deepseek-v4.1-flash

Overall

74.8

/ 100

Tasks

500/500

task suite

Avg latency

26657ms

round trip

Tokens used

14678

during evaluation

Per-category results

arithmetic 99.09 / 100

coding_light 66.25 / 100

data_manipulation 90.0 / 100

extraction 20.0 / 100

instruction_following 100.0 / 100

knowledge 85.0 / 100

language 51.43 / 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 model page →

Sample task outputs (first 60 of 500)

#	Category	Result	Latency	Reply
1	arithmetic	✓	1366 ms	4195
2	arithmetic	✓	1418 ms	365
3	arithmetic	✓	1404 ms	3900
4	arithmetic	✓	1436 ms	2122
5	arithmetic	✓	1387 ms	19430
6	arithmetic	✓	1410 ms	236
7	arithmetic	✓	1458 ms	4185
8	arithmetic	✓	2674 ms	12502
9	arithmetic	✓	1999 ms	42693
10	arithmetic	✓	1985 ms	27216
11	arithmetic	✓	2077 ms	4583
12	arithmetic	✓	1994 ms	15634
13	arithmetic	✓	2068 ms	3756
14	arithmetic	✓	2161 ms	35
15	arithmetic	✓	2194 ms	326
16	arithmetic	✓	2616 ms	12029
17	arithmetic	✓	2577 ms	82
18	arithmetic	✓	2628 ms	239
19	arithmetic	✓	2786 ms	2727
20	arithmetic	✓	2633 ms	30590
21	arithmetic	✓	2788 ms	3001
22	arithmetic	✓	2869 ms	137
23	arithmetic	✓	3146 ms	1393
24	arithmetic	✓	3226 ms	23650
25	arithmetic	✓	3229 ms	4050
26	arithmetic	✓	3223 ms	5
27	arithmetic	✓	3242 ms	30848
28	arithmetic	✓	3391 ms	7341
29	arithmetic	✓	3323 ms	140
30	arithmetic	✓	3722 ms	7747
31	arithmetic	✓	3789 ms	1778
32	arithmetic	✓	3841 ms	2828
33	arithmetic	✓	3937 ms	1096
34	arithmetic	✓	3839 ms	140
35	arithmetic	✓	3800 ms	12240
36	arithmetic	✓	3896 ms	9612
37	arithmetic	✓	4039 ms	302
38	arithmetic	✓	4564 ms	5063
39	arithmetic	✓	4817 ms	3272
40	arithmetic	✓	4534 ms	334
41	arithmetic	✓	4519 ms	24960
42	arithmetic	✓	4505 ms	263
43	arithmetic	✓	4524 ms	38
44	arithmetic	✓	4584 ms	14989
45	arithmetic	✓	4478 ms	4069
46	arithmetic	✓	5011 ms	3412
47	arithmetic	✓	5100 ms	7215
48	arithmetic	✓	5015 ms	261
49	arithmetic	✓	5103 ms	108
50	arithmetic	✓	5061 ms	231
51	arithmetic	✓	5120 ms	24060
52	arithmetic	✓	5114 ms	1443
53	arithmetic	✓	5367 ms	13617
54	arithmetic	✓	5934 ms	19228
55	arithmetic	✓	5645 ms	18760
56	arithmetic	✓	5679 ms	5286
57	arithmetic	✓	6201 ms	281
58	arithmetic	✓	5650 ms	42816
59	arithmetic	✓	6457 ms	4326
60	arithmetic	✓	5708 ms	8552