Files changed (1) hide show
  1. README.md +48 -48
README.md CHANGED
@@ -162,7 +162,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
162
  <td align="center" style="vertical-align: middle; text-align: center">GPQA Diamond</td>
163
  <td align="center" style="vertical-align: middle; text-align: center">93.5</td>
164
  <td align="center" style="vertical-align: middle; text-align: center">92.6</td>
165
- <td align="center" style="vertical-align: middle; text-align: center">94.1</td>
166
  <td align="center" style="vertical-align: middle; text-align: center">91.0</td>
167
  <td align="center" style="vertical-align: middle; text-align: center">93.5</td>
168
  <td align="center" style="vertical-align: middle; text-align: center">91.2</td>
@@ -171,14 +171,14 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
171
  <td align="center" style="vertical-align: middle; text-align: center">CritPt</td>
172
  <td align="center" style="vertical-align: middle; text-align: center">23.4</td>
173
  <td align="center" style="vertical-align: middle; text-align: center">28.6</td>
174
- <td align="center" style="vertical-align: middle; text-align: center">32.3</td>
175
  <td align="center" style="vertical-align: middle; text-align: center">20.9</td>
176
  <td align="center" style="vertical-align: middle; text-align: center">27.1</td>
177
  <td align="center" style="vertical-align: middle; text-align: center">20.9</td>
178
  </tr>
179
  <tr>
180
  <td align="center" style="vertical-align: middle; text-align: center">AA-LCR</td>
181
- <td align="center" style="vertical-align: middle; text-align: center">74.7</td>
182
  <td align="center" style="vertical-align: middle; text-align: center">70.0</td>
183
  <td align="center" style="vertical-align: middle; text-align: center">73.7</td>
184
  <td align="center" style="vertical-align: middle; text-align: center">67.7</td>
@@ -188,7 +188,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
188
  <tr>
189
  <td align="center" style="vertical-align: middle; text-align: center">HLE-Full</td>
190
  <td align="center" style="vertical-align: middle; text-align: center">43.5 / 56.0</td>
191
- <td align="center" style="vertical-align: middle; text-align: center">53.3 / 63.0</td>
192
  <td align="center" style="vertical-align: middle; text-align: center">44.5 / 58.0</td>
193
  <td align="center" style="vertical-align: middle; text-align: center">49.8 / 57.9</td>
194
  <td align="center" style="vertical-align: middle; text-align: center">41.4 / 52.2</td>
@@ -201,14 +201,14 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
201
  <td align="center" style="vertical-align: middle; text-align: center">DeepSWE</td>
202
  <td align="center" style="vertical-align: middle; text-align: center">67.5</td>
203
  <td align="center" style="vertical-align: middle; text-align: center">70.0</td>
204
- <td align="center" style="vertical-align: middle; text-align: center">73.0</td>
205
  <td align="center" style="vertical-align: middle; text-align: center">59.0</td>
206
  <td align="center" style="vertical-align: middle; text-align: center">67.0</td>
207
  <td align="center" style="vertical-align: middle; text-align: center">46.2</td>
208
  </tr>
209
  <tr>
210
  <td align="center" style="vertical-align: middle; text-align: center">ProgramBench</td>
211
- <td align="center" style="vertical-align: middle; text-align: center">77.8</td>
212
  <td align="center" style="vertical-align: middle; text-align: center">76.8</td>
213
  <td align="center" style="vertical-align: middle; text-align: center">77.6</td>
214
  <td align="center" style="vertical-align: middle; text-align: center">71.9</td>
@@ -219,7 +219,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
219
  <td align="center" style="vertical-align: middle; text-align: center">Terminal-Bench 2.1</td>
220
  <td align="center" style="vertical-align: middle; text-align: center">88.3</td>
221
  <td align="center" style="vertical-align: middle; text-align: center">88.0</td>
222
- <td align="center" style="vertical-align: middle; text-align: center">88.8</td>
223
  <td align="center" style="vertical-align: middle; text-align: center">84.6</td>
224
  <td align="center" style="vertical-align: middle; text-align: center">83.4</td>
225
  <td align="center" style="vertical-align: middle; text-align: center">82.7</td>
@@ -227,7 +227,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
227
  <tr>
228
  <td align="center" style="vertical-align: middle; text-align: center">FrontierSWE</td>
229
  <td align="center" style="vertical-align: middle; text-align: center">81.2</td>
230
- <td align="center" style="vertical-align: middle; text-align: center">86.6</td>
231
  <td align="center" style="vertical-align: middle; text-align: center">71.3</td>
232
  <td align="center" style="vertical-align: middle; text-align: center">66.7</td>
233
  <td align="center" style="vertical-align: middle; text-align: center">64.9</td>
@@ -235,7 +235,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
235
  </tr>
236
  <tr>
237
  <td align="center" style="vertical-align: middle; text-align: center">SWE-Marathon</td>
238
- <td align="center" style="vertical-align: middle; text-align: center">42.0</td>
239
  <td align="center" style="vertical-align: middle; text-align: center">35.0</td>
240
  <td align="center" style="vertical-align: middle; text-align: center">39.0</td>
241
  <td align="center" style="vertical-align: middle; text-align: center">40.0</td>
@@ -245,7 +245,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
245
  <tr>
246
  <td align="center" style="vertical-align: middle; text-align: center">PostTrainBench</td>
247
  <td align="center" style="vertical-align: middle; text-align: center">36.6</td>
248
- <td align="center" style="vertical-align: middle; text-align: center">41.4</td>
249
  <td align="center" style="vertical-align: middle; text-align: center">34.6</td>
250
  <td align="center" style="vertical-align: middle; text-align: center">34.1</td>
251
  <td align="center" style="vertical-align: middle; text-align: center">28.4</td>
@@ -254,7 +254,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
254
  <tr>
255
  <td align="center" style="vertical-align: middle; text-align: center">MLS-Bench-Lite</td>
256
  <td align="center" style="vertical-align: middle; text-align: center">48.3</td>
257
- <td align="center" style="vertical-align: middle; text-align: center">49.9</td>
258
  <td align="center" style="vertical-align: middle; text-align: center">46.2</td>
259
  <td align="center" style="vertical-align: middle; text-align: center">42.8</td>
260
  <td align="center" style="vertical-align: middle; text-align: center">35.5</td>
