_poem_identification.yaml |
sha256=D8f5nuvabD2uztzRz7M1N7PeTEmSTwoGUiswtOo3qN8
|
267 |
evals/registry/evals/chinese_poem.yaml |
sha256=CeWt-1_5YYQr0bW45UVI66j896qD6p-JDr-5zqoPv3Q
|
178 |
evals/registry/evals/chinese_shi_jing.yaml |
sha256=aRsYvMQny-7fDe-PnpJlOgAI7E7jQYaeI_6frrXIHVo
|
195 |
evals/registry/evals/chinese_song_ci.yaml |
sha256=zieF6aBnldTmJF-wAh0yHlpMIECgxUBme11hJKeLFSA
|
190 |
evals/registry/evals/chinese_tang_poetries.yaml |
sha256=IHGxrGTIWOcfkYP4siaNCahmd67fSi5-YeZMJOgaHmU
|
330 |
evals/registry/evals/chinese_zodiac.yaml |
sha256=cWXV7nELckY_FhiaRwmcUv8mmI8755rD7s_09uBM4L8
|
187 |
evals/registry/evals/cissp-study-questions.yaml |
sha256=_uV8i6ljRhlMI3ZOWv3PecVVnSlm6njMQDxtaLtVuv0
|
295 |
evals/registry/evals/co-sql.yaml |
sha256=aF7HYskA2mh3U5nFKeWxzzn2_lUg0wHLAotNgghbYB4
|
643 |
evals/registry/evals/code_combination.yaml |
sha256=BqjMIY749fyiVBJbzGPYBrpWTEuXw61xbBdY7oOHvhU
|
372 |
evals/registry/evals/code_progress.yaml |
sha256=U4fTtTgzaXv9vNVFitffuAGEGycPgOvK3eHKGABvGCc
|
382 |
evals/registry/evals/color_theory_complementary.yaml |
sha256=bDqrkULMUKetd54J4YtdH-O7G4ul-AaZ_HX9x6hC8LI
|
343 |
evals/registry/evals/compare-countries-area.yaml |
sha256=8yAFASQknGebNjJpsZcvcF7IzjsB3OXdjM9NTIZb4hU
|
308 |
evals/registry/evals/complex-analogies-en-ru.yaml |
sha256=uojDdV63HfRkq47nizBHGXDbZiClXxtRNf2IN-ZzWdc
|
223 |
evals/registry/evals/complex-replace-characters.yaml |
sha256=3IK6V6e_Mk0CVc7MeU8jca2MyrHbwOKT1QNJ3FK0FCs
|
250 |
evals/registry/evals/comprehensive-graph-reasoning.yaml |
sha256=rJzwC7zZr4bPwMh1raHA75uJjXzIERLFrxLedlFkQvI
|
423 |
evals/registry/evals/confusing_korean.yaml |
sha256=JuFk_LgJjx-447HPei1OY23UroPaXHqZu2gydpDrKFE
|
275 |
evals/registry/evals/connect-4.yaml |
sha256=ah0jeU9zuhTh0jowaUCAVTXmbqkiqbKUZc2byS51jQI
|
160 |
evals/registry/evals/consensus_summary.yaml |
sha256=_9-4vGTQO3eIfof2lscP7aKkIUueuF1-X0CWAeBJ7xA
|
379 |
evals/registry/evals/context-free-grammar.yaml |
sha256=oz5sCC4TUy29Ce522peWW3tAFhzMr09F0CSv8TFrTi4
|
288 |
evals/registry/evals/convert-hex-hsl-lightness.yaml |
sha256=QTDxs9RgnV38-3Fa-COYQmcNh8ALnJR-zRYASE3DH3U
|
335 |
evals/registry/evals/convert_bwt_num_and_chinese_num.yaml |
sha256=-MevBZFOMvX5JHu-b48HCt_bNgLz4G1yM3i-OKysHrs
|
1594 |
evals/registry/evals/coq-editing.yaml |
sha256=EF_4Tx_htEqi90OT3-4woniR7Akd4bkQYov_tMyLDGc
|
787 |
evals/registry/evals/coq-proof-step.yaml |
sha256=JAbyhQIwrX-46osN1DO4Saw_iTAjINKB8CJluKfZgLU
|
453 |
evals/registry/evals/coqa-ex.yaml |
sha256=eo-VpJTBrR5ivsIn8sWTy4601mzUgNtkCZoL2OrKb6o
|
1719 |
evals/registry/evals/corr2cause.yaml |
sha256=BORU7UdxO-L4YblfviVBC7yOwW_cyValiMIkIf8tcro
|
328 |
evals/registry/evals/count_intersections_polynomial.yaml |
sha256=Z6o8K4XuH2AF-QXBHWROw-OyHtBQ2SwdgzE5wbPT9Uw
|
435 |
evals/registry/evals/count_token_freq_dna.yaml |
sha256=vyXgaN0y_BEI8bUv-6fi1Y4_WQE-nPmwpGstMxWigw4
|
349 |
evals/registry/evals/counterfactual-reasoning.yaml |
sha256=AlfD2ZxBx6_wYmCOpPfQtEFJssFss22y2CCDaMHqkhc
|
387 |
evals/registry/evals/countries.yaml |
sha256=V24O30XqnoDtfs9Mc6xBW79CvNUKrW1_N9zmPxhqjgo
|
166 |
evals/registry/evals/crepe.yaml |
sha256=EYmAW3HRbdgWbuUC5CvIHXdzEefOGX3bm6gqbwCEcao
|
151 |
evals/registry/evals/cricket_situations.yaml |
sha256=Adg2KXQmWOjdQOTr02FfhkpjeGLdv69ewH9O5IIJRtg
|
301 |
evals/registry/evals/crontab.yaml |
sha256=UY8lKH0wamS7AQ6rBT1i250E1uDDZugkNIcFrwX1qlQ
|
158 |
evals/registry/evals/csharp-linq.yaml |
sha256=ORAeFzQvW7fH4za_q8l8anNvg4s5ne3IUcda3AuCWbQ
|
270 |
evals/registry/evals/css-selectors.yaml |
sha256=zbZjaYyiHUg70imPZFGsUBvMM-mmy_gozSsKnaiPEUE
|
579 |
evals/registry/evals/cube-pack.yaml |
sha256=s0q3fah1Me30IB5gnrhxacBMlgyQqhHJJXFYavTUd4o
|
167 |
evals/registry/evals/cybersecurity-filepaths.yaml |
sha256=36BU1XkMUmN2glhycDamob1UrQ3hEHpGV48X2vTqAIM
|
553 |
evals/registry/evals/date-booking.yaml |
sha256=5s8kGT9SGHe2iC1DLsIHjH1tiJCjiOTE4iFd-WzVP7w
|
179 |
evals/registry/evals/date-calculator.yaml |
sha256=y9OL67eOlLttm8LRYviY-eYLXls3q25CscqH76C8aAY
|
192 |
evals/registry/evals/day-of-week-from-date.yaml |
sha256=z_L6BcWY6In6dctnhFeg--Tw9d1GB12ZbZBc5woUIpM
|
214 |
evals/registry/evals/decrypt-caesar-cipher.yaml |
sha256=BUlG1ZpALPTD94hvQTGtPDXoNjWCwHWpstLJ_7y6O5Q
|
214 |
evals/registry/evals/detect-hshd.yaml |
sha256=wOYcODdXtcaY443aNYllBcumxsJ2SNDvQKDUde2-2bI
|
189 |
evals/registry/evals/determinant.yaml |
sha256=pqk4MlDRmrIdBTmrx4ANpjtI-LyWD73j4neV_fgotDo
|
175 |
evals/registry/evals/dhammapada-reference.yaml |
sha256=J0vet6JXTs1L8yjeSd3KzGgeHmrk-P90k2xi5vU3cLE
|
345 |
evals/registry/evals/diabetes.yaml |
sha256=yUakVSb2l41ZM2n04NFFjQdVnNcqYz4ZK82uM1xOo4A
|
163 |
evals/registry/evals/diagrammatic_logic.yaml |
sha256=vMex2id5tmcOsTkza3o2Lf3xHiMo47xbgQG__QYEQEo
|
202 |
evals/registry/evals/dice-rotation-sequence.yaml |
sha256=gl-DEn9uUFRQUIfoVRKsXL1LsRIO0Oib5GSqP44rRok
|
377 |
evals/registry/evals/direct-speech-tag.yaml |
sha256=QP0RKh-U68fjc0HdiqpeI58LJyCNoEbnYbswIJc03pA
|
199 |
evals/registry/evals/directions.yaml |
sha256=DBbJvr65KEQacSbnjMmWEhlxi2emEHUoazUG1GgvcVo
|
276 |
evals/registry/evals/dna-melting-calculation.yaml |
