JessicaOjo commited on
Commit
0dee3a2
·
verified ·
1 Parent(s): e513991

update wolof and claude 4.5 mmlu results

Browse files
data/leaderboard_json/lite_language_scores.json CHANGED
@@ -53,7 +53,7 @@
53
  "ibo": 17.0,
54
  "kin": 17.2,
55
  "lin": 16.6,
56
- "lug": 17.0,
57
  "orm": 15.1,
58
  "sna": 16.3,
59
  "sot": 16.1,
@@ -203,6 +203,7 @@
203
  "sot": 52.6,
204
  "swa": 69.8,
205
  "xho": 55.9,
 
206
  "yor": 45.2,
207
  "zul": 57.4
208
  },
@@ -218,6 +219,7 @@
218
  "sot": 63.8,
219
  "swa": 78.4,
220
  "xho": 69.7,
 
221
  "yor": 64.5,
222
  "zul": 68.2
223
  },
@@ -233,6 +235,7 @@
233
  "sot": 66.5,
234
  "swa": 79.7,
235
  "xho": 71.5,
 
236
  "yor": 61.7,
237
  "zul": 71.0
238
  },
@@ -266,20 +269,53 @@
266
  "yor": 21.9,
267
  "zul": 20.6
268
  },
269
- "Gemini-2.5 Pro": {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
270
  "amh": 78.6,
271
- "hau": 72.6,
272
- "ibo": 73.9,
273
- "kin": 74.7,
274
- "lin": 68.4,
275
- "lug": 72.2,
276
- "orm": 75.3,
277
- "sna": 78.6,
278
- "sot": 72.9,
279
- "swa": 82.5,
280
- "xho": 78.3,
281
- "yor": 71.8,
282
- "zul": 76.7
 
283
  },
284
  "Gemini-2.5 Flash": {
285
  "amh": 71.2,
@@ -293,52 +329,24 @@
293
  "sot": 65.1,
294
  "swa": 73.7,
295
  "xho": 70.1,
 
296
  "yor": 65.5,
297
  "zul": 69.4
298
  },
299
- "Claude 4.5 Sonnet": {
300
- "amh": 76.1,
301
- "hau": 72.1,
302
- "ibo": 69.8,
303
- "kin": 67.9,
304
- "lin": 60.8,
305
- "lug": 64.6,
306
- "orm": 67.9,
307
- "sna": 70.9,
308
- "sot": 69.4,
309
- "swa": 79.6,
310
- "xho": 73.0,
311
- "yor": 68.5,
312
- "zul": 70.5
313
- },
314
- "Claude 3.7 Sonnet": {
315
- "amh": 66.0,
316
- "hau": 60.9,
317
- "ibo": 59.0,
318
- "kin": 61.3,
319
- "lin": 55.0,
320
- "lug": 58.3,
321
- "orm": 57.7,
322
- "sna": 61.1,
323
- "sot": 61.6,
324
- "swa": 71.9,
325
- "xho": 64.1,
326
- "yor": 57.9,
327
- "zul": 62.2
328
- },
329
- "Claude 4.0 Sonnet": {
330
- "amh": 78.0,
331
- "hau": 73.9,
332
- "ibo": 71.8,
333
- "kin": 69.0,
334
- "lin": 62.9,
335
- "lug": 62.5,
336
- "orm": 65.6,
337
- "sna": 71.3,
338
- "sot": 70.2,
339
- "swa": 82.0,
340
- "xho": 74.2,
341
- "yor": 67.8,
342
- "zul": 72.4
343
  }
344
  }
 
53
  "ibo": 17.0,
54
  "kin": 17.2,
55
  "lin": 16.6,
56
+ "lug": 16.9,
57
  "orm": 15.1,
58
  "sna": 16.3,
59
  "sot": 16.1,
 
203
  "sot": 52.6,
204
  "swa": 69.8,
205
  "xho": 55.9,
206
+ "wol": 30.9,
207
  "yor": 45.2,
208
  "zul": 57.4
209
  },
 
219
  "sot": 63.8,
220
  "swa": 78.4,
221
  "xho": 69.7,
222
+ "wol": 63.7,
223
  "yor": 64.5,
224
  "zul": 68.2
225
  },
 
235
  "sot": 66.5,
236
  "swa": 79.7,
237
  "xho": 71.5,
238
+ "wol": 51.9,
239
  "yor": 61.7,
240
  "zul": 71.0
241
  },
 
269
  "yor": 21.9,
270
  "zul": 20.6
271
  },
272
+ "Claude 4.0 Sonnet": {
273
+ "amh": 78.0,
274
+ "hau": 73.9,
275
+ "ibo": 71.8,
276
+ "kin": 69.0,
277
+ "lin": 62.9,
278
+ "lug": 62.5,
279
+ "orm": 65.6,
280
+ "sna": 71.3,
281
+ "sot": 70.2,
282
+ "swa": 82.0,
283
+ "xho": 74.2,
284
+ "wol": 39.7,
285
+ "yor": 67.8,
286
+ "zul": 72.4
287
+ },
288
+ "Claude 3.7 Sonnet": {
289
+ "amh": 66.0,
290
+ "hau": 60.9,
291
+ "ibo": 59.0,
292
+ "kin": 61.3,
293
+ "lin": 55.0,
294
+ "lug": 58.3,
295
+ "orm": 57.7,
296
+ "sna": 61.1,
297
+ "sot": 61.6,
298
+ "swa": 71.9,
299
+ "xho": 64.1,
300
+ "wol": 46.4,
301
+ "yor": 57.9,
302
+ "zul": 62.2
303
+ },
304
+ "Claude 4.5 Sonnet": {
305
  "amh": 78.6,
306
+ "hau": 75.2,
307
+ "ibo": 73.1,
308
+ "kin": 70.5,
309
+ "lin": 63.3,
310
+ "lug": 66.1,
311
+ "orm": 70.8,
312
+ "sna": 72.6,
313
+ "sot": 71.8,
314
+ "swa": 83.4,
315
+ "xho": 75.8,
316
+ "wol": 43.9,
317
+ "yor": 69.8,
318
+ "zul": 73.4
319
  },
320
  "Gemini-2.5 Flash": {
321
  "amh": 71.2,
 
329
  "sot": 65.1,
330
  "swa": 73.7,
331
  "xho": 70.1,
332
+ "wol": 57.8,
333
  "yor": 65.5,
334
  "zul": 69.4
335
  },
336
+ "Gemini-2.5 Pro": {
337
+ "amh": 78.6,
338
+ "hau": 72.6,
339
+ "ibo": 73.9,
340
+ "kin": 74.7,
341
+ "lin": 68.4,
342
+ "lug": 72.2,
343
+ "orm": 75.3,
344
+ "sna": 78.6,
345
+ "sot": 72.9,
346
+ "swa": 82.5,
347
+ "xho": 78.3,
348
+ "wol": 66.9,
349
+ "yor": 71.8,
350
+ "zul": 76.7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
351
  }
352
  }