@@ -263,7 +263,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
263
  <tr>
264
  <td align="center" style="vertical-align: middle; text-align: center">SciCode</td>
265
  <td align="center" style="vertical-align: middle; text-align: center">58.7</td>
266
- <td align="center" style="vertical-align: middle; text-align: center">60.2</td>
267
  <td align="center" style="vertical-align: middle; text-align: center">56.1</td>
268
  <td align="center" style="vertical-align: middle; text-align: center">53.5</td>
269
  <td align="center" style="vertical-align: middle; text-align: center">56.1</td>
@@ -272,7 +272,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
272
  <tr>
273
  <td align="center" style="vertical-align: middle; text-align: center">Kimi Code Bench 2.0</td>
274
  <td align="center" style="vertical-align: middle; text-align: center">72.9</td>
275
- <td align="center" style="vertical-align: middle; text-align: center">76.9</td>
276
  <td align="center" style="vertical-align: middle; text-align: center">64.8</td>
277
  <td align="center" style="vertical-align: middle; text-align: center">71.7</td>
278
  <td align="center" style="vertical-align: middle; text-align: center">69.0</td>
@@ -283,7 +283,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
283
  </tr>
284
  <tr>
285
  <td align="center" style="vertical-align: middle; text-align: center">BrowseComp</td>
286
- <td align="center" style="vertical-align: middle; text-align: center">91.2</td>
287
  <td align="center" style="vertical-align: middle; text-align: center">88.0</td>
288
  <td align="center" style="vertical-align: middle; text-align: center">90.4</td>
289
  <td align="center" style="vertical-align: middle; text-align: center">84.3</td>
@@ -292,7 +292,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
292
  </tr>
293
  <tr>
294
  <td align="center" style="vertical-align: middle; text-align: center">DeepSearchQA (F1)</td>
295
- <td align="center" style="vertical-align: middle; text-align: center">95.0</td>
296
  <td align="center" style="vertical-align: middle; text-align: center">94.2</td>
297
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
298
  <td align="center" style="vertical-align: middle; text-align: center">93.1</td>
@@ -301,7 +301,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
301
  </tr>
302
  <tr>
303
  <td align="center" style="vertical-align: middle; text-align: center">ResearchRubrics</td>
304
- <td align="center" style="vertical-align: middle; text-align: center">76.2</td>
305
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
306
  <td align="center" style="vertical-align: middle; text-align: center">73.8</td>
307
  <td align="center" style="vertical-align: middle; text-align: center">73.5</td>
@@ -311,7 +311,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
311
  <tr>
312
  <td align="center" style="vertical-align: middle; text-align: center">GDPval-AA v2 (Elo)</td>
313
  <td align="center" style="vertical-align: middle; text-align: center">1686</td>
314
- <td align="center" style="vertical-align: middle; text-align: center">1747</td>
315
  <td align="center" style="vertical-align: middle; text-align: center">1736</td>
316
  <td align="center" style="vertical-align: middle; text-align: center">1593</td>
317
  <td align="center" style="vertical-align: middle; text-align: center">1491</td>
@@ -320,7 +320,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
320
  <tr>
321
  <td align="center" style="vertical-align: middle; text-align: center">Toolathlon-Verified</td>
322
  <td align="center" style="vertical-align: middle; text-align: center">76.5</td>
323
- <td align="center" style="vertical-align: middle; text-align: center">77.9</td>
324
  <td align="center" style="vertical-align: middle; text-align: center">74.9</td>
325
  <td align="center" style="vertical-align: middle; text-align: center">76.2</td>
326
  <td align="center" style="vertical-align: middle; text-align: center">73.5</td>
@@ -328,7 +328,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
328
  </tr>
329
  <tr>
330
  <td align="center" style="vertical-align: middle; text-align: center">MCPMark-Verified</td>
331
- <td align="center" style="vertical-align: middle; text-align: center">94.5</td>
332
  <td align="center" style="vertical-align: middle; text-align: center">87.4</td>
333
  <td align="center" style="vertical-align: middle; text-align: center">92.9</td>
334
  <td align="center" style="vertical-align: middle; text-align: center">76.4</td>
@@ -338,7 +338,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
338
  <tr>
339
  <td align="center" style="vertical-align: middle; text-align: center">MCP-Atlas</td>
340
  <td align="center" style="vertical-align: middle; text-align: center">84.2</td>
341
- <td align="center" style="vertical-align: middle; text-align: center">84.7</td>
342
  <td align="center" style="vertical-align: middle; text-align: center">83.6</td>
343
  <td align="center" style="vertical-align: middle; text-align: center">83.6</td>
344
  <td align="center" style="vertical-align: middle; text-align: center">82.8</td>
@@ -346,7 +346,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
346
  </tr>
347
  <tr>
348
  <td align="center" style="vertical-align: middle; text-align: center">AutomationBench</td>
349
- <td align="center" style="vertical-align: middle; text-align: center">30.8</td>
350
  <td align="center" style="vertical-align: middle; text-align: center">29.1</td>
351
  <td align="center" style="vertical-align: middle; text-align: center">29.7</td>
352
  <td align="center" style="vertical-align: middle; text-align: center">27.2</td>
@@ -356,7 +356,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
356
  <tr>
357
  <td align="center" style="vertical-align: middle; text-align: center">JobBench</td>
358
  <td align="center" style="vertical-align: middle; text-align: center">54.3</td>
359
- <td align="center" style="vertical-align: middle; text-align: center">57.4</td>
360
  <td align="center" style="vertical-align: middle; text-align: center">45.4</td>
361
  <td align="center" style="vertical-align: middle; text-align: center">48.4</td>
362
  <td align="center" style="vertical-align: middle; text-align: center">38.3</td>
@@ -365,7 +365,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
365
  <tr>
366
  <td align="center" style="vertical-align: middle; text-align: center">AA-Briefcase (Elo)</td>
367
  <td align="center" style="vertical-align: middle; text-align: center">1548</td>
368
- <td align="center" style="vertical-align: middle; text-align: center">1583</td>
369
  <td align="center" style="vertical-align: middle; text-align: center">1495</td>
370