sha256=iTepd6wnxcVKrM2UOIWB89d_W1inwQjvowFM2Zkyipk
|
316 |
evals/registry/evals/dutch-lexicon.yaml |
sha256=8j3LZLwB837v1FRCqZycXSLkajLN1pIJjVmQE-dvTVs
|
306 |
evals/registry/evals/dutch-rhymes.yaml |
sha256=TpqjG1mBnn6B142FeNFXpiINlpDD1RNw4dIzuykttPY
|
244 |
evals/registry/evals/emoji-riddle.yaml |
sha256=KVeqtWzWHNMthqXderhK4Mzl4bbiyG43bejybpc3IOQ
|
269 |
evals/registry/evals/emotional-intelligence.yaml |
sha256=vvenROXWERbItVcAG8enrGS2LcI5LjWFih7Z6LydWpA
|
387 |
evals/registry/evals/escher-sentences.yaml |
sha256=wYNZaOlV8wj9s0aFsMCI6XMVmbnjVso9Xtsl9BJIjT0
|
195 |
evals/registry/evals/euler_problems.yaml |
sha256=EvyvYAkYiMUj-Uo_OzqcZKZnEgAot8_9sSMxhLAxygo
|
669 |
evals/registry/evals/european-date-format-challenge.yaml |
sha256=QoPRoLwuPbxkJX-H-HGY856cK5nI6Q590rWMocgOFaI
|
497 |
evals/registry/evals/event-categories.yaml |
sha256=kYTPrjyOY-PXq2FvDprMJBdt5dlX4_iI9Ty1N0-dWwo
|
350 |
evals/registry/evals/fcc_amateur_extra.yaml |
sha256=-t3Yi22-CuZ7GmVIwRXQe4PDodx9yq8zL38h3LeXMdo
|
314 |
evals/registry/evals/finance.yaml |
sha256=awAtEEAqTEkCQZOGlf1lfGumUwi3Buy3zMuZrM1nYko
|
254 |
evals/registry/evals/finance_calc.yaml |
sha256=U0SfZLydWOcv7VNE_XqYJe3AwIi17bAq9eZeKKLGkUc
|
277 |
evals/registry/evals/financial-derivatives.yaml |
sha256=NfUf5VIMMy4IVWTQhJV8wuNda4aK6jpBWBRgdZ9ctk8
|
311 |
evals/registry/evals/find-letter.yaml |
sha256=p92BKLOf2nQOMbRHfYqowvJfskeXILUoB2cQG0XSPuM
|
181 |
evals/registry/evals/find-thirukkural.yaml |
sha256=GcIhyLyWNJFUv8c5GkxAR6pn76ea5nyzgCNFHWwp6cs
|
303 |
evals/registry/evals/find_country_from_svg.yaml |
sha256=6u3_T1ncV2gDPTsnO58SR8Nc5AGIXH1zkqo1hBPL8ZE
|
336 |
evals/registry/evals/finger-tracking.yaml |
sha256=jlkoOI-ryrkpPUTkhJSUbUCCwL_32hoZXL1P-k-zg6s
|
276 |
evals/registry/evals/finnish-rhyme.yaml |
sha256=zeFD59r3VcBGa8p3YBvfB8a9wqpqSGILrRgGmkrTwPY
|
262 |
evals/registry/evals/first-letters.yaml |
sha256=zzmk6jkpLNt348PaAV5jAT4-BQgcgHj8BRpZqa4EB3U
|
183 |
evals/registry/evals/food.yaml |
sha256=eBSDFlSEe4NnByaMRYhVAylxr3e81YIP9igpUqsPDsY
|
147 |
evals/registry/evals/formal-grammar-to-regex.yaml |
sha256=yrPTBhhR_2TxRT36CvcL1d-4ai5HSXn5z5RSvLQS44M
|
245 |
evals/registry/evals/formal_logic.yaml |
sha256=qj40MTn1oe0ddxSkxHZh2yxAuT_0s8Mzok-hIrUNmI8
|
276 |
evals/registry/evals/forth-stack-sim.yaml |
sha256=sB_xETrsKGOqONCYC6gAmlkTCHyN_7_uEXFWOmLmD6I
|
928 |
evals/registry/evals/french-lexicon.yaml |
sha256=y9JoP1Bm0LpREsgP3qy1lk99-SNSDNTfIgb6G9YMrHI
|
273 |
evals/registry/evals/french-part-of-speech.yaml |
sha256=VMDaTc5Wq94Sxb0ACYkvxYthg-G05JSkgTwtLVUX-gQ
|
361 |
evals/registry/evals/french_homonym_and_homograph.yaml |
sha256=lwEu4QW6bP8cAS7S8G4EnLbsCGffaAiE3gSnakxkU6c
|
537 |
evals/registry/evals/game-theory.yaml |
sha256=e5HM7TUbSr6iVKrSZrSvXGoDcJ9JBEjq6yPIwneTUso
|
289 |
evals/registry/evals/gears_rotation.yaml |
sha256=NiyTaP8SmhI38wkGEB_r07SwDa1NFVxoCLXBAz73VMA
|
338 |
evals/registry/evals/geometry_puzzle.yaml |
sha256=-Kw3HIkY1s2fq6dF8kGay_4WfDSXq2HNxps1hnYcAEU
|
345 |
evals/registry/evals/german-part-of-speech.yaml |
sha256=pwg2Vsx80-ieMjpuHZt7dQAe4EZoqxEVZF95cim7RPA
|
361 |
evals/registry/evals/gol.yaml |
sha256=dutW4ObZMmbIcHlLFTcLI6vJ5HYAXx3e_T-YQUe7p3Q
|
254 |
evals/registry/evals/gpt-protocol-buffers.yaml |
sha256=f_DXS7fSFQdCciSKFtm7Lp2dRDtCPED6rprQgyhzOsE
|
217 |
evals/registry/evals/greek-nt-manuscripts.yaml |
sha256=9CkHQ8GYvtbIRiBEExOXDd92K2Ud08CaEcX849Yu8QQ
|
404 |
evals/registry/evals/greek-vocabulary.yaml |
sha256=Hkg3lYh3TONOY1evPqz6NP8CoAHgNKKOT9YDaPeY6YI
|
194 |
evals/registry/evals/gregorian-to-hebrew-date.yaml |
sha256=Xig6P97l9dTe0-U7_fM_umfOGmbMbuXT7SmKKStaMRg
|
334 |
evals/registry/evals/guess-the-singer.yaml |
sha256=W-D-_eFQ73_ArHM6uHRihBXxcxpouDWligKV8UwWjlg
|
292 |
evals/registry/evals/heart-disease.yaml |
sha256=vtg4-PDKRyKAjqKZMwz3ELwidw76bLdC1TPBOIWH35I
|
258 |
evals/registry/evals/hebrew-bible.yaml |
sha256=TKN0i6etbTSO1mccdNQlWvexqCWpRlMAa6q2qqv08U4
|
315 |
evals/registry/evals/hebrew-homophones.yaml |
sha256=65U6Jhc--hC5X5w3Onih6ujZcAVcAji_bDZ3xN3UtEc
|
283 |
evals/registry/evals/hebrew-rhyme.yaml |
sha256=MIMif2NKAV0NLoUsWiwLxqbn7aRTxntu_9xdfwKlzmA
|
250 |
evals/registry/evals/hebrew-same-noun-gender.yaml |
sha256=_4_33PUeiI1AAT8ky5IEWkVXLd_c5GBKR6Y0k7JlRPc
|
285 |
evals/registry/evals/hebrew_grammar.yaml |
sha256=VhOr8IpXb1FUaaKlpDNP2aU9eM74cJxNE9ke4Uw_nA0
|
264 |
evals/registry/evals/hebrew_plurals.yaml |
sha256=MQSNbU88ymfjhXj0G48eqv_kldVCkpT9hT3vEOijmBQ
|
269 |
evals/registry/evals/hebrew_talmud_suka.yaml |
sha256=KD0yoq80cD-8xjorYri8fJaryQYY5xqGrIavJITMapg
|
339 |
evals/registry/evals/hindi_shuddha.yaml |
sha256=iV8b9HC1LCim-ldDeuwltXWq6yEWnQFRojKUDYSOUFM
|
183 |
evals/registry/evals/hindi_upsc.yaml |
sha256=YCcpnzrcGvb-PC_4K2FyXhiTMgrTj2iwMpbiwvVH_Gg
|
170 |
evals/registry/evals/hindi_words.yaml |
sha256=6ZdOWJziVxFJfCbew3-lgRs1v8VDMZa9rpekhIpq4jQ
|
175 |
evals/registry/evals/historical-kana-orthography-reading.yaml |
sha256=aVbRgHpXKcDDJp4PhsveTWSqF3ljKdZFGCKNVEiK270
|
351 |
evals/registry/evals/human-safety.yaml |
sha256=sq7LX3AChGyzVgA-H3aZhJB4nEd3iQA88I7CJ7_IHeU
