kimi-k3

Overall

79.4

/ 100

Tasks

500/500

task suite

Avg latency

49397ms

round trip

Tokens used

96607

during evaluation

Per-category results

arithmetic 100.0 / 100

coding_light 75.0 / 100

data_manipulation 95.71 / 100

extraction 30.0 / 100

instruction_following 100.0 / 100

knowledge 85.0 / 100

language 58.57 / 100

Strongest category: language

About the suite

Fikra Eval 500 is one deterministic 500-task platform evaluation generated from a fixed seed: 110 arithmetic, 60 knowledge, 80 coding-light, 70 data manipulation, 70 language, 60 extraction and 50 instruction-following tasks. Same tasks every model, automatic scoring, published exactly when 500/500 completes.

suite :: fikra-eval-500 / v1

kimi-k3 model page →

Sample task outputs (first 60 of 500)

#	Category	Result	Latency	Reply
1	arithmetic	✓	1801 ms	4195
2	arithmetic	✓	1408 ms	365
3	arithmetic	✓	1563 ms	3900
4	arithmetic	✓	1376 ms	2122
5	arithmetic	✓	1336 ms	19430
6	arithmetic	✓	1639 ms	236
7	arithmetic	✓	1365 ms	4185
8	arithmetic	✓	1549 ms	12502
9	arithmetic	✓	3161 ms	42693
10	arithmetic	✓	2450 ms	27216
11	arithmetic	✓	2481 ms	4583
12	arithmetic	✓	2795 ms	15634
13	arithmetic	✓	2867 ms	3756
14	arithmetic	✓	2812 ms	35
15	arithmetic	✓	2810 ms	326
16	arithmetic	✓	2958 ms	12029
17	arithmetic	✓	3787 ms	82
18	arithmetic	✓	3854 ms	239
19	arithmetic	✓	4316 ms	2727
20	arithmetic	✓	3750 ms	30590
21	arithmetic	✓	3788 ms	3001
22	arithmetic	✓	4388 ms	137
23	arithmetic	✓	3924 ms	1393
24	arithmetic	✓	4684 ms	23650
25	arithmetic	✓	4840 ms	4050
26	arithmetic	✓	4748 ms	5
27	arithmetic	✓	5076 ms	30848
28	arithmetic	✓	5251 ms	7341
29	arithmetic	✓	5064 ms	140
30	arithmetic	✓	5230 ms	7747
31	arithmetic	✓	5459 ms	1778
32	arithmetic	✓	5694 ms	2828
33	arithmetic	✓	5603 ms	1096
34	arithmetic	✓	5892 ms	140
35	arithmetic	✓	6060 ms	12240
36	arithmetic	✓	6516 ms	9612
37	arithmetic	✓	6311 ms	302
38	arithmetic	✓	6307 ms	5063
39	arithmetic	✓	6409 ms	3272
40	arithmetic	✓	7686 ms	334
41	arithmetic	✓	6719 ms	24960
42	arithmetic	✓	7269 ms	263
43	arithmetic	✓	7367 ms	38
44	arithmetic	✓	7689 ms	14989
45	arithmetic	✓	7434 ms	4069
46	arithmetic	✓	8303 ms	3412
47	arithmetic	✓	7653 ms	7215
48	arithmetic	✓	7618 ms	261
49	arithmetic	✓	8575 ms	108
50	arithmetic	✓	8741 ms	231
51	arithmetic	✓	8736 ms	24060
52	arithmetic	✓	8920 ms	1443
53	arithmetic	✓	8740 ms	13617
54	arithmetic	✓	8820 ms	19228
55	arithmetic	✓	8784 ms	18760
56	arithmetic	✓	9520 ms	5286
57	arithmetic	✓	9722 ms	281
58	arithmetic	✓	10221 ms	42816
59	arithmetic	✓	9791 ms	4326
60	arithmetic	✓	10269 ms	8552