  <td align="center" style="vertical-align: middle; text-align: center">1354</td>
371
  <td align="center" style="vertical-align: middle; text-align: center">1158</td>
@@ -375,7 +375,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
375
  <td align="center" style="vertical-align: middle; text-align: center">Agents' Last Exam</td>
376
  <td align="center" style="vertical-align: middle; text-align: center">28.3</td>
377
  <td align="center" style="vertical-align: middle; text-align: center">25.7<sup>†</sup></td>
378
- <td align="center" style="vertical-align: middle; text-align: center">29.6</td>
379
  <td align="center" style="vertical-align: middle; text-align: center">27.0</td>
380
  <td align="center" style="vertical-align: middle; text-align: center">26.6</td>
381
  <td align="center" style="vertical-align: middle; text-align: center">20.4</td>
@@ -383,7 +383,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
383
  <tr>
384
  <td align="center" style="vertical-align: middle; text-align: center">APEX-Agents</td>
385
  <td align="center" style="vertical-align: middle; text-align: center">41.0</td>
386
- <td align="center" style="vertical-align: middle; text-align: center">43.3</td>
387
  <td align="center" style="vertical-align: middle; text-align: center">39.9</td>
388
  <td align="center" style="vertical-align: middle; text-align: center">39.4</td>
389
  <td align="center" style="vertical-align: middle; text-align: center">38.5</td>
@@ -392,7 +392,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
392
  <tr>
393
  <td align="center" style="vertical-align: middle; text-align: center">OfficeQA Pro</td>
394
  <td align="center" style="vertical-align: middle; text-align: center">63.3</td>
395
- <td align="center" style="vertical-align: middle; text-align: center">69.9</td>
396
  <td align="center" style="vertical-align: middle; text-align: center">63.2</td>
397
  <td align="center" style="vertical-align: middle; text-align: center">63.9</td>
398
  <td align="center" style="vertical-align: middle; text-align: center">60.9</td>
@@ -400,7 +400,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
400
  </tr>
401
  <tr>
402
  <td align="center" style="vertical-align: middle; text-align: center">SpreadsheetBench 2</td>
403
- <td align="center" style="vertical-align: middle; text-align: center">34.8</td>
404
  <td align="center" style="vertical-align: middle; text-align: center">34.7</td>
405
  <td align="center" style="vertical-align: middle; text-align: center">32.4</td>
406
  <td align="center" style="vertical-align: middle; text-align: center">31.6</td>
@@ -410,7 +410,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
410
  <tr>
411
  <td align="center" style="vertical-align: middle; text-align: center">OSWorld-Verified</td>
412
  <td align="center" style="vertical-align: middle; text-align: center">84.8</td>
413
- <td align="center" style="vertical-align: middle; text-align: center">85.0</td>
414
  <td align="center" style="vertical-align: middle; text-align: center">83.0</td>
415
  <td align="center" style="vertical-align: middle; text-align: center">83.4</td>
416
  <td align="center" style="vertical-align: middle; text-align: center">79.0</td>
@@ -419,7 +419,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
419
  <tr>
420
  <td align="center" style="vertical-align: middle; text-align: center">OSWorld 2.0</td>
421
  <td align="center" style="vertical-align: middle; text-align: center">58.3</td>
422
- <td align="center" style="vertical-align: middle; text-align: center">66.1</td>
423
  <td align="center" style="vertical-align: middle; text-align: center">62.6</td>
424
  <td align="center" style="vertical-align: middle; text-align: center">55.7</td>
425
  <td align="center" style="vertical-align: middle; text-align: center">49.5</td>
@@ -429,14 +429,14 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
429
  <td align="center" style="vertical-align: middle; text-align: center">SaaS-Bench</td>
430
  <td align="center" style="vertical-align: middle; text-align: center">60.1</td>
431
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
432
- <td align="center" style="vertical-align: middle; text-align: center">61.4</td>
433
  <td align="center" style="vertical-align: middle; text-align: center">56.1</td>
434
  <td align="center" style="vertical-align: middle; text-align: center">43.8</td>
435
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
436
  </tr>
437
  <tr>
438
  <td align="center" style="vertical-align: middle; text-align: center">τ³-Banking</td>
439
- <td align="center" style="vertical-align: middle; text-align: center">33.4</td>
440
  <td align="center" style="vertical-align: middle; text-align: center">26.8</td>
441
  <td align="center" style="vertical-align: middle; text-align: center">33.0</td>
442
  <td align="center" style="vertical-align: middle; text-align: center">27.6</td>
@@ -445,7 +445,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
445
  </tr>
446
  <tr>
447
  <td align="center" style="vertical-align: middle; text-align: center">Harvey Lab-AA</td>
448
- <td align="center" style="vertical-align: middle; text-align: center">94.6</td>
449
  <td align="center" style="vertical-align: middle; text-align: center">93.6</td>
450
  <td align="center" style="vertical-align: middle; text-align: center">87.2</td>
451
  <td align="center" style="vertical-align: middle; text-align: center">91.1</td>
@@ -455,7 +455,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
455
  <tr>
456
  <td align="center" style="vertical-align: middle; text-align: center">CorpFin v2</td>
457
  <td align="center" style="vertical-align: middle; text-align: center">71.6</td>
458
- <td align="center" style="vertical-align: middle; text-align: center">71.8</td>
459
  <td align="center" style="vertical-align: middle; text-align: center">64.4</td>
460
  <td align="center" style="vertical-align: middle; text-align: center">66.7</td>
461
  <td align="center" style="vertical-align: middle; text-align: center">68.4</td>
@@ -464,7 +464,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
464
  <tr>
465
  <td align="center" style="vertical-align: middle; text-align: center">Finance Agent v2</td>
466
  <td align="center" style="vertical-align: middle; text-align: center">54.4</td>
467
- <td align="center" style="vertical-align: middle; text-align: center">56.3</td>
468
  <td align="center" style="vertical-align: middle; text-align: center">53.8</td>
469
  <td align="center" style="vertical-align: middle; text-align: center">53.9</td>
470
  <td align="center" style="vertical-align: middle; text-align: center">51.8</td>
@@ -473,7 +473,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
473