|
313 |
evals/registry/evals/iambic-pentameter.yaml |
sha256=Sq2WjWQpXAk_6r388WWxi4xyArQWQF0Bs-co2MAchE4
|
307 |
evals/registry/evals/illinois-law.yaml |
sha256=VjSHfp4uxMQhbH8vM0ZdnAss1zItckBWQMyhyyJ1l2k
|
265 |
evals/registry/evals/imperial_date_to_string.yaml |
sha256=stjZipZ-jUTM24g6uMH8dPPHGqGemAi92C4dl_j_YUI
|
222 |
evals/registry/evals/indonesian_numbers.yaml |
sha256=-BEdKexO6Hm6DRq9xrxhYskL_3o_S2GIWEBKbrP4znY
|
213 |
evals/registry/evals/infiniteloop-match.yaml |
sha256=Ue8fjK8svQRLldmqZtdhc_85tVqHPl7Wx54d8eGt_lw
|
347 |
evals/registry/evals/integer-sequence-predictions.yaml |
sha256=dVgPXb4uZhvfp8QWvDHFW-9MqzVVzbTi9WU-szqz3Kw
|
1113 |
evals/registry/evals/interlingual-homograph.yaml |
sha256=BiUY_z_n4NX5cJ3TFLImFwkUMcfh3LccgBXNwyr0p0w
|
339 |
evals/registry/evals/internal_representations.yaml |
sha256=FfOjuHOa2Ky0RzKdTlpOOz6CpZ06BQYca9VuINihpMw
|
235 |
evals/registry/evals/invert_word_wise.yaml |
sha256=WvPCNy5Sx8NATvn3MFLTJSsjFZ21c3RhnF_IqgB8tE4
|
390 |
evals/registry/evals/invoice_due_date_leap_day_adjustment.yaml |
sha256=JlOsHBdgXW6mnEl0C0GEBwmm6nB7UpfMeHzt8mULKVc
|
275 |
evals/registry/evals/invoices.yaml |
sha256=htfOfjzin0CNT1puNMh9Z-KinTvejmLG7PPeR8ADixE
|
262 |
evals/registry/evals/iqbal-poetry-translation.yaml |
sha256=q_jW9gQ3Pon99dweHGkYZnFQV4vTV2VNJywSUDMwkj0
|
1021 |
evals/registry/evals/irish-lexicon.yaml |
sha256=px99Gw_jMDgIm_DmpBss6KtwSbfBEU1Ooqx25_SvFcE
|
285 |
evals/registry/evals/irish-plural-nouns.yaml |
sha256=1Pjk5IHI9RA-BxbvGcZoD6Au647H80IMFYL1CokRDos
|
308 |
evals/registry/evals/irony.yaml |
sha256=cTB-grtsYqN2o75aTIurBPKrGK9sk5pjNVukQiCONyw
|
258 |
evals/registry/evals/irrelevant-negative-diversion.yaml |
sha256=8d8rNXj07xje0rbkOxvRktT7y2ua0RER1xei3oavWNg
|
402 |
evals/registry/evals/islands.yaml |
sha256=3q4WFbSf6FONVBrcak2ovwCB9U4d0cxFfIKzTBC-LqY
|
370 |
evals/registry/evals/isosceles-right-triangle.yaml |
sha256=Q79wjBCOTlIyY-Wh108vn5bzPFeuCV1N5SjbuxcsKfc
|
233 |
evals/registry/evals/italian-new-words.yaml |
sha256=o_wyyXpegUUtQ0pfv9G0M-IyXpYSrtxujXOFPWjuhY0
|
308 |
evals/registry/evals/italian-rhyme.yaml |
sha256=a-86a65RvL9ZIhvVclM8cm-WfdJKHXgKpNF5kLnuT2s
|
254 |
evals/registry/evals/italian_big_math_expression.yaml |
sha256=3mGzDm6mx1wo-KkDs6MLMpT3qlS_hLmWcgReuljoEtw
|
422 |
evals/registry/evals/japanese-decimal-units.yaml |
sha256=zHzrBfZUI5dDc0DpM9LgIxqQMx7o9uF-vY0ktf-mwu4
|
279 |
evals/registry/evals/japanese-itpassport-exam01.yaml |
sha256=6WTl1g43tP2DbSc3fN7Y9UeyUvxIqcYbYpZ4SvNexlA
|
428 |
evals/registry/evals/japanese-national-medical-exam01.yaml |
sha256=CTVxj-krMG6izCaB-Dw93tO4k4RmgzjhbzKqQDm9q5s
|
292 |
evals/registry/evals/japanese-national-medical-exam02.yaml |
sha256=25Nln1_WCaWY2qS2I9NIAG5rFHIxiHUOPtmmsXx2Mfk
|
292 |
evals/registry/evals/japanese-station.yaml |
sha256=9zj1dt-6SdjpRARYNPcKDXqRkcquZ9JY6dYemAwvZ2Q
|
203 |
evals/registry/evals/japanese_approval.yaml |
sha256=5Y96SM_-zOiJPMts9jDCiKnTAxJa5R3X9lrG5uhtsso
|
319 |
evals/registry/evals/japanese_city_name_pronuciation.yaml |
sha256=TuqD6fOvUTjOywNZnGaZ-gJfQhIfSJfNxc22yk03Nms
|
399 |
evals/registry/evals/japanese_driving_license.yaml |
sha256=s91j3Xr1CmyQeMIK9I2E-3sE3C5BfUtQGtaP1cmdezw
|
329 |
evals/registry/evals/japanese_mahjong_discard_tile.yaml |
sha256=fkpUZWr_aTRSMVX4ge0t3q95UhGypiouQeEG1-rU4po
|
381 |
evals/registry/evals/japanese_number_reading.yaml |
sha256=P-_LsB7d8sEmTx1TqDo9Gnecs_6CpkZPwN3RccUbmd8
|
338 |
evals/registry/evals/japanese_onomatopoeia.yaml |
sha256=Q-jzXEssrxfJw_ggJy0tA9qr4iCwD23wZJ6EXHkTe1U
|
300 |
evals/registry/evals/japanese_populer_video_game_title_and_the_publisher.yaml |
sha256=8ZI_UvbHsvkq52XbI7Ndr-14LmkFA0Dvh-zMc3NlmZY
|
448 |
evals/registry/evals/japanese_romantic_context.yaml |
sha256=_b7ASDtgtALnYQnR82m3_ngi91WoV0MDubg__MizdL8
|
237 |
evals/registry/evals/jee-math.yaml |
sha256=NU9SV56MqGAcFCLbWkNG4ycujbvFhEqI0S4YY9Cs9t0
|
169 |
evals/registry/evals/job_listing_title_for_a_caregiver_in_japan.yaml |
sha256=QnUOYjn01vXeVu-aeSMpmjZU9TQ3KbwRSxjPNX4aHv0
|
382 |
evals/registry/evals/json_patch_object.yaml |
sha256=d6K9R6X1tgILrSNGXx_l9QgJjefj046X5DBKzBLySVU
|
305 |
evals/registry/evals/kanji-idioms.yaml |
sha256=stmQWbP5EZcL3LWbfN2euy40zDrtG_ZZ8FfJ9nxvsjI
|
248 |
evals/registry/evals/knot-theory.yaml |
sha256=rT09edvnlCf7dY99rS7A2bGhI5diAX6ie7rE2F4phmY
|
754 |
evals/registry/evals/korean-consonant-vowel-combination.yaml |
sha256=7G9MVKmq4CV6qEkAR3p1MKIWhsJGaO_7b1FPkw5KeR8
|
390 |
evals/registry/evals/korean-honorific.yaml |
sha256=z42vLi7yT-ydzD-q97qT3Co25UpWfmkEMFSUTtCVHto
|
281 |
evals/registry/evals/korean-phonetics.yaml |
sha256=E2_pyItq5sOZxT0KimYTa-Bf_pQB1Eg0FzH6HSPAaAs
|
284 |
evals/registry/evals/korean-postposition.yaml |
sha256=aYBonSiKAu2sU0JcVGMeEONhEmlqfS7KqwaSa6IOi0k
|
291 |
evals/registry/evals/korean_date_counting.yaml |
sha256=Pt8JRXa3KMpYXsQL1dKuDY95Vx9wtCWcVgm2zvlwj3I
|
284 |
evals/registry/evals/korean_dialects.yaml |
sha256=_QKoG0iItBwYLukBQRKTS_GPDW6jIpnfQxAe3K4Qhs0
|
293 |
evals/registry/evals/korean_foreign_words.yaml |
sha256=5fUa5h_O13HSH0PRqT_1_ciU0697xHngiMhpSi6iwbw
