mx1 commited on
Commit
9837a93
·
verified ·
1 Parent(s): f9d99bd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -0
README.md CHANGED
@@ -24,11 +24,17 @@ Trained on __20T+ tokens of high-quality data__, together with __supervised fine
24
  ### Powerful Complex Reasoning Abilities
25
 
26
  We conducted a comprehensive evaluation of Ling-flash-2.0’s reasoning capabilities, reporting strong results on representative benchmarks:
 
27
  ● __Multi-disciplinary knowledge reasoning__: GPQA-Diamond, MMLU-Pro
 
28
  ● __Advanced mathematical reasoning__: AIME 2025, Omni-MATH, OptMATH (advanced mathematical optimization tasks)
 
29
  ● __Challenging code generation__: LiveCodeBench v6, CodeForces-Elo
 
30
  ● __Logical reasoning__: KOR-Bench, ARC-Prize
 
31
  ● __Key regulated industries (Finance, Healthcare)__: FinanceReasoning, HealthBench
 
32
  Compared with __dense models under 40B__ (e.g., Qwen3-32B-Non-Thinking, Seed-OSS-36B-Instruct (think budget=0)) and __larger-activation/total-parameter MoE models__ (e.g., Hunyuan-A13B-Instruct, GPT-OSS-120B/low), __Ling-flash-2.0__ demonstrates stronger complex reasoning power. Moreover, it shows high competitiveness on __creative tasks__ (Creative Writing v3).
33
  <p align="center">
34
  <img src="https://mdn.alipayobjects.com/huamei_fi95qp/afts/img/zxAvQ7QtrAwAAAAAQqAAAAgADkZ7AQFr/fmt.webp"/>
 
24
  ### Powerful Complex Reasoning Abilities
25
 
26
  We conducted a comprehensive evaluation of Ling-flash-2.0’s reasoning capabilities, reporting strong results on representative benchmarks:
27
+
28
  ● __Multi-disciplinary knowledge reasoning__: GPQA-Diamond, MMLU-Pro
29
+
30
  ● __Advanced mathematical reasoning__: AIME 2025, Omni-MATH, OptMATH (advanced mathematical optimization tasks)
31
+
32
  ● __Challenging code generation__: LiveCodeBench v6, CodeForces-Elo
33
+
34
  ● __Logical reasoning__: KOR-Bench, ARC-Prize
35
+
36
  ● __Key regulated industries (Finance, Healthcare)__: FinanceReasoning, HealthBench
37
+
38
  Compared with __dense models under 40B__ (e.g., Qwen3-32B-Non-Thinking, Seed-OSS-36B-Instruct (think budget=0)) and __larger-activation/total-parameter MoE models__ (e.g., Hunyuan-A13B-Instruct, GPT-OSS-120B/low), __Ling-flash-2.0__ demonstrates stronger complex reasoning power. Moreover, it shows high competitiveness on __creative tasks__ (Creative Writing v3).
39
  <p align="center">
40
  <img src="https://mdn.alipayobjects.com/huamei_fi95qp/afts/img/zxAvQ7QtrAwAAAAAQqAAAAgADkZ7AQFr/fmt.webp"/>