  <tr>
474
  <td align="center" style="vertical-align: middle; text-align: center">Legal Research Bench</td>
475
  <td align="center" style="vertical-align: middle; text-align: center">44.2</td>
476
- <td align="center" style="vertical-align: middle; text-align: center">49.5</td>
477
  <td align="center" style="vertical-align: middle; text-align: center">48.1</td>
478
  <td align="center" style="vertical-align: middle; text-align: center">43.8</td>
479
  <td align="center" style="vertical-align: middle; text-align: center">40.4</td>
@@ -485,7 +485,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
485
  <tr>
486
  <td align="center" style="vertical-align: middle; text-align: center">WorldVQA ForceAnswer</td>
487
  <td align="center" style="vertical-align: middle; text-align: center">51.0</td>
488
- <td align="center" style="vertical-align: middle; text-align: center">56.7</td>
489
  <td align="center" style="vertical-align: middle; text-align: center">41.8</td>
490
  <td align="center" style="vertical-align: middle; text-align: center">39.1</td>
491
  <td align="center" style="vertical-align: middle; text-align: center">38.5</td>
@@ -493,7 +493,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
493
  </tr>
494
  <tr>
495
  <td align="center" style="vertical-align: middle; text-align: center">OmniDocBench</td>
496
- <td align="center" style="vertical-align: middle; text-align: center">91.1</td>
497
  <td align="center" style="vertical-align: middle; text-align: center">89.8</td>
498
  <td align="center" style="vertical-align: middle; text-align: center">85.8</td>
499
  <td align="center" style="vertical-align: middle; text-align: center">87.9</td>
@@ -504,14 +504,14 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
504
  <td align="center" style="vertical-align: middle; text-align: center">PerceptionBench</td>
505
  <td align="center" style="vertical-align: middle; text-align: center">58.5</td>
506
  <td align="center" style="vertical-align: middle; text-align: center">57.2</td>
507
- <td align="center" style="vertical-align: middle; text-align: center">59.7</td>
508
  <td align="center" style="vertical-align: middle; text-align: center">47.2</td>
509
  <td align="center" style="vertical-align: middle; text-align: center">55.8</td>
510
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
511
  </tr>
512
  <tr>
513
  <td align="center" style="vertical-align: middle; text-align: center">Video-MME (w. sub)</td>
514
- <td align="center" style="vertical-align: middle; text-align: center">90.0</td>
515
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
516
  <td align="center" style="vertical-align: middle; text-align: center">89.5</td>
517
  <td align="center" style="vertical-align: middle; text-align: center">86.0</td>
@@ -520,7 +520,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
520
  </tr>
521
  <tr>
522
  <td align="center" style="vertical-align: middle; text-align: center">MMVU</td>
523
- <td align="center" style="vertical-align: middle; text-align: center">82.1</td>
524
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
525
  <td align="center" style="vertical-align: middle; text-align: center">81.2</td>
526
  <td align="center" style="vertical-align: middle; text-align: center">79.2</td>
@@ -530,7 +530,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
530
  <tr>
531
  <td align="center" style="vertical-align: middle; text-align: center">BabyVision w/ python</td>
532
  <td align="center" style="vertical-align: middle; text-align: center">85.7</td>
533
- <td align="center" style="vertical-align: middle; text-align: center">90.5</td>
534
  <td align="center" style="vertical-align: middle; text-align: center">88.9</td>
535
  <td align="center" style="vertical-align: middle; text-align: center">81.2</td>
536
  <td align="center" style="vertical-align: middle; text-align: center">83.6</td>
@@ -539,8 +539,8 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
539
  <tr>
540
  <td align="center" style="vertical-align: middle; text-align: center">MMMU-Pro</td>
541
  <td align="center" style="vertical-align: middle; text-align: center">81.6 / 83.4</td>
542
- <td align="center" style="vertical-align: middle; text-align: center">81.2 / 86.5</td>
543
- <td align="center" style="vertical-align: middle; text-align: center">83.0 / 84.6</td>
544
  <td align="center" style="vertical-align: middle; text-align: center">78.9 / 82.7</td>
545
  <td align="center" style="vertical-align: middle; text-align: center">81.2 / 83.2</td>
546
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
@@ -548,7 +548,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
548
  <tr>
549
  <td align="center" style="vertical-align: middle; text-align: center">CharXiv (RQ)</td>
550
  <td align="center" style="vertical-align: middle; text-align: center">84.8 / 91.3</td>
551
- <td align="center" style="vertical-align: middle; text-align: center">88.9 / 93.5</td>
552
  <td align="center" style="vertical-align: middle; text-align: center">84.6 / 89.1</td>
553
  <td align="center" style="vertical-align: middle; text-align: center">80.5 / 89.9</td>
554
  <td align="center" style="vertical-align: middle; text-align: center">84.1 / 89.0</td>
@@ -557,8 +557,8 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
557
  <tr>
558
  <td align="center" style="vertical-align: middle; text-align: center">MathVision</td>
559
  <td align="center" style="vertical-align: middle; text-align: center">94.3 / 97.8</td>
560
- <td align="center" style="vertical-align: middle; text-align: center">94.8 / 98.6</td>
561
- <td align="center" style="vertical-align: middle; text-align: center">95.8 / 97.8</td>
562
  <td align="center" style="vertical-align: middle; text-align: center">86.7 / 97.1</td>
563
  <td align="center" style="vertical-align: middle; text-align: center">92.2 / 96.8</td>
564
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
@@ -566,7 +566,7 @@ Kimi K3 is an open-weight, native multimodal agentic model and our most capable
566
  <tr>
567
  <td align="center" style="vertical-align: middle; text-align: center">ZeroBench (pass@5)</td>
568
  <td align="center" style="vertical-align: middle; text-align: center">23.0 / 41.0</td>
569
- <td align="center" style="vertical-align: middle; text-align: center">23.0 / 46.0</td>
570
  <td align="center" style="vertical-align: middle; text-align: center">17.0 / 35.0</td>
571
  <td align="center" style="vertical-align: middle; text-align: center">17.0 / 34.0</td>
572
  <td align="center" style="vertical-align: middle; text-align: center">22.0 / 41.0</td>
@@ -677,4 +677,4 @@ Both the code repository and the model weights are released under the [Kimi K3 L
677
 