|
276 |
evals/registry/evals/korean_romanization.yaml |
sha256=OjHSKDoPwNrjJPQfty_t10PJdOscuL_en2nxvYH0Vnw
|
471 |
evals/registry/evals/korean_spelling.yaml |
sha256=iQOBN0-WQomMxK6KmINJYSL3IgJmiXRhX_Bailxulds
|
191 |
evals/registry/evals/korean_yaminjeongeum.yaml |
sha256=7Zf1_dR-YQrDODDLtGOF_RR7ZpKcAvc6f-IwNxQH3t4
|
324 |
evals/registry/evals/language.yaml |
sha256=sPKh7Tmhxx7n3TtLrNqXCMKiIK1qIhgbCVhTAmQWBGY
|
400 |
evals/registry/evals/largest_country.yaml |
sha256=dICu1nvnjBAbMFiPhQmPZxjo5rXsU7L8ND_5D5rhAwI
|
275 |
evals/registry/evals/last-word-nth.yaml |
sha256=eBAn9nGT8J7NcL9WNVyy9K1CLo0TcVXunsQ2-KIBPzM
|
327 |
evals/registry/evals/lat_long_identify.yaml |
sha256=q5U0534OSm0s_G8-IkDJBK9p2pph_8LENPktMqQusbY
|
198 |
evals/registry/evals/latin_grammar.yaml |
sha256=N8eXEkYuI3jYq0nuQ582Pqtas41hbwgoaLKt-cHPs4w
|
307 |
evals/registry/evals/linear-equations.yaml |
sha256=bPYC1TwMxUJ78E1DfxC2C0-MQOn6VvVlWLB_-yCzQ0k
|
194 |
evals/registry/evals/linear-regression.yaml |
sha256=UHALeB0PTX5JNsCRi8QHzfbhn90hkAxtE1lmy4kmRUQ
|
802 |
evals/registry/evals/list_comparison_missing_name.yaml |
sha256=M8VmOkt3X2oTswHBOWrzAFngVtesTOiBJ9XrpGlZu5I
|
458 |
evals/registry/evals/logic-container.yaml |
sha256=gxtuiHWA8jp4fR1fiBB-jybwR6v3Ff0VRA_VZT7D8lk
|
374 |
evals/registry/evals/logic-grid-eval.yaml |
sha256=kmr9dNXvNFFWsNblOeJ49haXUTATrcE70A13gIzwfmw
|
814 |
evals/registry/evals/logic-liar-paradox.yaml |
sha256=tt3DxsOTTbohvf_x46MFCRol-DpGghJWmMCo9H9M08g
|
456 |
evals/registry/evals/logic-riddles.yaml |
sha256=4KGCd4iHmH8QX45geEEfNIJnIvyEH4spf7IKD7i-X1I
|
259 |
evals/registry/evals/logic-statements.yaml |
sha256=dr_K9Ii6A3mwScPa0t23IuWhxGqa8rFmsUoWs5iNJOY
|
214 |
evals/registry/evals/logic.yaml |
sha256=nA67Ix-JbTYzKoX2yIwNNOCvI_Sby5o-IHUCaADCW_Y
|
242 |
evals/registry/evals/logic_and_probability.yaml |
sha256=uSHDKb0jNGpkQ-aBaZIbdt1KqmB9Gz-lJ1FjxkkuzlM
|
322 |
evals/registry/evals/logical-black-scholes.yaml |
sha256=uj89NDRaSWJ8XtFP7EpCOZ_HNa6Mz4kjwjJYdSDXWdE
|
350 |
evals/registry/evals/logical_counting.yaml |
sha256=e7HKH91RfIUPSBTQ_JBCx2wKHnK44QE0G-H-X7qyeG0
|
194 |
evals/registry/evals/logical_reasoning_letter_series_test.yaml |
sha256=cJ025tr46I7ax79YOrDSNVk9fCOAVKRwQ1hvUHkWMto
|
435 |
evals/registry/evals/logiqa-logical-reasoning-plus.yaml |
sha256=eOj6RqFCiTbsqbSLS3MGksxy9Y7nfwtTUgEd_yhYciw
|
1041 |
evals/registry/evals/logiqa.yaml |
sha256=elwmRJ9P0nNcqR03NUX-xclazK9HPMbVDdtbdCessXc
|
153 |
evals/registry/evals/loss-logic.yaml |
sha256=lpAFT3DKqyxTe_07EjcTayPwZlpZnkseJmPVXajZ2Dc
|
262 |
evals/registry/evals/lunar-calendar.yaml |
sha256=vhxT6KNYINsxvidVJK6KQWiQpM80arF7WEGTN0Nv32I
|
919 |
evals/registry/evals/mandaliof-table.yaml |
sha256=LnEjCXtOjqWUfY2dxbpC-_qnUCr5fjxDLVu2BWKBmis
|
286 |
evals/registry/evals/manga-translation.yaml |
sha256=Mpvb6qUm8Fexyd4j7857yxWNkvnrnTx9L1ULRZ8vaKg
|
674 |
evals/registry/evals/map-electronic-component-part-to-fact.yaml |
sha256=bET5NPeVm69wsK31_dmFJVamTbFIHl7f3w6sKsag7BI
|
278 |
evals/registry/evals/mapping_to_matricies.yaml |
sha256=qI5T9dO-6I9OYpq_m9B-DIAWtdY2Ofli2QI7d6Ch3CI
|
217 |
evals/registry/evals/marxist_philosophy_exam.yaml |
sha256=Dp_QtPsVMc0qy7S3J0I75-0tza_NXUier8hNPwtnoek
|
333 |
evals/registry/evals/mate-in-one.yaml |
sha256=N_g7bsQOyVs1GWhcQjPPtPdF1F-WU7gxFqI6yIPdba8
|
243 |
evals/registry/evals/math-derivatives.yaml |
sha256=B8SkbxHzVFOR9vmC2SD62_s0nOE9dtm5jmFvY4N57jU
|
284 |
evals/registry/evals/math_equations.yaml |
sha256=P5_5RCumAbozJWAvay6HciikPFJ6Si5HX41alrXOeA0
|
292 |
evals/registry/evals/math_for_5th-grader.yaml |
sha256=MBeRekIn0eM8rSy_feqld76iDxNDtzJ_xRBuqWeri_c
|
334 |
evals/registry/evals/math_logic_operations.yaml |
sha256=hljXVGrnuCslk0qLctOEIxQrWbK_g1kGvF0MabIHCNw
|
354 |
evals/registry/evals/math_polish.yaml |
sha256=MGA20l2Z_NWMHUR8qQ9kdge8KIxHmB3Bz_kD8kHIO6M
|
312 |
evals/registry/evals/matrix-mult-rows.yaml |
sha256=OH3SDFjP4Xe9QVwq3Pk_e1f4SMPsGUpBrVNcBgE_LyQ
|
297 |
evals/registry/evals/mazes.yaml |
sha256=pf2kz1KvbfxN-gLVziI34wPmuuc2KXVu4vfFfv61mNw
|
1768 |
evals/registry/evals/medication_dose.yaml |
sha256=ujPR5PPV89Wy89SC_4vOmynoiaDSW0WxG5yLr7UabBU
|
318 |
evals/registry/evals/medmcqa.yaml |
sha256=sOotmRHe761Tf1RPYewTYdPWny-X2NYLiMggbmJJK-g
|
159 |
evals/registry/evals/mendelian_inheritance.yaml |
sha256=Lp4CH4ObwJjbSgFBjXMZKVxFwK4STGn7A-CjhsPEVLE
|
215 |
evals/registry/evals/missing-operators.yaml |
sha256=TmscS-PBZsaCetqwOoi3pIrW3srLuffqMjgJREOymJE
|
337 |
evals/registry/evals/mmlu.yaml |
sha256=b85wp6rktF5MNrrakGm8s_LOtUC9FW-FrG0kMguThl4
|
14586 |
evals/registry/evals/monthly_metric_comparison.yaml |
sha256=SjS1YvXkPpy9dvlkmJnOtHJBs81lUrYr6T-wkUFxAh0
|
313 |
evals/registry/evals/moral_exceptQA.yaml |
sha256=t8dURhF5kcrjn_24Z59vkoNl7PbqPu-D6dfHVuXMSeo
|
329 |
evals/registry/evals/multi-step-equations.yaml |
sha256=Mf22N3XHaQuY2T4Mb0geGO4kzgaFB-RxSKzh49dm-zo
|
211 |
evals/registry/evals/multistep-word-problems.yaml |
sha256=ad7F14h21XiAiBuaIs2IfbVM3JzJD89ReU-or4rLVls
|
310 |
evals/registry/evals/music-theory-chord-names.yaml |
sha256=UooSOy0SKnkx7GJTca1AK5pP_2vaDvdVdEfgjAkNYRk
