Tool-Calling LLMs — Page 935

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-6

qwen25-saudi-v2

group_model

group_model

Llama-3.1-8B-Instruct_grpo_aspo_rollout_8_kl_0.001_20260521_200940_step290

multilingual_model

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-7

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-1

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-10

Qwen2.5-Math-7B_grpo_aspo_rollout_8_ent_0.0_kl_True_0.001_20260521_202036_step580

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-5

general_knowledge_model

code_no_think_8_qwen3_4b_instruct_sft

sac-gspo-cl3e3-drgrpo-qwen25-math-1.5b-step1500

fgrpo-gspo-cl3e3-qwen25-math-1.5b-step751

qwen3-1.7b-summarization-arxiv-full

fgrpo-gspo-cl3e3-drgrpo-qwen25-math-1.5b-run9-step900

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-2

math_model

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step881-aime24-40pct

bm2_cs7_fixed_v1

sage-qwen3-4b-code-coevolve-solver-phase-5

sage-qwen3-4b-code-coevolve-gen-phase-5

general_knowledge_model

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step741-aime24-38pct

sage-qwen3-4b-code-coevolve-solver-phase-20

general_knowledge_model

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step761-aime24-38pct

Llama-3.2-3B-GSPO-cl3e3-DrGRPO-Step561-BestPass1-DeepScaleR-AIME24

fixedcl28-qwen25-math-1.5b-step450

fixedcl28-qwen25-math-1.5b-step455

grpo-3b

Qwen_Qwen3-4B-Thinking-2507_fp3-e2m0_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

sac-gspo-cl3e3-drgrpo-r1distill-qwen1.5b-24k-temp1-step1061-aime24-43pct

qwen3_8b_clipcov_baseline_solver_v5

qwen3_8b_vdrop75_solver_v5

qwen3_4b_klcov_baseline_solver_v2

qwen2.5-7B-it-dpo-abstention-high-lr

qwen3_8b_klcov_baseline_solver_v1

qwen3_8b_klcov_baseline_solver_v2

qwen3_4b_clipcov_baseline_solver_v3

qwen3_4b_klcov_baseline_solver_v4