678
  ## 8. Contact Us
679
 
680
- If you have any questions, please reach out at [support@moonshot.ai](mailto:support@moonshot.ai).
 
162
  <td align="center" style="vertical-align: middle; text-align: center">GPQA Diamond</td>
163
  <td align="center" style="vertical-align: middle; text-align: center">93.5</td>
164
  <td align="center" style="vertical-align: middle; text-align: center">92.6</td>
165
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>94.1</strong></td>
166
  <td align="center" style="vertical-align: middle; text-align: center">91.0</td>
167
  <td align="center" style="vertical-align: middle; text-align: center">93.5</td>
168
  <td align="center" style="vertical-align: middle; text-align: center">91.2</td>
 
171
  <td align="center" style="vertical-align: middle; text-align: center">CritPt</td>
172
  <td align="center" style="vertical-align: middle; text-align: center">23.4</td>
173
  <td align="center" style="vertical-align: middle; text-align: center">28.6</td>
174
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>32.3</strong></td>
175
  <td align="center" style="vertical-align: middle; text-align: center">20.9</td>
176
  <td align="center" style="vertical-align: middle; text-align: center">27.1</td>
177
  <td align="center" style="vertical-align: middle; text-align: center">20.9</td>
178
  </tr>
179
  <tr>
180
  <td align="center" style="vertical-align: middle; text-align: center">AA-LCR</td>
181
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>74.7</strong></td>
182
  <td align="center" style="vertical-align: middle; text-align: center">70.0</td>
183
  <td align="center" style="vertical-align: middle; text-align: center">73.7</td>
184
  <td align="center" style="vertical-align: middle; text-align: center">67.7</td>
 
188
  <tr>
189
  <td align="center" style="vertical-align: middle; text-align: center">HLE-Full</td>
190
  <td align="center" style="vertical-align: middle; text-align: center">43.5 / 56.0</td>
191
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>53.3 / 63.0</strong></td>
192
  <td align="center" style="vertical-align: middle; text-align: center">44.5 / 58.0</td>
193
  <td align="center" style="vertical-align: middle; text-align: center">49.8 / 57.9</td>
194
  <td align="center" style="vertical-align: middle; text-align: center">41.4 / 52.2</td>
 
201
  <td align="center" style="vertical-align: middle; text-align: center">DeepSWE</td>
202
  <td align="center" style="vertical-align: middle; text-align: center">67.5</td>
203
  <td align="center" style="vertical-align: middle; text-align: center">70.0</td>
204
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>73.0</strong></td>
205
  <td align="center" style="vertical-align: middle; text-align: center">59.0</td>
206
  <td align="center" style="vertical-align: middle; text-align: center">67.0</td>
207
  <td align="center" style="vertical-align: middle; text-align: center">46.2</td>
208
  </tr>
209
  <tr>
210
  <td align="center" style="vertical-align: middle; text-align: center">ProgramBench</td>
211
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>77.8</strong></td>
212
  <td align="center" style="vertical-align: middle; text-align: center">76.8</td>
213
  <td align="center" style="vertical-align: middle; text-align: center">77.6</td>
214
  <td align="center" style="vertical-align: middle; text-align: center">71.9</td>
 
219
  <td align="center" style="vertical-align: middle; text-align: center">Terminal-Bench 2.1</td>
220
  <td align="center" style="vertical-align: middle; text-align: center">88.3</td>
221
  <td align="center" style="vertical-align: middle; text-align: center">88.0</td>
222
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>88.8</strong></td>
223
  <td align="center" style="vertical-align: middle; text-align: center">84.6</td>
224
  <td align="center" style="vertical-align: middle; text-align: center">83.4</td>
225
  <td align="center" style="vertical-align: middle; text-align: center">82.7</td>
 
227
  <tr>
228
  <td align="center" style="vertical-align: middle; text-align: center">FrontierSWE</td>
229
  <td align="center" style="vertical-align: middle; text-align: center">81.2</td>
230
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>86.6</strong></td>
231
  <td align="center" style="vertical-align: middle; text-align: center">71.3</td>
232
  <td align="center" style="vertical-align: middle; text-align: center">66.7</td>
233
  <td align="center" style="vertical-align: middle; text-align: center">64.9</td>
 