|
315 |
evals/registry/evals/music-theory-chord-notes.yaml |
sha256=3DHEagLI4GYGl2oejIs3NHSTooQFKr56Z0NWRvuyRdc
|
315 |
evals/registry/evals/music-theory.yaml |
sha256=rPK6ysJg5FZpLsCYZUbxX79TrfPM-AYXcAZcKWZbk9I
|
874 |
evals/registry/evals/music_theory_scale_modes.yaml |
sha256=hHR2aBjHtEooEpJhTmrcaXYbx4MwTN37CIE7BZ52C60
|
346 |
evals/registry/evals/naughty_strings.yaml |
sha256=w0KiqaiyetF-CHIyXTMnhjFUpRx-k7w6d6c05PheCKk
|
1193 |
evals/registry/evals/nepali-numerals.yaml |
sha256=0fq5AuOO8FA6FGDz3_IS6Irmk3kGpXyOAkX1bN822tE
|
270 |
evals/registry/evals/nepali-song-singer.yaml |
sha256=2PpcIk6zgVl3-nsnSICFb7FJirmLC8wJJ7frXgds4rE
|
361 |
evals/registry/evals/ner_finance.yaml |
sha256=_RP5f14PXCq8ETuPyO5BFJ86eQpUgiCCXHM7WUl2OCE
|
247 |
evals/registry/evals/newsology.yaml |
sha256=YsQtIkYvVHjRMHXaF9FZ3Tlt-VAtf1ntFFAZwH8BmLE
|
340 |
evals/registry/evals/next-val-series.yaml |
sha256=pUb2oPKf46OrJezNow1s41dWk3u3dRmiilHH8UoZ9NE
|
290 |
evals/registry/evals/nfl-point-combinations.yaml |
sha256=y-SHkU4VWZjx29prcEH4BqqdycAopID9MKzru2PGQkQ
|
345 |
evals/registry/evals/non-compound-names.yaml |
sha256=kLShbj1uh43KxNB26J94y8jqwX0p9BvRoYhLPn_58ZI
|
3875 |
evals/registry/evals/norwegian-lexicon.yaml |
sha256=ozFqfAhEmYImLUb5FNmZRPL9zYjcgl9P4ODtmeQ6190
|
274 |
evals/registry/evals/norwegian-rhymes.yaml |
sha256=vFHGTpNaknpiSSFlaX3LGz0qefg-d4FDOs63I_oZp_U
|
358 |
evals/registry/evals/number-pattern.yaml |
sha256=7iZ9sKdmlT51DC-pwKnWz3Kbv4e2WXLRleIMtMGcypk
|
186 |
evals/registry/evals/number-reading.yaml |
sha256=X3PLjQTqjvRn1Qf2x5c4uv4dvwsUmJ_EtPDiKR7Vfto
|
292 |
evals/registry/evals/number_series_test.yaml |
sha256=VYovCYJGTU3i8iuRo9ANgfNm1bLEUQzCyNjn6KhLpbY
|
209 |
evals/registry/evals/numbers_game.yaml |
sha256=tUfPXeN8wYaDXNJ-keh1pNPvM2sbLcaRkTMLEBekKmQ
|
256 |
evals/registry/evals/numeral-type-comparisons.yaml |
sha256=vZPwpDEyyTjSCGO4eJoChUkvi6rL3sohRkCnInWP5mE
|
368 |
evals/registry/evals/numerical-cabbala-casanova.yaml |
sha256=qxS3cSWF5ZTc0yz3yYykxl6xBx5NtT2Q50Bc28CMnxw
|
928 |
evals/registry/evals/nutrition.yaml |
sha256=6s7B2EjIjkWVI0g7uUP0S8P77_RAZ1Z93rUlv8nXMCU
|
317 |
evals/registry/evals/ordered-history-events.yaml |
sha256=02ULUiPubqC4Jpu6CVo7axZD23BAtVDnEvQZ8YkGtyE
|
224 |
evals/registry/evals/ordering_randomised_versionlist.yaml |
sha256=0Ffe-vuPPU_HP6lxvm2mixKRMYuoxcRSLmpb0Ul-_dg
|
675 |
evals/registry/evals/override-system-instruction.yaml |
sha256=0OxOr9CFi5aWx7mfcupGPDT7IXU9xTE6zolQumnm9gs
|
239 |
evals/registry/evals/pantone_to_hex.yaml |
sha256=94dVacWWGdej87Pe_uWXBYSVUONESEGXCkH5VWsFGRQ
|
194 |
evals/registry/evals/parable-to-moral-match.yaml |
sha256=YRSDiSVNFqDrkFcxxuatV7NwuMppVdndNXJGZQuwLh8
|
502 |
evals/registry/evals/pararule-plus-multi-step-deductive-reasoning.yaml |
sha256=1YIsxc8YQDFNYLvH6m36W9pzGe5M9Nz8gR8YPpK6-rQ
|
441 |
evals/registry/evals/partially_solved_crossword_clues.yaml |
sha256=th3E26uTd5wud7ombx5VDLrpRkE8O64Zn8mXgEHFrEE
|
258 |
evals/registry/evals/passing-balls.yaml |
sha256=UxAnb0ZRZI0l1xnr3t1oiy0DptPCUonHEpDL4n-Z9SM
|
322 |
evals/registry/evals/path_enclosed_area.yaml |
sha256=gS3xtdZ67pZZDF2vdDlsWRHE4MSkYsj2z7et54Lepeo
|
304 |
evals/registry/evals/pattern_identification.yaml |
sha256=B7y4I9N0FKPW3yY4U_e0vjNk2pdFFVtRSBJ8xP51qIQ
|
221 |
evals/registry/evals/persian-kinship-riddles.yaml |
sha256=E6w8VBhAFFRO49krySpoUIzQkS3fRDTDNBcY1_cb5_E
|
353 |
evals/registry/evals/ph_calculation.yaml |
sha256=-N-SS9J9zuKpdl2Wu3FWl_Ck1SsAc2Qn-D4ppzVnzWc
|
287 |
evals/registry/evals/phonetics-identify-words-needing-missing-gpcs.yaml |
sha256=IfUrc1SD27sGaCGxBAjqXzT5NYXSy018sntREOBP3P4
|
429 |
evals/registry/evals/physics-interaction.yaml |
sha256=HovqQUjR2cZuod679bd_-qz74Zw_j0Bwad6zPBaRAvI
|
317 |
evals/registry/evals/pointer-value-retrieval.yaml |
sha256=Tp-s_m3kMFsY-pFgkKCaT_ydnaO51_6TEtQ70q-qPNg
|
2427 |
evals/registry/evals/points-on-line.yaml |
sha256=p2t0ENxWNDa05ZVCT332q8vA5_CTz-I4yBNonl2qxOA
|
297 |
evals/registry/evals/poker_analysis.yaml |
sha256=TVhzxQqRHhe-71o55S5zpZlx6s8m5l6cc-Hn65c5EWg
|
309 |
evals/registry/evals/poker_hand_ranks.yaml |
sha256=SiZBsIvCMt6jlM5MMOytTMDMzm6gDwhjkF1m8oT4who
|
188 |
evals/registry/evals/polish-lexicon.yaml |
sha256=rZFvz04fEkDicNrLd5N6WsuTI_fr5q90nSnao-2VdDw
|
290 |
evals/registry/evals/polish-proverbs.yaml |
sha256=sWHr8lU3X8mT3eLeAC0ggBnDXr4kRXpv5R97UP_nxxk
|
272 |
evals/registry/evals/polish-syllable-count.yaml |
sha256=_uRZ21amHGxkDyRnEBWavUsJ-kYcdXRIA_VqdqACcxQ
|
214 |
evals/registry/evals/polish_rhymes_generation.yaml |
sha256=VK6fl4zEokq9qiJY68uO75t2XPCMt8z3KffGDuMw2U4
|
270 |
evals/registry/evals/population_span_extraction.yaml |
sha256=8hNXgkFkzOaT6QhL3LdC7x57aiuhGvLHjcero7nGMwo
|
579 |
evals/registry/evals/portuguese-kinship-riddles.yaml |
sha256=xrwlmeG0mKhDjb5KnrPFj5dL38hJ0w-aIOG2z_u4yec
|
363 |
evals/registry/evals/portuguese-sarcasm.yaml |
sha256=aLRwge2tFexwwtuXmTzgHM581X-lMxChT3VTxx5yjyc
|
277 |
evals/registry/evals/portuguese-syllable-count.yaml |
sha256=DvVXOPMMDQCLkT4O7zq2zBVfdxcJDjdmnWMi8hCGYrE
|
297 |
evals/registry/evals/positive-binary-operations.yaml |
