deepseek-v4.1-flash-1017

Overall

77.8

/ 100

Tasks

500/500

task suite

Avg latency

43010ms

round trip

Tokens used

14789

during evaluation

Per-category results

arithmetic 97.27 / 100

coding_light 70.0 / 100

data_manipulation 91.43 / 100

extraction 15.0 / 100

instruction_following 100.0 / 100

knowledge 83.33 / 100

language 75.71 / 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

deepseek-v4.1-flash-1017 model page →

Sample task outputs (first 60 of 500)

#	Category	Result	Latency	Reply
1	arithmetic	✓	1344 ms	4195
2	arithmetic	✓	2398 ms	365
3	arithmetic	✓	1627 ms	3900
4	arithmetic	✓	1767 ms	2122
5	arithmetic	✓	1379 ms	19430
6	arithmetic	✓	2375 ms	236
7	arithmetic	✓	1735 ms	4185
8	arithmetic	✓	1284 ms	12502
9	arithmetic	✓	2425 ms	42693
10	arithmetic	✓	2095 ms	27216
11	arithmetic	✓	2497 ms	4583
12	arithmetic	✓	3147 ms	15634
13	arithmetic	✓	3199 ms	3756
14	arithmetic	✓	2907 ms	35
15	arithmetic	✓	3492 ms	326
16	arithmetic	✓	3789 ms	12029
17	arithmetic	✓	3744 ms	82
18	arithmetic	✓	3522 ms	239
19	arithmetic	✓	4116 ms	2727
20	arithmetic	✓	4032 ms	30590
21	arithmetic	✓	4694 ms	3001
22	arithmetic	✓	4830 ms	137
23	arithmetic	✓	4793 ms	1393
24	arithmetic	✓	4698 ms	23650
25	arithmetic	✓	4878 ms	4050
26	arithmetic	✓	4666 ms	5
27	arithmetic	✓	5220 ms	30848
28	arithmetic	✓	5640 ms	7341
29	arithmetic	✓	5944 ms	140
30	arithmetic	✓	5474 ms	7747
31	arithmetic	✓	5978 ms	1778
32	arithmetic	✓	6459 ms	2828
33	arithmetic	✓	6788 ms	1096
34	arithmetic	✓	6479 ms	140
35	arithmetic	✓	6672 ms	12240
36	arithmetic	✓	6719 ms	9612
37	arithmetic	✓	6759 ms	302
38	arithmetic	✓	7131 ms	5063
39	arithmetic	✓	7121 ms	3272
40	arithmetic	✓	7928 ms	334
41	arithmetic	✓	7698 ms	24960
42	arithmetic	✓	8012 ms	263
43	arithmetic	✓	7815 ms	38
44	arithmetic	✓	8036 ms	14989
45	arithmetic	✓	7722 ms	4069
46	arithmetic	✓	7972 ms	3412
47	arithmetic	✓	8218 ms	7215
48	arithmetic	✓	8915 ms	261
49	arithmetic	✓	8930 ms	108
50	arithmetic	✓	9403 ms	231
51	arithmetic	✓	9201 ms	24060
52	arithmetic	✓	9190 ms	1443
53	arithmetic	✓	9414 ms	13617
54	arithmetic	✓	9427 ms	19228
55	arithmetic	✓	9215 ms	18760
56	arithmetic	✓	10164 ms	5286
57	arithmetic	✓	10258 ms	281
58	arithmetic	✓	10058 ms	42816
59	arithmetic	✓	10234 ms	4326
60	arithmetic	✓	10151 ms	8552