235
  </tr>
236
  <tr>
237
  <td align="center" style="vertical-align: middle; text-align: center">SWE-Marathon</td>
238
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>42.0</strong></td>
239
  <td align="center" style="vertical-align: middle; text-align: center">35.0</td>
240
  <td align="center" style="vertical-align: middle; text-align: center">39.0</td>
241
  <td align="center" style="vertical-align: middle; text-align: center">40.0</td>
 
245
  <tr>
246
  <td align="center" style="vertical-align: middle; text-align: center">PostTrainBench</td>
247
  <td align="center" style="vertical-align: middle; text-align: center">36.6</td>
248
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>41.4</strong></td>
249
  <td align="center" style="vertical-align: middle; text-align: center">34.6</td>
250
  <td align="center" style="vertical-align: middle; text-align: center">34.1</td>
251
  <td align="center" style="vertical-align: middle; text-align: center">28.4</td>
 
254
  <tr>
255
  <td align="center" style="vertical-align: middle; text-align: center">MLS-Bench-Lite</td>
256
  <td align="center" style="vertical-align: middle; text-align: center">48.3</td>
257
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>49.9</strong></td>
258
  <td align="center" style="vertical-align: middle; text-align: center">46.2</td>
259
  <td align="center" style="vertical-align: middle; text-align: center">42.8</td>
260
  <td align="center" style="vertical-align: middle; text-align: center">35.5</td>
 
263
  <tr>
264
  <td align="center" style="vertical-align: middle; text-align: center">SciCode</td>
265
  <td align="center" style="vertical-align: middle; text-align: center">58.7</td>
266
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>60.2</strong></td>
267
  <td align="center" style="vertical-align: middle; text-align: center">56.1</td>
268
  <td align="center" style="vertical-align: middle; text-align: center">53.5</td>
269
  <td align="center" style="vertical-align: middle; text-align: center">56.1</td>
 
272
  <tr>
273
  <td align="center" style="vertical-align: middle; text-align: center">Kimi Code Bench 2.0</td>
274
  <td align="center" style="vertical-align: middle; text-align: center">72.9</td>
275
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>76.9</strong></td>
276
  <td align="center" style="vertical-align: middle; text-align: center">64.8</td>
277
  <td align="center" style="vertical-align: middle; text-align: center">71.7</td>
278
  <td align="center" style="vertical-align: middle; text-align: center">69.0</td>
 
283
  </tr>
284
  <tr>
285
  <td align="center" style="vertical-align: middle; text-align: center">BrowseComp</td>
286
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>91.2</strong></td>
287
  <td align="center" style="vertical-align: middle; text-align: center">88.0</td>
288
  <td align="center" style="vertical-align: middle; text-align: center">90.4</td>
289
  <td align="center" style="vertical-align: middle; text-align: center">84.3</td>
 
292
  </tr>
293
  <tr>
294
  <td align="center" style="vertical-align: middle; text-align: center">DeepSearchQA (F1)</td>
295
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>95.0</strong></td>
296
  <td align="center" style="vertical-align: middle; text-align: center">94.2</td>
297
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
298
  <td align="center" style="vertical-align: middle; text-align: center">93.1</td>
 
301
  </tr>
302
  <tr>
303
  <td align="center" style="vertical-align: middle; text-align: center">ResearchRubrics</td>
304
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>76.2</strong></td>
305
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
306
  <td align="center" style="vertical-align: middle; text-align: center">73.8</td>
307
  <td align="center" style="vertical-align: middle; text-align: center">73.5</td>
 
311
  <tr>
312
  <td align="center" style="vertical-align: middle; text-align: center">GDPval-AA v2 (Elo)</td>
313
  <td align="center" style="vertical-align: middle; text-align: center">1686</td>
314
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>1747</strong></td>
315
  <td align="center" style="vertical-align: middle; text-align: center">1736</td>
316
  <td align="center" style="vertical-align: middle; text-align: center">1593</td>
317
  <td align="center" style="vertical-align: middle; text-align: center">1491</td>
 
320
  <tr>
321
  <td align="center" style="vertical-align: middle; text-align: center">Toolathlon-Verified</td>
322
  <td align="center" style="vertical-align: middle; text-align: center">76.5</td>
323
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>77.9</strong></td>
324
  <td align="center" style="vertical-align: middle; text-align: center">74.9</td>
325
  <td align="center" style="vertical-align: middle; text-align: center">76.2</td>
326
  <td align="center" style="vertical-align: middle; text-align: center">73.5</td>
 
328
  </tr>
329
  <tr>
330
  <td align="center" style="vertical-align: middle; text-align: center">MCPMark-Verified</td>
331
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>94.5</strong></td>
332
  <td align="center" style="vertical-align: middle; text-align: center">87.4</td>
333
  <td align="center" style="vertical-align: middle; text-align: center">92.9</td>
334
  <td align="center" style="vertical-align: middle; text-align: center">76.4</td>
 
338
  <tr>
339
  <td align="center" style="vertical-align: middle; text-align: center">MCP-Atlas</td>
340
  <td align="center" style="vertical-align: middle; text-align: center">84.2</td>
341
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>84.7</strong></td>
342
  <td align="center" style="vertical-align: middle; text-align: center">83.6</td>
343
  <td align="center" style="vertical-align: middle; text-align: center">83.6</td>
344
  <td align="center" style="vertical-align: middle; text-align: center">82.8</td>
 
346
  </tr>
347
  <tr>
348
  <td align="center" style="vertical-align: middle; text-align: center">AutomationBench</td>
349
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>30.8</strong></td>
350
  <td align="center" style="vertical-align: middle; text-align: center">29.1</td>
351
  <td align="center" style="vertical-align: middle; text-align: center">29.7</td>
352
  <td align="center" style="vertical-align: middle; text-align: center">27.2</td>
 