sha256=moiZ-N2fs9KXLcPG_sxT3cGkQqTG-n2gsDYop9RUXT0
|
320 |
evals/registry/evals/premature-conclusions.yaml |
sha256=CShHYKkG7_oBrLn01TxlBorLfWL_0Ujbo-uxc3tNN74
|
354 |
evals/registry/evals/probabilities-word-problems.yaml |
sha256=S9fj1LTYKmNtFWdUwfWq2jvwTaKPgWpdwQlecl0k0C4
|
347 |
evals/registry/evals/probability_questions.yaml |
sha256=qS9pBdUVo-bH7-ewLEjYqIicgIi7d2urjdM2McipSWc
|
335 |
evals/registry/evals/product-matching.yaml |
sha256=flbFWqo90lEFLtZf3GSpRkWd0kvXI1LZ-iJf2UhWoE8
|
1847 |
evals/registry/evals/prompt-injection.yaml |
sha256=q01QVmMDBOgWbl26_3jNPGI5f9iKu9rVNEDk22uLy4Q
|
281 |
evals/registry/evals/proofreader.yaml |
sha256=fk2hrHfYnfkdGWpJom8Zyors3yV1oFu61pBfZS3ytyM
|
262 |
evals/registry/evals/pure_korean.yaml |
sha256=H41iSpq-A0f9w0CzGBLfZWeLc2P0wHbkGR_M12l2nl8
|
235 |
evals/registry/evals/python_list_comprehension.yaml |
sha256=csKNmg0jlOYqO1TFO50sQg6zKNF_VQsW0Ayde0lf-KI
|
334 |
evals/registry/evals/qa.yaml |
sha256=VzRFQP-dhOezS88MM3AZxwop0XWAMiW2vWoIfg5dYZo
|
282 |
evals/registry/evals/quartz.yaml |
sha256=0EHWFx6lpnprBZgMgu6kc8MwGL_iFBPqwV-1K7UN_mM
|
219 |
evals/registry/evals/ral_to_hex.yaml |
sha256=moSh3ifpn7Wv8iWEqg6yN8t1-voTjWM-OQ6BOQIyAcA
|
176 |
evals/registry/evals/rare-and-loanwords-dutch-lexicon.yaml |
sha256=k_kLjx_5IMYV52jPUzIDVTQk63sVb5YEZBoEhE8Cr50
|
380 |
evals/registry/evals/raven-matrices.yaml |
sha256=YEAP4309dnnCQ-k3NGCrWLjhCa2_839-Ze6oPNirdB8
|
14285 |
evals/registry/evals/reasoning_with_contradictory_statements.yaml |
sha256=whbop_aJotmnMPEnI9tTo5-fowbCo4ZXMTmFyDamUN4
|
366 |
evals/registry/evals/rectangles.yaml |
sha256=ULq-dSXtuxSktCM73PWWs4Gs5uLu3K3EH1BIiTdmfm0
|
171 |
evals/registry/evals/recurrence-relation.yaml |
sha256=N94HfmShehFvvtosC_m15wvQAu612H5RwSydU7RzN9I
|
216 |
evals/registry/evals/regex-match.yaml |
sha256=qOU03xzvbRFT1C1IFPru3TbPLrlrAyWxsb6u3NeTaRc
|
175 |
evals/registry/evals/relative-orientations.yaml |
sha256=dFtW-UInzP67Gi80ZvR4TREbSW_cPdFKoQRNumIvgso
|
221 |
evals/registry/evals/resistor-ohm-calculator.yaml |
sha256=dGPG5l8O6jLSUty2tnHR5zjT_97FdHT4fPGNX7C0pMY
|
350 |
evals/registry/evals/resource_id_extraction.yaml |
sha256=D3QnLnN4IE8HeMyIGukHJnM1c6MzC-iyV0rQUxAc2Nc
|
362 |
evals/registry/evals/reverse-polish-notation.yaml |
sha256=SjCbi9WQJ5rGAaIv0wANB_h7sBvB1vApsf0fgWs4uTg
|
321 |
evals/registry/evals/reverse-shell.yaml |
sha256=1a-LZubKZJwhBc2F1PvgrClLO1jceyu90RUPXcf2t0s
|
283 |
evals/registry/evals/reverse-sort-words-eng.yaml |
sha256=MzccyfZ_ZpCXytqavOiZnEm6NWZQOMx3AhTSSxne0U0
|
370 |
evals/registry/evals/reverse-string.yaml |
sha256=4YD9q2QugHODFDUYDZ1jh-ALuNyiQ_23jogZudLgV1s
|
378 |
evals/registry/evals/rhetorical-devices.yaml |
sha256=iFWFEzUPMNDX35IElSPecTUFwg2Uv3VIKXuY6UzkkYg
|
294 |
evals/registry/evals/rock-climbing.yaml |
sha256=iGFpgRJyx2rPxORI-I87rXNYE9yf1WF6iDf5CPQNYMo
|
182 |
evals/registry/evals/romanian-logic.yaml |
sha256=AFO0vm_KtsB3XBEmxlhMtPJyr4RQgOHYWC3lhgDZGSM
|
338 |
evals/registry/evals/romanian_homonyms.yaml |
sha256=ZWlP018xtsHPG8qPIu-KtkteeUhe85cN387m1g8ywoQ
|
266 |
evals/registry/evals/rot13.yaml |
sha256=bJqvQ-bO_7rCoFTj_PqNZrDRBW0SJOYpSpJIPdBIup8
|
255 |
evals/registry/evals/ru_rhymes.yaml |
sha256=JXBbw53hV2gi3LLVNBkoBd-IsBfhqJJBlZZIVgGPpoU
|
468 |
evals/registry/evals/rubiks-colors.yaml |
sha256=VwyOsuMSHkQHac0Hlr4vb8wqK5lb9AwlhK7_OiWziAc
|
294 |
evals/registry/evals/rucola.yaml |
sha256=OXpRYqknO92SzBVkotHK2LmPK-zQPl4JPOQvzU60AMg
|
236 |
evals/registry/evals/russe.yaml |
sha256=KoXTQAtgybFlUqfjwytL6RfuU22UwV2VAMkO1ifeZCU
|
364 |
evals/registry/evals/russian-english-homonym-context-resolution.yaml |
sha256=AviQ_iYCTyePMAZ86GKb5bR5e_wMqziTgr6w-gGvpzM
|
298 |
evals/registry/evals/russian-lexicon.yaml |
sha256=RBcLoUIb37M5KdVI8NyNyBl7zoLZMRnnrJiM8ou22es
|
278 |
evals/registry/evals/russian-nlp-tasks.yaml |
sha256=fy1TANYx-H3SPmLRAdYDbYXAqHEPB426OEuAN_urgCQ
|
199 |
evals/registry/evals/russian-rhyme.yaml |
sha256=1mARLGCY-28V8HMtRToMiS-s-szsdbIBsV9ohi4p23o
|
254 |
evals/registry/evals/russian-verse.yaml |
sha256=cwHuZmeDmzfkTS5XOMf5cqB-D9hmhN1Emg5ypfaeFMA
|
285 |
evals/registry/evals/russian_medical.yaml |
sha256=XU8ViRSVGluUYXweOBlzialcuCk3I_3vCCDTXjG9i0M
|
190 |
evals/registry/evals/russian_sarcasm.yaml |
sha256=jOYzSdnNJPXGBY54Yb5ef5DEGQ040L55Du_mHWh8CRc
|
248 |
evals/registry/evals/sarcasm.yaml |
sha256=OnfU-Hac-TuB3382Bs63-tH6Lo61s0ya0ygA9DWvS1w
|
274 |
evals/registry/evals/seating_arrangements.yaml |
sha256=rX0evVx4LH9icxNKUlcetQyvOz9M3uJ4Dzpu7C82mf8
|
338 |
evals/registry/evals/security_guide.yaml |
sha256=i49LrtzNZwy7C9C7ZMT5UWZdUqDfmehmnKmLBR4D01U
|
334 |
evals/registry/evals/seo_keywords.yaml |
sha256=RV9kMJcfGGwMutKc4bZ-unlQb2zZ07oc30po-JjzhjU
|
328 |
evals/registry/evals/sexagenary-cycle-calculation.yaml |
sha256=mhgIVGYu-QfDqioZvPVuCNn2Gg-QJ6N4l0Vo1f2D1mY
|
247 |
evals/registry/evals/shape-in-shape.yaml |
sha256=qCljT5OfPaz1sRq6hJJMXm0GrT8yJt6ySZV2_21mLs0
|
295 |
evals/registry/evals/shared-borders.yaml |
sha256=Pnd7Ld6ZQxbd1XEN2VV4N8G_IUzxj7DeHgjy8flGeUM
|
379 |
evals/registry/evals/shopping_discount_comparison.yaml |