356
  <tr>
357
  <td align="center" style="vertical-align: middle; text-align: center">JobBench</td>
358
  <td align="center" style="vertical-align: middle; text-align: center">54.3</td>
359
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>57.4</strong></td>
360
  <td align="center" style="vertical-align: middle; text-align: center">45.4</td>
361
  <td align="center" style="vertical-align: middle; text-align: center">48.4</td>
362
  <td align="center" style="vertical-align: middle; text-align: center">38.3</td>
 
365
  <tr>
366
  <td align="center" style="vertical-align: middle; text-align: center">AA-Briefcase (Elo)</td>
367
  <td align="center" style="vertical-align: middle; text-align: center">1548</td>
368
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>1583</strong></td>
369
  <td align="center" style="vertical-align: middle; text-align: center">1495</td>
370
  <td align="center" style="vertical-align: middle; text-align: center">1354</td>
371
  <td align="center" style="vertical-align: middle; text-align: center">1158</td>
 
375
  <td align="center" style="vertical-align: middle; text-align: center">Agents' Last Exam</td>
376
  <td align="center" style="vertical-align: middle; text-align: center">28.3</td>
377
  <td align="center" style="vertical-align: middle; text-align: center">25.7<sup>†</sup></td>
378
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>29.6</strong></td>
379
  <td align="center" style="vertical-align: middle; text-align: center">27.0</td>
380
  <td align="center" style="vertical-align: middle; text-align: center">26.6</td>
381
  <td align="center" style="vertical-align: middle; text-align: center">20.4</td>
 
383
  <tr>
384
  <td align="center" style="vertical-align: middle; text-align: center">APEX-Agents</td>
385
  <td align="center" style="vertical-align: middle; text-align: center">41.0</td>
386
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>43.3</strong></td>
387
  <td align="center" style="vertical-align: middle; text-align: center">39.9</td>
388
  <td align="center" style="vertical-align: middle; text-align: center">39.4</td>
389
  <td align="center" style="vertical-align: middle; text-align: center">38.5</td>
 
392
  <tr>
393
  <td align="center" style="vertical-align: middle; text-align: center">OfficeQA Pro</td>
394
  <td align="center" style="vertical-align: middle; text-align: center">63.3</td>
395
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>69.9</strong></td>
396
  <td align="center" style="vertical-align: middle; text-align: center">63.2</td>
397
  <td align="center" style="vertical-align: middle; text-align: center">63.9</td>
398
  <td align="center" style="vertical-align: middle; text-align: center">60.9</td>
 
400
  </tr>
401
  <tr>
402
  <td align="center" style="vertical-align: middle; text-align: center">SpreadsheetBench 2</td>
403
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>34.8</strong></td>
404
  <td align="center" style="vertical-align: middle; text-align: center">34.7</td>
405
  <td align="center" style="vertical-align: middle; text-align: center">32.4</td>
406
  <td align="center" style="vertical-align: middle; text-align: center">31.6</td>
 
410
  <tr>
411
  <td align="center" style="vertical-align: middle; text-align: center">OSWorld-Verified</td>
412
  <td align="center" style="vertical-align: middle; text-align: center">84.8</td>
413
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>85.0</strong></td>
414
  <td align="center" style="vertical-align: middle; text-align: center">83.0</td>
415
  <td align="center" style="vertical-align: middle; text-align: center">83.4</td>
416
  <td align="center" style="vertical-align: middle; text-align: center">79.0</td>
 
419
  <tr>
420
  <td align="center" style="vertical-align: middle; text-align: center">OSWorld 2.0</td>
421
  <td align="center" style="vertical-align: middle; text-align: center">58.3</td>
422
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>66.1</strong></td>
423
  <td align="center" style="vertical-align: middle; text-align: center">62.6</td>
424
  <td align="center" style="vertical-align: middle; text-align: center">55.7</td>
425
  <td align="center" style="vertical-align: middle; text-align: center">49.5</td>
 
429
  <td align="center" style="vertical-align: middle; text-align: center">SaaS-Bench</td>
430
  <td align="center" style="vertical-align: middle; text-align: center">60.1</td>
431
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
432
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>61.4</strong></td>
433
  <td align="center" style="vertical-align: middle; text-align: center">56.1</td>
434
  <td align="center" style="vertical-align: middle; text-align: center">43.8</td>
435
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
436
  </tr>
437
  <tr>
438
  <td align="center" style="vertical-align: middle; text-align: center">τ³-Banking</td>
439
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>33.4</strong></td>
440
  <td align="center" style="vertical-align: middle; text-align: center">26.8</td>
441
  <td align="center" style="vertical-align: middle; text-align: center">33.0</td>
442
  <td align="center" style="vertical-align: middle; text-align: center">27.6</td>
 
445
  </tr>
446
  <tr>
447
  <td align="center" style="vertical-align: middle; text-align: center">Harvey Lab-AA</td>
448
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>94.6</strong></td>
449
  <td align="center" style="vertical-align: middle; text-align: center">93.6</td>
450
  <td align="center" style="vertical-align: middle; text-align: center">87.2</td>
451
  <td align="center" style="vertical-align: middle; text-align: center">91.1</td>
 
455
  <tr>
456
  <td align="center" style="vertical-align: middle; text-align: center">CorpFin v2</td>
457
  <td align="center" style="vertical-align: middle; text-align: center">71.6</td>
458
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>71.8</strong></td>
459
  <td align="center" style="vertical-align: middle; text-align: center">64.4</td>
460
  <td align="center" style="vertical-align: middle; text-align: center">66.7</td>
461
  <td align="center" style="vertical-align: middle; text-align: center">68.4</td>
 
464
  <tr>
465
  <td align="center" style="vertical-align: middle; text-align: center">Finance Agent v2</td>
466
  <td align="center" style="vertical-align: middle; text-align: center">54.4</td>
467
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>56.3</strong></td>
468
  <td align="center" style="vertical-align: middle; text-align: center">53.8</td>
469
  <td align="center" style="vertical-align: middle; text-align: center">53.9</td>
470
  <td align="center" style="vertical-align: middle; text-align: center">51.8</td>
 