sha256=LATGYAG9o3HoIi2WUDv-4ufXVF2126JrG7AgYB2c77o
|
328 |
evals/registry/evals/simple-block-puzzles.yaml |
sha256=kbeknpZExqZhzLT7sV3vr-fBSleNLTXP8E9_ouwc2hk
|
341 |
evals/registry/evals/simple-charting.yaml |
sha256=7GSg1TnokXG2jLCRulOrpr8OnAHcmpOZAF5EQ0GzTgc
|
295 |
evals/registry/evals/simple-knowledge-mongolian.yaml |
sha256=TcMjFqx8Ng85w7JZ6e-eEWByk2G1Sa6UeAYauRlQEMQ
|
364 |
evals/registry/evals/simple-visual-understanding.yaml |
sha256=FZG8GrAEFJaXlahe2NGr1f2ZKRVvva7mSQov8OTash0
|
377 |
evals/registry/evals/simple_math.yaml |
sha256=3ZzzKXLt_UjK2uBNPZDrwpKrFnE6fqxn7c4zzfJ1f5I
|
253 |
evals/registry/evals/simple_physics_engine.yaml |
sha256=Xuvkz8lT4tMJqkoMhhHdpFfsfI3ogeeK2SY1W39SE8s
|
338 |
evals/registry/evals/sindarin-fluency.yaml |
sha256=7SVAAprfqctlJakggzSM5CPjP8BDhZLttJ847MA24To
|
292 |
evals/registry/evals/singapore_data_protection_decisions.yaml |
sha256=NHH-epIL-yQSSVdnaq5bcZF9tydK8Y5oGSSzbttPKNI
|
541 |
evals/registry/evals/singlestore-vectorsearch.yaml |
sha256=GQwio-jLDeidiDqEh8EitgA0HfOCqDNo4rIF0fCXyYY
|
430 |
evals/registry/evals/smiles_to_formula.yaml |
sha256=1EfI8Y6x_NTjgp6CKguYGFqc90NGJBUpGEAny8XNCBY
|
206 |
evals/registry/evals/soc_codes.yaml |
sha256=cd0O1z5HWkIR6WhgquChQarRFx-_-jwIT5DuuKtJGRM
|
382 |
evals/registry/evals/solve-for-variable.yaml |
sha256=nu8izNq9PQf6CzfDj5Q8DKMuBS7IDJmEmZ7xUWNIlXY
|
304 |
evals/registry/evals/sort-numeric.yaml |
sha256=QuXSOrj0W8xqn20Z3Xz1fVZtoOnUYco2nyxZktxrUxY
|
374 |
evals/registry/evals/south-african-bands.yaml |
sha256=Ak8myxi2XoFQv23NT72sfIHkQCNLrfrFZVDX1LH0rWM
|
441 |
evals/registry/evals/spanish-lexicon.yaml |
sha256=slXr6TW9-hZ8MW14qBzMuXjd-agZSmoWIw3P2DK8hGo
|
310 |
evals/registry/evals/spanish_feminine_noun_masculine_article.yaml |
sha256=BS1lafn6OboARgfrARq6g-iYBETi1NM4jXEqgxafrgw
|
453 |
evals/registry/evals/split_chinese_characters.yaml |
sha256=bhVwTzPS-0MYbSiKt0uX9Sb6eLyIfs9VFcyCFBnqnrg
|
227 |
evals/registry/evals/sql.yaml |
sha256=F-ZH0r1EyPXhOtitUwVyuA17aGSCOcSsZly2VL98HVo
|
1048 |
evals/registry/evals/squares-gpt.yaml |
sha256=DRn4BvDRmcJ7oukYftYLzIGY6O7rL1uOpqyGairjOik
|
273 |
evals/registry/evals/stats-tests.yaml |
sha256=azj7949bHgxbLDSs_4pvyx4rAJXrZdqO_W9UdNfSHwc
|
174 |
evals/registry/evals/stock-options.yaml |
sha256=OX7A_FTLT59BN_0ynPs_3WZw_EoO9Fj78ak92ce_7OU
|
4472 |
evals/registry/evals/superficial-patterns.yaml |
sha256=hO1DDrucJfWf8i_hYKKB_esNjlohIIZVLxy58wbyzsY
|
286 |
evals/registry/evals/svg_alphabet.yaml |
sha256=cfhMMfD8t_WkKke7y22AqJ1mlQBPrVm5Yy-1XyiN2yQ
|
272 |
evals/registry/evals/svg_to_text.yaml |
sha256=tbFaupas4OskRnPITdwXXWNm_0alGxROqmJR4st28c0
|
250 |
evals/registry/evals/svg_understanding.yaml |
sha256=xtPDHMd1XWTuwYy6q9kLSzeSXxKudPEcXuVssYQzdbg
|
245 |
evals/registry/evals/swap-words.yaml |
sha256=j4DbLz97h70zj-_y1CYTfv7TfG3n3dR_5ahIrU3UxuY
|
171 |
evals/registry/evals/swedish-spelling.yaml |
sha256=KUhH-CFMXRnvsYPXVkkjEZSwTnPQOgNsOLU_VegJPYE
|
272 |
evals/registry/evals/swedish_sat.yaml |
sha256=3I_e1woOyG3TogavIv5dUHuc4G9pz2VkUR6gJDKAth4
|
376 |
evals/registry/evals/syllables_long_words.yaml |
sha256=-YSs3YubeV3ikMQt67TzW24TZMp2F8gg7R947orY9zY
|
197 |
evals/registry/evals/syntax-check.yaml |
sha256=Xpwl1a8DjnM270EfoOPgC2ybyt57D4czPuk9vzf1TLM
|
269 |
evals/registry/evals/taxes.yaml |
sha256=_sUoQmiuP0KinVWmfinr3WZld-uWKYLLsAMf-xZz6lY
|
150 |
evals/registry/evals/tempo_to_measure_count.yaml |
sha256=z5kBFRsnqSIH9uFwVHMZbaTdScgnE6bkE6aulVdzsNQ
|
399 |
evals/registry/evals/test-basic.yaml |
sha256=KbRk8TxXbrGtHjFKxle2sekfNvho-GQzqoTw6g9l_Vw
|
1169 |
evals/registry/evals/test-comp-sci.yaml |
sha256=yqT5_aFRZxltThsyxxpc_nX9SxJmUO0hvOtbowkejAo
|
400 |
evals/registry/evals/test-modelgraded-battle.yaml |
sha256=ukmOqejQo_UgXA1HVZVtPdoOJYAmD3olntrWWjdlhxk
|
1271 |
evals/registry/evals/test-modelgraded-generated.yaml |
sha256=S7fIzT6SB6gkJUUtiMeZwsS72IsE2xwAzQfNClC66ek
|
347 |
evals/registry/evals/test-modelgraded.yaml |
sha256=ufxE_DMYM5g3O7y9ftGnTkomY7JjW3OaqgOlJhKAt3M
|
3040 |
evals/registry/evals/test_english_pronunciations.yaml |
sha256=7q-G6slHETUl_rSpcD_aWXuALc0x7WYP9TmXsUI9-gE
|
376 |
evals/registry/evals/test_japanese_english_numerals.yaml |
sha256=ShN9YLuKA8NEPVw4oB9Om_W5nQyBLSkKdkyy-fit-eA
|
381 |
evals/registry/evals/test_japanese_radical.yaml |
sha256=TuNQB230HUnFcEYBGnOzU67iyKShSsoZ54SGuJySMF8
|
340 |
evals/registry/evals/test_japanese_units.yaml |
sha256=QtSc0sFKL8l7dyozZB3gHEeg7fCLJrkiT5kVpmJwwx8
|
335 |
evals/registry/evals/tetris.yaml |
sha256=znxB2W_ueFcHGCZEdAQHePtgnD7k7zZQA_x9BPW08NI
|
360 |
evals/registry/evals/thirty_six_stratagems.yaml |
sha256=UZQmVkoAuGQFGzI7DpYiJxrQVXhohAzsw0UPYzHz2KM
|
325 |
evals/registry/evals/three-pt-mapping.yaml |
sha256=bsxAEXvPC-weUekXjw1ouWgqGnT1E7F7yUhRX-w2cAA
|
323 |
evals/registry/evals/time-zone-conversion.yaml |
sha256=nie50PQAEz_XCl-90BqntWOrsD9RbcryI4lSFrgVPps
|
397 |
evals/registry/evals/tokyo-station-number.yaml |
sha256=Tye6oEIFL7UJNOOthruNgyn-z_ROhCbcf4B9im9okns
|
280 |
evals/registry/evals/track_objects.yaml |
sha256=HMiDD5C0l7pQ7k87xP7nwjte-zEPVL3A82paaHFvukA
|
263 |