473
  <tr>
474
  <td align="center" style="vertical-align: middle; text-align: center">Legal Research Bench</td>
475
  <td align="center" style="vertical-align: middle; text-align: center">44.2</td>
476
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>49.5</strong></td>
477
  <td align="center" style="vertical-align: middle; text-align: center">48.1</td>
478
  <td align="center" style="vertical-align: middle; text-align: center">43.8</td>
479
  <td align="center" style="vertical-align: middle; text-align: center">40.4</td>
 
485
  <tr>
486
  <td align="center" style="vertical-align: middle; text-align: center">WorldVQA ForceAnswer</td>
487
  <td align="center" style="vertical-align: middle; text-align: center">51.0</td>
488
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>56.7</strong></td>
489
  <td align="center" style="vertical-align: middle; text-align: center">41.8</td>
490
  <td align="center" style="vertical-align: middle; text-align: center">39.1</td>
491
  <td align="center" style="vertical-align: middle; text-align: center">38.5</td>
 
493
  </tr>
494
  <tr>
495
  <td align="center" style="vertical-align: middle; text-align: center">OmniDocBench</td>
496
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>91.1</strong></td>
497
  <td align="center" style="vertical-align: middle; text-align: center">89.8</td>
498
  <td align="center" style="vertical-align: middle; text-align: center">85.8</td>
499
  <td align="center" style="vertical-align: middle; text-align: center">87.9</td>
 
504
  <td align="center" style="vertical-align: middle; text-align: center">PerceptionBench</td>
505
  <td align="center" style="vertical-align: middle; text-align: center">58.5</td>
506
  <td align="center" style="vertical-align: middle; text-align: center">57.2</td>
507
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>59.7</strong></td>
508
  <td align="center" style="vertical-align: middle; text-align: center">47.2</td>
509
  <td align="center" style="vertical-align: middle; text-align: center">55.8</td>
510
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
511
  </tr>
512
  <tr>
513
  <td align="center" style="vertical-align: middle; text-align: center">Video-MME (w. sub)</td>
514
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>90.0</strong></td>
515
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
516
  <td align="center" style="vertical-align: middle; text-align: center">89.5</td>
517
  <td align="center" style="vertical-align: middle; text-align: center">86.0</td>
 
520
  </tr>
521
  <tr>
522
  <td align="center" style="vertical-align: middle; text-align: center">MMVU</td>
523
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>82.1</strong></td>
524
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
525
  <td align="center" style="vertical-align: middle; text-align: center">81.2</td>
526
  <td align="center" style="vertical-align: middle; text-align: center">79.2</td>
 
530
  <tr>
531
  <td align="center" style="vertical-align: middle; text-align: center">BabyVision w/ python</td>
532
  <td align="center" style="vertical-align: middle; text-align: center">85.7</td>
533
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>90.5</strong></td>
534
  <td align="center" style="vertical-align: middle; text-align: center">88.9</td>
535
  <td align="center" style="vertical-align: middle; text-align: center">81.2</td>
536
  <td align="center" style="vertical-align: middle; text-align: center">83.6</td>
 
539
  <tr>
540
  <td align="center" style="vertical-align: middle; text-align: center">MMMU-Pro</td>
541
  <td align="center" style="vertical-align: middle; text-align: center">81.6 / 83.4</td>
542
+ <td align="center" style="vertical-align: middle; text-align: center">81.2 / <strong>86.5</strong></td>
543
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>83.0</strong> / 84.6</td>
544
  <td align="center" style="vertical-align: middle; text-align: center">78.9 / 82.7</td>
545
  <td align="center" style="vertical-align: middle; text-align: center">81.2 / 83.2</td>
546
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
 
548
  <tr>
549
  <td align="center" style="vertical-align: middle; text-align: center">CharXiv (RQ)</td>
550
  <td align="center" style="vertical-align: middle; text-align: center">84.8 / 91.3</td>
551
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>88.9 / 93.5</strong></td>
552
  <td align="center" style="vertical-align: middle; text-align: center">84.6 / 89.1</td>
553
  <td align="center" style="vertical-align: middle; text-align: center">80.5 / 89.9</td>
554
  <td align="center" style="vertical-align: middle; text-align: center">84.1 / 89.0</td>
 
557
  <tr>
558
  <td align="center" style="vertical-align: middle; text-align: center">MathVision</td>
559
  <td align="center" style="vertical-align: middle; text-align: center">94.3 / 97.8</td>
560
+ <td align="center" style="vertical-align: middle; text-align: center">94.8 / <strong>98.6</strong></td>
561
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>95.8</strong> / 97.8</td>
562
  <td align="center" style="vertical-align: middle; text-align: center">86.7 / 97.1</td>
563
  <td align="center" style="vertical-align: middle; text-align: center">92.2 / 96.8</td>
564
  <td align="center" style="vertical-align: middle; text-align: center">—</td>
 
566
  <tr>
567
  <td align="center" style="vertical-align: middle; text-align: center">ZeroBench (pass@5)</td>
568
  <td align="center" style="vertical-align: middle; text-align: center">23.0 / 41.0</td>
569
+ <td align="center" style="vertical-align: middle; text-align: center"><strong>23.0 / 46.0</strong></td>
570
  <td align="center" style="vertical-align: middle; text-align: center">17.0 / 35.0</td>
571
  <td align="center" style="vertical-align: middle; text-align: center">17.0 / 34.0</td>
572
  <td align="center" style="vertical-align: middle; text-align: center">22.0 / 41.0</td>
 
677
 
678
  ## 8. Contact Us
679
 
680
+ If you have any questions, please reach out at [support@moonshot.ai](mailto:support@moonshot.ai).