evals/registry/evals/tracking-shuffled-objects.yaml |
sha256=oAr2z9noPLSNPG1483-f2IIIEl6eVASfgV23nfkQPY8
|
230 |
evals/registry/evals/tricky-word-problems.yaml |
sha256=1behCvhbtHtigxDLQo20s18nKfImW7aWXl-lAEJ_mnQ
|
373 |
evals/registry/evals/turkish_characters.yaml |
sha256=q7xPZehczQorXckXRkoQX79mUS_f5AVgDLKMsTPnxsA
|
302 |
evals/registry/evals/ukraine-eit.yaml |
sha256=tXjtkAH60MOiMxhg79GXfd5eLyWf1P1f9Kw9oiDyQ_4
|
174 |
evals/registry/evals/ukraine-gec.yaml |
sha256=yM4Uu_8FSy8xNPLYmqsPMVGRJDazdirwjM4arum-N38
|
6692 |
evals/registry/evals/ukraine_electronic_petitions.yaml |
sha256=ZptbdYLuIcY75gNN8kjy_klUI7pYP_HctMNkA3TiP8k
|
319 |
evals/registry/evals/unified-patch.yaml |
sha256=B4aiU1HjFW10W4EaOUh2aB58tlqJKY9pzinrrQcX1IU
|
189 |
evals/registry/evals/unique_combinations.yaml |
sha256=Ij0uWchgtoccGv500S8zbTEFZX7wSyHeEDCbwrv6dw4
|
307 |
evals/registry/evals/unsolvable_questions.yaml |
sha256=5_Bc9DcofRNJ4PST8c4nnt7LJeiyhS--FVcU5PlRK-o
|
211 |
evals/registry/evals/unwanted-rhyming.yaml |
sha256=nffZ7RZEUdOCpe2kXS2NeGfk0dgryNaymDmc-6RCL7M
|
274 |
evals/registry/evals/urdu-lexicon.yaml |
sha256=zRGd6yteF8gAG9cZbK-KkcpsFU3iFjQtEEuNDUdssO8
|
289 |
evals/registry/evals/urdu-transliteration.yaml |
sha256=WXeQtVA6UZOrMy56sW9eZrE5BIByVblDuk_ykVbkl5U
|
297 |
evals/registry/evals/us-tort-law.yaml |
sha256=gqq4T-Xof57eWncpshQUMePSGpW_pAdWKbk7kL4y2vE
|
329 |
evals/registry/evals/utah_real_estate.yaml |
sha256=AzGWr03krh4WF8m5n5wYCLZxJThnUJfOkThX86h6fP8
|
284 |
evals/registry/evals/utility_price_parsing.yaml |
sha256=ph84pD5IEJLDeTFC36MOZPpFek6a7iRElg_dWxVg3fM
|
214 |
evals/registry/evals/viewport_to_grid_size.yaml |
sha256=eUXzWH93UTRVGxugY54I0-ZWRJPaRvf-6httJh0-nhE
|
379 |
evals/registry/evals/vigenere.yaml |
sha256=3MVVmzxE8t3rIFHCQ_fAaEcUd7gqKiFu9tQyXvaAzhw
|
266 |
evals/registry/evals/vintage_phone_keyboard_decode.yaml |
sha256=FXvwiATImlWHWYVPMqVrBEGa2bF6TCSmy70bwjNmoQY
|
503 |
evals/registry/evals/which-is-heavier.yaml |
sha256=DVA-pI99UH2Ad0-lb3B9HgtG9sFSiLl3gjH64Mdbst0
|
365 |
evals/registry/evals/wkt_understanding.yaml |
sha256=z42MKP9Ejex69QFJX8bdV6jfXHRwiFy7ltDi9_SvJZE
|
392 |
evals/registry/evals/word-association.yaml |
sha256=ONEfyzAWN9_vC5tj-d9dcSLy8o5Cw87RIhR6CwVz-Qk
|
1451 |
evals/registry/evals/word_vector_over_reliance.yaml |
sha256=78mALlnOr-_Gm-o84RuExdvtmN62i0O2vVBmdl0sD_w
|
397 |
evals/registry/modelgraded/arithmetic-expression.yaml |
sha256=wV9ylHviFiSgjWrw1iWKdWresgLKyYZ-kgspyIz1ApY
|
976 |
evals/registry/modelgraded/battle.yaml |
sha256=GyhK2Zpiz_8ZjMClad7ZnNgwKiBMlNTSXlqRoX0lMF8
|
492 |
evals/registry/modelgraded/best.yaml |
sha256=vilUeFU_1qP5w170l_3hoHKF8IHqGzqwsD3drjf8H2M
|
263 |
evals/registry/modelgraded/closedqa.yaml |
sha256=S5zCk_p7Jh7efQPn5xvLd0nF01CqRk48sza-FcOmsMs
|
831 |
evals/registry/modelgraded/diversity.yaml |
sha256=72YBUR5bI7MIjgl77U8jUlvOU-fVhrIB9QRIMV1nigs
|
246 |
evals/registry/modelgraded/fact.yaml |
sha256=KVo_PDrQJRG13VN4vkvbsYeCIRHfKS9Jol0PJ7B20PY
|
1157 |
evals/registry/modelgraded/humor.yaml |
sha256=DRYksqdu0EihCb9n9jlPFt3IUvfwfz_oxUC-42srlpQ
|
2564 |
evals/registry/modelgraded/iambic_pentameter.yaml |
sha256=cOZRPR5s56D-2ONXyYqDPxkzY0MIjdcqZeDnAeXz6iI
|
275 |
evals/registry/modelgraded/keywords.yaml |
sha256=B3m1OdhUjLGC1j1BC6r6Q6QkvAvUPxb-AJkUuGUd3kg
|
765 |
evals/registry/modelgraded/onomatopoeia.yaml |
sha256=7hsdCl0pmoPc6kaSLXUbPrpWn4cKA92UyiJYBti6lz8
|
1355 |
evals/registry/modelgraded/possible.yaml |
sha256=aRscHlzOdERDalY7usmXnuO3LGEMVPQaCDcT-VTMQ-k
|
700 |
evals/registry/modelgraded/regression-equation.yaml |
sha256=RBT_Jz8LtFKd5-qpof0AnyIKjlEfzocBtQ_qUo5cFHY
|
887 |
evals/registry/modelgraded/rhyming.yaml |
sha256=vhO7rNijTaCc5y-jx5GOJl3i16bwYP8e0urkQasLMXs
|
309 |
evals/registry/modelgraded/security.yaml |
sha256=a01Fgo4--V27C5Is6rTvIATSEJj-bSlseyh5l82U6tA
|
230 |
evals/registry/modelgraded/singlestore.yaml |
sha256=xQ-L3td9Y0yAGT-v4G6_a8rZLiPquXR6eRws0iJP4tc
|
1416 |
evals/registry/modelgraded/sql.yaml |
sha256=aN6bn2GTTRwNy5OUUDKap6DKXxZBUOE8IhJHrWgIKoI
|
1203 |
evals/registry/modelgraded/translation.yaml |
sha256=D2ucKsI1_05eQpoAoVP5uqdbbv6upH5Jk7LZuTPkbhA
|
1204 |
evals/utils/api_utils.py |
sha256=a2UrtHPGVvhZfIWcsvUPziB10jUf9jY9ZTGukQWHXvE
|
2136 |
evals/utils/misc.py |
sha256=l-SEafhRiI8cpMhXhit036DbMmrqbkyhHB2jHMX1Ajk
|
713 |
evals/utils/snowflake.py |
sha256=1PhhD7sQzw-RAl7QADm7gSRFUl9_ZnXBE0AVRXUhXNs
|
4076 |
evals/utils/test.py |
sha256=cQzlgyjMWA8ok7imndckqsyump5eBGLbewIyJiRnXOQ
|
668 |
evals_nightly-1.0.3.dev20230807.dist-info/LICENSE |
sha256=3PeSfsAA4L6gIbr1Vsgq16wuls3YKFociypwFOgwDG0
|
1063 |
evals_nightly-1.0.3.dev20230807.dist-info/METADATA |
sha256=lB4GEqwCl4xLhEyCcxBG273VXI-TYXQWiTB7bbqvmNw
|
918 |
evals_nightly-1.0.3.dev20230807.dist-info/WHEEL |
sha256=5sUXSg9e4bi7lTLOHcm6QEYwO5TIF1TNbTSVFVjcJcc
|
92 |
evals_nightly-1.0.3.dev20230807.dist-info/entry_points.txt |
sha256=VCG8Tg79A6FR1bHPBG6Vk2ZSTKBsqb7HZhN9qa1kiS8
|
90 |
evals_nightly-1.0.3.dev20230807.dist-info/top_level.txt |
sha256=-RPWnvpqWuvduYuK6BeQVBTji6GNx1s_SNB011XaRzY
|
6 |
evals_nightly-1.0.3.dev20230807.dist-info/RECORD |
— |
— |